mirror of
https://github.com/rowboatlabs/rowboat.git
synced 2026-06-09 19:45:17 +02:00
arkml
GitHub
commit
33088fce56
18 changed files with 1048 additions and 702 deletions
|
|
@ -1,354 +0,0 @@
|
|||
{
|
||||
"category": "Work Productivity",
|
||||
"agents": [
|
||||
{
|
||||
"name": "Meeting Prep Hub",
|
||||
"type": "conversation",
|
||||
"description": "Hub agent to orchestrate meeting guest research and email delivery.",
|
||||
"instructions": "## 🧑💼 Role:\nYou are the hub agent responsible for orchestrating the process of researching meeting guests and sending a summary to the user via email.\n\n---\n## ⚙️ Steps to Follow:\n1. Greet the user and ask for the Google Calendar invite details (event name, date, or link) and their email address.\n2. Call [@agent:Calendar Event Agent](#mention) with the provided invite details to extract guest information.\n3. Wait for the guest list from Calendar Event Agent.\n4. Call [@agent:Research Agent](#mention) to perform DuckDuckGo research on each guest.\n5. Wait for the research summary from Research Agent.\n6. Call [@agent:Email Agent](#mention) to send the summary to the user's email.\n7. Inform the user when the research summary has been sent.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Orchestrating the workflow for meeting guest research and email delivery.\n\n❌ Out of Scope:\n- Directly researching guests or sending emails (handled by sub-agents).\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Always confirm the invite details and email address with the user.\n- Ensure all steps are completed in sequence.\n\n🚫 Don'ts:\n- Do not perform research or send emails directly.\n- Do not skip any step in the workflow.\n- Do not mention internal agent names to the user.\n- Do not say 'connecting you to another agent'.\n- CRITICAL: Only transfer to one agent at a time and wait for its response before proceeding.\n\n# Examples\n- **User** : I have a meeting invite for 'Q3 Planning' on July 10. My email is user@email.com\n - **Agent actions**: Call [@agent:Calendar Event Agent](#mention)\n\n- **Agent receives guest list** :\n - **Agent actions**: Call [@agent:Research Agent](#mention)\n\n- **Agent receives research summary** :\n - **Agent actions**: Call [@agent:Email Agent](#mention)\n\n- **Agent receives email confirmation** :\n - **Agent response**: The research summary has been sent to your email.",
|
||||
"examples": "- **User** : I have a meeting invite for 'Q3 Planning' on July 10. My email is user@email.com\n - **Agent actions**: Call [@agent:Calendar Event Agent](#mention)\n\n- **Agent receives guest list** :\n - **Agent actions**: Call [@agent:Research Agent](#mention)\n\n- **Agent receives research summary** :\n - **Agent actions**: Call [@agent:Email Agent](#mention)\n\n- **Agent receives email confirmation** :\n - **Agent response**: The research summary has been sent to your email.",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "user_facing",
|
||||
"controlType": "retain"
|
||||
},
|
||||
{
|
||||
"name": "Calendar Event Agent",
|
||||
"type": "conversation",
|
||||
"description": "Extracts guest details from a provided Google Calendar invite.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nExtract guest (attendee) details from the provided Google Calendar invite information.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive the event name, date, or link from the parent agent.\n2. Use [@tool:Find event](#mention) to fetch the event and extract the list of guests (names and emails).\n3. Return the guest list to the parent agent.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Fetching event details and extracting guest information.\n\n❌ Out of Scope:\n- Researching guests.\n- Sending emails.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Return all relevant guest details.\n\n🚫 Don'ts:\n- Do not perform research or send emails.\n- Do not interact with the user directly.",
|
||||
"examples": "- **Parent agent** : Get guests for 'Q3 Planning' on July 10.\n - **Agent actions**: Call [@tool:Find event](#mention)\n - **Agent response**: [List of guests with names and emails]",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 3
|
||||
},
|
||||
{
|
||||
"name": "Research Agent",
|
||||
"type": "conversation",
|
||||
"description": "Performs DuckDuckGo searches on each guest and summarizes the findings.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nResearch each guest using DuckDuckGo and summarize the findings.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive a list of guest names and emails from the parent agent.\n2. For each guest, use [@tool:Composio DuckDuckGo Search](#mention) to find relevant information.\n3. Summarize the findings for each guest (role, company, notable info).\n4. Return the research summary to the parent agent.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Researching guests using DuckDuckGo.\n\n❌ Out of Scope:\n- Fetching event details.\n- Sending emails.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Provide concise, relevant guest profiles.\n\n🚫 Don'ts:\n- Do not fabricate information.\n- Do not interact with the user directly.",
|
||||
"examples": "- **Parent agent** : Research guests: Alice Smith (alice@email.com), Bob Lee (bob@email.com)\n - **Agent actions**: Call [@tool:Composio DuckDuckGo Search](#mention) for each guest\n - **Agent response**: Alice Smith: [summary], Bob Lee: [summary]",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 3
|
||||
},
|
||||
{
|
||||
"name": "Email Agent",
|
||||
"type": "conversation",
|
||||
"description": "Sends the research summary to the user's email address.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nSend the provided research summary to the user's email address.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive the research summary and recipient email from the parent agent.\n2. Use [@tool:Send Email](#mention) to send the summary.\n3. Confirm delivery to the parent agent.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Sending research summaries via email.\n\n❌ Out of Scope:\n- Fetching event details.\n- Researching guests.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Ensure the summary is sent to the correct email.\n\n🚫 Don'ts:\n- Do not interact with the user directly.",
|
||||
"examples": "- **Parent agent** : Send summary to user@email.com: [summary text]\n - **Agent actions**: Call [@tool:Send Email](#mention)\n - **Agent response**: Email sent confirmation.",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 3
|
||||
}
|
||||
],
|
||||
"prompts": [],
|
||||
"tools": [
|
||||
{
|
||||
"name": "Find event",
|
||||
"description": "Finds events in a specified google calendar using text query, time ranges, and event types.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"calendar_id": {
|
||||
"default": "primary",
|
||||
"description": "Identifier of the Google Calendar to query.",
|
||||
"examples": [
|
||||
"primary",
|
||||
"user@example.com",
|
||||
"abc...@group.calendar.google.com"
|
||||
],
|
||||
"title": "Calendar Id",
|
||||
"type": "string"
|
||||
},
|
||||
"event_types": {
|
||||
"default": [
|
||||
"birthday",
|
||||
"default",
|
||||
"focusTime",
|
||||
"outOfOffice",
|
||||
"workingLocation"
|
||||
],
|
||||
"description": "Event types to include.",
|
||||
"examples": [
|
||||
"default",
|
||||
"focusTime",
|
||||
"outOfOffice"
|
||||
],
|
||||
"items": {
|
||||
"enum": [
|
||||
"birthday",
|
||||
"default",
|
||||
"focusTime",
|
||||
"outOfOffice",
|
||||
"workingLocation"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Event Types",
|
||||
"type": "array"
|
||||
},
|
||||
"max_results": {
|
||||
"default": 10,
|
||||
"description": "Maximum number of events per page (1-2500).",
|
||||
"title": "Max Results",
|
||||
"type": "integer"
|
||||
},
|
||||
"order_by": {
|
||||
"default": null,
|
||||
"description": "Order of events: 'startTime' or 'updated'.",
|
||||
"examples": [
|
||||
"startTime",
|
||||
"updated"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Order By",
|
||||
"type": "string"
|
||||
},
|
||||
"page_token": {
|
||||
"default": null,
|
||||
"description": "Token for pagination.",
|
||||
"nullable": true,
|
||||
"title": "Page Token",
|
||||
"type": "string"
|
||||
},
|
||||
"query": {
|
||||
"default": null,
|
||||
"description": "Free-text search terms to find events.",
|
||||
"examples": [
|
||||
"Project Alpha Review",
|
||||
"Birthday Party"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Query",
|
||||
"type": "string"
|
||||
},
|
||||
"show_deleted": {
|
||||
"default": null,
|
||||
"description": "Include deleted events.",
|
||||
"nullable": true,
|
||||
"title": "Show Deleted",
|
||||
"type": "boolean"
|
||||
},
|
||||
"single_events": {
|
||||
"default": true,
|
||||
"description": "Expand recurring events into individual instances.",
|
||||
"title": "Single Events",
|
||||
"type": "boolean"
|
||||
},
|
||||
"timeMax": {
|
||||
"default": null,
|
||||
"description": "Upper bound for event's start time.",
|
||||
"examples": [
|
||||
"2024-12-31T23:59:59Z"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Time Max",
|
||||
"type": "string"
|
||||
},
|
||||
"timeMin": {
|
||||
"default": null,
|
||||
"description": "Lower bound for event's end time.",
|
||||
"examples": [
|
||||
"2024-01-01T00:00:00Z"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Time Min",
|
||||
"type": "string"
|
||||
},
|
||||
"updated_min": {
|
||||
"default": null,
|
||||
"description": "Lower bound for event's last modification time.",
|
||||
"examples": [
|
||||
"2024-07-01T00:00:00Z"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Updated Min",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": []
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "GOOGLECALENDAR_FIND_EVENT",
|
||||
"noAuth": false,
|
||||
"toolkitName": "googlecalendar",
|
||||
"toolkitSlug": "googlecalendar",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master/google-calendar.svg"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Composio DuckDuckGo Search",
|
||||
"description": "Performs web searches using DuckDuckGo to retrieve relevant information.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"query": {
|
||||
"description": "The search query for DuckDuckGo.",
|
||||
"examples": [
|
||||
"Python programming"
|
||||
],
|
||||
"title": "Query",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"query"
|
||||
]
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "COMPOSIO_SEARCH_DUCK_DUCK_GO_SEARCH",
|
||||
"noAuth": true,
|
||||
"toolkitName": "composio_search",
|
||||
"toolkitSlug": "composio_search",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master//composio-logo.png"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Send Email",
|
||||
"description": "Sends an email via Gmail using the authenticated user's Google profile.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"attachment": {
|
||||
"additionalProperties": false,
|
||||
"description": "File to attach; ensure s3key, mimetype, and name are set if provided.",
|
||||
"file_uploadable": true,
|
||||
"properties": {
|
||||
"mimetype": {
|
||||
"title": "Mimetype",
|
||||
"type": "string"
|
||||
},
|
||||
"name": {
|
||||
"title": "Name",
|
||||
"type": "string"
|
||||
},
|
||||
"s3key": {
|
||||
"title": "S3Key",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"name",
|
||||
"mimetype",
|
||||
"s3key"
|
||||
],
|
||||
"title": "FileUploadable",
|
||||
"type": "object"
|
||||
},
|
||||
"bcc": {
|
||||
"default": [],
|
||||
"description": "BCC recipients' email addresses.",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Bcc",
|
||||
"type": "array"
|
||||
},
|
||||
"body": {
|
||||
"description": "Email content (plain text or HTML).",
|
||||
"examples": [
|
||||
"Hello team, let's discuss the project updates tomorrow."
|
||||
],
|
||||
"title": "Body",
|
||||
"type": "string"
|
||||
},
|
||||
"cc": {
|
||||
"default": [],
|
||||
"description": "CC recipients' email addresses.",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Cc",
|
||||
"type": "array"
|
||||
},
|
||||
"extra_recipients": {
|
||||
"default": [],
|
||||
"description": "Additional 'To' recipients' email addresses.",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Extra Recipients",
|
||||
"type": "array"
|
||||
},
|
||||
"is_html": {
|
||||
"default": false,
|
||||
"description": "Set to True if the email body contains HTML tags.",
|
||||
"title": "Is Html",
|
||||
"type": "boolean"
|
||||
},
|
||||
"recipient_email": {
|
||||
"description": "Primary recipient's email address.",
|
||||
"examples": [
|
||||
"john@doe.com"
|
||||
],
|
||||
"title": "Recipient Email",
|
||||
"type": "string"
|
||||
},
|
||||
"subject": {
|
||||
"default": null,
|
||||
"description": "Subject line of the email.",
|
||||
"examples": [
|
||||
"Project Update Meeting"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Subject",
|
||||
"type": "string"
|
||||
},
|
||||
"user_id": {
|
||||
"default": "me",
|
||||
"description": "User's email address; 'me' refers to the authenticated user.",
|
||||
"examples": [
|
||||
"user@example.com",
|
||||
"me"
|
||||
],
|
||||
"title": "User Id",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"recipient_email",
|
||||
"body"
|
||||
]
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "GMAIL_SEND_EMAIL",
|
||||
"noAuth": false,
|
||||
"toolkitName": "gmail",
|
||||
"toolkitSlug": "gmail",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master/gmail.svg"
|
||||
}
|
||||
}
|
||||
],
|
||||
"startAgent": "Meeting Prep Hub",
|
||||
"lastUpdatedAt": "2025-09-07T17:06:05.564Z",
|
||||
"name": "Meeting Prep",
|
||||
"description": "Research meeting attendees and send summary to Slack"
|
||||
}
|
||||
|
|
@ -108,5 +108,6 @@
|
|||
"lastUpdatedAt": "2025-09-11T18:51:15.548Z",
|
||||
"name": "Customer Support",
|
||||
"description": "Answers product information (RAG) and delivery status (MCP) questions.",
|
||||
"category": "Customer Support"
|
||||
}
|
||||
"category": "Customer Support",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant."
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,5 +1,4 @@
|
|||
{
|
||||
"category": "Developer Productivity",
|
||||
"agents": [
|
||||
{
|
||||
"name": "GitHub Stats Hub",
|
||||
|
|
@ -575,5 +574,7 @@
|
|||
],
|
||||
"startAgent": "GitHub Stats Pipeline Hub",
|
||||
"name": "GitHub Data to Spreadsheet",
|
||||
"description": "Fetches GitHub repository stats and logs them to a Google Sheet with Slack notifications"
|
||||
"description": "Fetches GitHub repository stats and logs them to a Google Sheet with Slack notifications",
|
||||
"category": "Developer Productivity",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant. Also briefly tell me about how to setup a trigger for this assistant."
|
||||
}
|
||||
|
|
|
|||
120
apps/rowboat/app/lib/prebuilt-cards/github-issue-to-slack.json
Normal file
120
apps/rowboat/app/lib/prebuilt-cards/github-issue-to-slack.json
Normal file
|
|
@ -0,0 +1,120 @@
|
|||
{
|
||||
"agents": [
|
||||
{
|
||||
"name": "GitHub Issue to Slack Hub",
|
||||
"type": "conversation",
|
||||
"description": "Receives new GitHub issue details and sends a formatted message to Slack.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nYou are the assistant responsible for sending new GitHub issue details to Slack.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive a new GitHub issue payload (via trigger).\n2. Extract the relevant details: issue title, description, URL, creator, and any labels.\n3. Format a Slack message summarizing the issue (include all details and a direct link).\n4. Use [@tool:Send message](#mention) to post the message to the specified Slack channel.\n5. Respond with 'done!' to indicate completion.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Formatting and sending Slack messages for new GitHub issues.\n\n❌ Out of Scope:\n- Handling other GitHub events.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Ensure the message is clear and includes all relevant details.\n- Use markdown formatting for readability.\n\n🚫 Don'ts:\n- Do not process non-issue events.\n- CRITICAL: Only call the Slack tool once per issue event.\n\n# Examples\n- **Trigger** : New GitHub issue: 'Bug: Login fails', description: 'User cannot log in', url: 'https://github.com/org/repo/issues/123', creator: 'alice', labels: ['bug']\n - **Agent actions**: Call [@tool:Send message](#mention)\n - **Agent response**: done!",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "user_facing",
|
||||
"controlType": "retain",
|
||||
"maxCallsPerParentAgent": 3
|
||||
}
|
||||
],
|
||||
"prompts": [
|
||||
{
|
||||
"name": "Slack Channel",
|
||||
"type": "base_prompt",
|
||||
"prompt": "<needs to be added>"
|
||||
}
|
||||
],
|
||||
"tools": [
|
||||
{
|
||||
"name": "Send message",
|
||||
"description": "Posts a message to a slack channel, direct message, or private group; requires content via `text`, `blocks`, or `attachments`.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"as_user": {
|
||||
"description": "Post as the authenticated user instead of as a bot. Defaults to `false`. If `true`, `username`, `icon_emoji`, and `icon_url` are ignored. If `false`, the message is posted as a bot, allowing appearance customization.",
|
||||
"type": "boolean"
|
||||
},
|
||||
"attachments": {
|
||||
"description": "URL-encoded JSON array of message attachments, a legacy method for rich content. See Slack API documentation for structure.",
|
||||
"type": "string"
|
||||
},
|
||||
"blocks": {
|
||||
"description": "DEPRECATED: Use `markdown_text` field instead. URL-encoded JSON array of layout blocks for rich/interactive messages. See Slack API Block Kit docs for structure.",
|
||||
"type": "string"
|
||||
},
|
||||
"channel": {
|
||||
"description": "ID or name of the channel, private group, or IM channel to send the message to.",
|
||||
"type": "string"
|
||||
},
|
||||
"icon_emoji": {
|
||||
"description": "Emoji for bot's icon (e.g., ':robot_face:'). Overrides `icon_url`. Applies if `as_user` is `false`.",
|
||||
"type": "string"
|
||||
},
|
||||
"icon_url": {
|
||||
"description": "Image URL for bot's icon (must be HTTPS). Applies if `as_user` is `false`.",
|
||||
"type": "string"
|
||||
},
|
||||
"link_names": {
|
||||
"description": "Automatically hyperlink channel names (e.g., #channel) and usernames (e.g., @user) in message text. Defaults to `false` for bot messages.",
|
||||
"type": "boolean"
|
||||
},
|
||||
"markdown_text": {
|
||||
"description": "PREFERRED: Write your message in markdown for nicely formatted display. Supports: headers (# ## ###), bold (**text** or __text__), italic (*text* or _text_), strikethrough (~~text~~), inline code (`code`), code blocks (```), links ([text](url)), block quotes (>), lists (- item, 1. item), dividers (--- or ***), context blocks (:::context with images), and section buttons (:::section-button). IMPORTANT: Use \\\\n for line breaks (e.g., 'Line 1\\\\nLine 2'), not actual newlines. USER MENTIONS: To tag users, use their user ID with <@USER_ID> format (e.g., <@U1234567890>), not username.",
|
||||
"type": "string"
|
||||
},
|
||||
"mrkdwn": {
|
||||
"description": "Disable Slack's markdown for `text` field if `false`. Default `true` (allows *bold*, _italic_, etc.).",
|
||||
"type": "boolean"
|
||||
},
|
||||
"parse": {
|
||||
"description": "Message text parsing behavior. Default `none` (no special parsing). `full` parses as user-typed (links @mentions, #channels). See Slack API docs for details.",
|
||||
"type": "string"
|
||||
},
|
||||
"reply_broadcast": {
|
||||
"description": "If `true` for a threaded reply, also posts to main channel. Defaults to `false`.",
|
||||
"type": "boolean"
|
||||
},
|
||||
"text": {
|
||||
"description": "DEPRECATED: This sends raw text only, use markdown_text field. Primary textual content. Recommended fallback if using `blocks` or `attachments`. Supports mrkdwn unless `mrkdwn` is `false`.",
|
||||
"type": "string"
|
||||
},
|
||||
"thread_ts": {
|
||||
"description": "Timestamp (`ts`) of an existing message to make this a threaded reply. Use `ts` of the parent message, not another reply. Example: '1476746824.000004'.",
|
||||
"type": "string"
|
||||
},
|
||||
"unfurl_links": {
|
||||
"description": "Enable unfurling of text-based URLs. Defaults `false` for bots, `true` if `as_user` is `true`.",
|
||||
"type": "boolean"
|
||||
},
|
||||
"unfurl_media": {
|
||||
"description": "Disable unfurling of media content from URLs if `false`. Defaults to `true`.",
|
||||
"type": "boolean"
|
||||
},
|
||||
"username": {
|
||||
"description": "Bot's name in Slack (max 80 chars). Applies if `as_user` is `false`.",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"channel"
|
||||
]
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "SLACK_SEND_MESSAGE",
|
||||
"noAuth": false,
|
||||
"toolkitName": "slack",
|
||||
"toolkitSlug": "slack",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master/slack.svg"
|
||||
}
|
||||
}
|
||||
],
|
||||
"pipelines": [],
|
||||
"startAgent": "GitHub Issue to Slack Hub",
|
||||
"lastUpdatedAt": "2025-09-12T13:46:12.039Z",
|
||||
"name": "GitHub Issue to Slack",
|
||||
"description": "Assistant that sends a formatted Slack message with GitHub issue details when a issue is opened or updated.",
|
||||
"category": "Developer Productivity",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant. Also briefly tell me about how to setup a trigger for this assistant."
|
||||
}
|
||||
134
apps/rowboat/app/lib/prebuilt-cards/github-pr-to-slack.json
Normal file
134
apps/rowboat/app/lib/prebuilt-cards/github-pr-to-slack.json
Normal file
|
|
@ -0,0 +1,134 @@
|
|||
{
|
||||
"agents": [
|
||||
{
|
||||
"name": "PR to Slack Agent",
|
||||
"type": "conversation",
|
||||
"description": "Receives PR event details and sends a formatted Slack message to a specified channel.",
|
||||
"instructions": "## 🧑💼 Role:\nYou are an internal agent that receives pull request (PR) event details and sends a Slack message with the PR information.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive PR event details (title, author, URL, description, etc.) and the Slack channel name.\n2. Format a clear, concise Slack message summarizing the PR (e.g., title, author, link, and description).\n3. Use [@tool:Send message](#mention) to post the message to the specified Slack channel.\n4. Return confirmation of message sent.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Formatting PR details for Slack.\n- Sending messages to Slack channels.\n\n❌ Out of Scope:\n- Handling PR events directly (trigger is external).\n- User interaction or responding to user queries.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Ensure the Slack message is clear and includes a link to the PR.\n- Use markdown formatting for readability.\n\n🚫 Don'ts:\n- Do not interact with users.\n- Do not process events other than PRs.\n\n# Examples\n- **Trigger** : PR opened: Title: \"Add new feature\", Author: \"alice\", URL: \"https://github.com/org/repo/pull/123\", Description: \"Implements feature X.\"\n - **Agent actions**: Call [@tool:Send message](#mention)\n - **Agent response**: Slack message sent: \"*New PR Opened*\n*Title:* Add new feature\n*Author:* alice\n*Description:* Implements feature X.\n<https://github.com/org/repo/pull/123>\"\n\n- **Trigger** : PR merged: Title: \"Fix bug\", Author: \"bob\", URL: \"https://github.com/org/repo/pull/456\", Description: \"Fixes Y bug.\"\n - **Agent actions**: Call [@tool:Send message](#mention)\n - **Agent response**: Slack message sent: \"*PR Merged*\n*Title:* Fix bug\n*Author:* bob\n*Description:* Fixes Y bug.\n<https://github.com/org/repo/pull/456>\"",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 1
|
||||
}
|
||||
],
|
||||
"prompts": [
|
||||
{
|
||||
"name": "Slack Channel",
|
||||
"type": "base_prompt",
|
||||
"prompt": "<needs to be added>"
|
||||
}
|
||||
],
|
||||
"tools": [
|
||||
{
|
||||
"name": "Send message",
|
||||
"description": "Posts a message to a slack channel, direct message, or private group; requires content via `text`, `blocks`, or `attachments`.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"as_user": {
|
||||
"description": "Post as the authenticated user instead of as a bot. Defaults to `false`. If `true`, `username`, `icon_emoji`, and `icon_url` are ignored. If `false`, the message is posted as a bot, allowing appearance customization.",
|
||||
"title": "As User",
|
||||
"type": "boolean"
|
||||
},
|
||||
"attachments": {
|
||||
"description": "URL-encoded JSON array of message attachments, a legacy method for rich content. See Slack API documentation for structure.",
|
||||
"title": "Attachments",
|
||||
"type": "string"
|
||||
},
|
||||
"blocks": {
|
||||
"description": "DEPRECATED: Use `markdown_text` field instead. URL-encoded JSON array of layout blocks for rich/interactive messages. See Slack API Block Kit docs for structure.",
|
||||
"title": "Blocks",
|
||||
"type": "string"
|
||||
},
|
||||
"channel": {
|
||||
"description": "ID or name of the channel, private group, or IM channel to send the message to.",
|
||||
"title": "Channel",
|
||||
"type": "string"
|
||||
},
|
||||
"icon_emoji": {
|
||||
"description": "Emoji for bot's icon (e.g., ':robot_face:'). Overrides `icon_url`. Applies if `as_user` is `false`.",
|
||||
"title": "Icon Emoji",
|
||||
"type": "string"
|
||||
},
|
||||
"icon_url": {
|
||||
"description": "Image URL for bot's icon (must be HTTPS). Applies if `as_user` is `false`.",
|
||||
"title": "Icon Url",
|
||||
"type": "string"
|
||||
},
|
||||
"link_names": {
|
||||
"description": "Automatically hyperlink channel names (e.g., #channel) and usernames (e.g., @user) in message text. Defaults to `false` for bot messages.",
|
||||
"title": "Link Names",
|
||||
"type": "boolean"
|
||||
},
|
||||
"markdown_text": {
|
||||
"description": "PREFERRED: Write your message in markdown for nicely formatted display. Supports: headers (# ## ###), bold (**text** or __text__), italic (*text* or _text_), strikethrough (~~text~~), inline code (`code`), code blocks (```), links ([text](url)), block quotes (>), lists (- item, 1. item), dividers (--- or ***), context blocks (:::context with images), and section buttons (:::section-button). IMPORTANT: Use \\\\n for line breaks (e.g., 'Line 1\\\\nLine 2'), not actual newlines. USER MENTIONS: To tag users, use their user ID with <@USER_ID> format (e.g., <@U1234567890>), not username.",
|
||||
"title": "Markdown Text",
|
||||
"type": "string"
|
||||
},
|
||||
"mrkdwn": {
|
||||
"description": "Disable Slack's markdown for `text` field if `false`. Default `true` (allows *bold*, _italic_, etc.).",
|
||||
"title": "Mrkdwn",
|
||||
"type": "boolean"
|
||||
},
|
||||
"parse": {
|
||||
"description": "Message text parsing behavior. Default `none` (no special parsing). `full` parses as user-typed (links @mentions, #channels). See Slack API docs for details.",
|
||||
"title": "Parse",
|
||||
"type": "string"
|
||||
},
|
||||
"reply_broadcast": {
|
||||
"description": "If `true` for a threaded reply, also posts to main channel. Defaults to `false`.",
|
||||
"title": "Reply Broadcast",
|
||||
"type": "boolean"
|
||||
},
|
||||
"text": {
|
||||
"description": "DEPRECATED: This sends raw text only, use markdown_text field. Primary textual content. Recommended fallback if using `blocks` or `attachments`. Supports mrkdwn unless `mrkdwn` is `false`.",
|
||||
"title": "Text",
|
||||
"type": "string"
|
||||
},
|
||||
"thread_ts": {
|
||||
"description": "Timestamp (`ts`) of an existing message to make this a threaded reply. Use `ts` of the parent message, not another reply. Example: '1476746824.000004'.",
|
||||
"title": "Thread Ts",
|
||||
"type": "string"
|
||||
},
|
||||
"unfurl_links": {
|
||||
"description": "Enable unfurling of text-based URLs. Defaults `false` for bots, `true` if `as_user` is `true`.",
|
||||
"title": "Unfurl Links",
|
||||
"type": "boolean"
|
||||
},
|
||||
"unfurl_media": {
|
||||
"description": "Disable unfurling of media content from URLs if `false`. Defaults to `true`.",
|
||||
"title": "Unfurl Media",
|
||||
"type": "boolean"
|
||||
},
|
||||
"username": {
|
||||
"description": "Bot's name in Slack (max 80 chars). Applies if `as_user` is `false`.",
|
||||
"title": "Username",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"channel"
|
||||
]
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "SLACK_SEND_MESSAGE",
|
||||
"noAuth": false,
|
||||
"toolkitName": "slack",
|
||||
"toolkitSlug": "slack",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master/slack.svg"
|
||||
}
|
||||
}
|
||||
],
|
||||
"pipelines": [],
|
||||
"startAgent": "PR to Slack Agent",
|
||||
"lastUpdatedAt": "2025-09-12T06:30:34.203Z",
|
||||
"name": "GitHub PR to Slack",
|
||||
"description": "Assistant that sends a formatted Slack message with PR details when a PR is opened or merged.",
|
||||
"category": "Developer Productivity",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant. Also briefly tell me about how to setup a trigger for this assistant."
|
||||
}
|
||||
|
|
@ -3,11 +3,13 @@
|
|||
|
||||
import githubDataToSpreadsheet from './github-data-to-spreadsheet.json';
|
||||
import interviewScheduler from './interview-scheduler.json';
|
||||
import meetingPrepAssistant from './Meeting Prep Assistant.json';
|
||||
import redditOnSlack from './Reddit on Slack.json';
|
||||
import meetingPrepAssistant from './meeting-prep-assistant.json';
|
||||
import redditOnSlack from './reddit-on-slack.json';
|
||||
import twitterSentiment from './twitter-sentiment.json';
|
||||
import tweetWithGeneratedImage from './Tweet with generated image.json';
|
||||
import tweetWithGeneratedImage from './tweet-with-generated-image.json';
|
||||
import customerSupport from './customer-support.json';
|
||||
import githubIssueToSlack from './github-issue-to-slack.json';
|
||||
import githubPrToSlack from './github-pr-to-slack.json';
|
||||
|
||||
// Keep keys consistent with prior file basenames to avoid breaking links.
|
||||
export const prebuiltTemplates = {
|
||||
|
|
@ -18,5 +20,7 @@ export const prebuiltTemplates = {
|
|||
'Twitter Sentiment': twitterSentiment,
|
||||
'Tweet with generated image': tweetWithGeneratedImage,
|
||||
'Customer Support': customerSupport,
|
||||
'GitHub Issue to Slack': githubIssueToSlack,
|
||||
'GitHub PR to Slack': githubPrToSlack,
|
||||
};
|
||||
|
||||
|
|
|
|||
|
|
@ -465,5 +465,6 @@
|
|||
],
|
||||
"startAgent": "Recruitment HR Bot",
|
||||
"name": "Interview Scheduler",
|
||||
"description": "Automate interview scheduling with candidates from Google Sheets"
|
||||
"description": "Automate interview scheduling with candidates from Google Sheets",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant."
|
||||
}
|
||||
|
|
|
|||
243
apps/rowboat/app/lib/prebuilt-cards/meeting-prep-assistant.json
Normal file
243
apps/rowboat/app/lib/prebuilt-cards/meeting-prep-assistant.json
Normal file
|
|
@ -0,0 +1,243 @@
|
|||
{
|
||||
"agents": [
|
||||
{
|
||||
"name": "Research Guests Agent",
|
||||
"type": "pipeline",
|
||||
"description": "Researches each guest in the calendar invite using Exa Answer and compiles a summary.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nYou are a pipeline agent that researches each guest in a Google Calendar invite.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive a list of guest names and emails from the calendar invite.\n2. For each guest, use [@tool:Exa Answer](#mention) to search for public information about them (e.g., 'Who is [Name] [Email]?').\n3. Summarize the findings for each guest in 2-3 sentences.\n4. Return a list of guest research summaries for the next step.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Be concise and factual.\n- If no information is found, state 'No public information found.'\n🚫 Don'ts:\n- Do not fabricate information.\n- Do not send emails or interact with the user.",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 3
|
||||
},
|
||||
{
|
||||
"name": "Compile Email Agent",
|
||||
"type": "pipeline",
|
||||
"description": "Formats the guest research summaries into a clear email body.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nYou are a pipeline agent that formats guest research into an email body.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive the list of guest research summaries.\n2. Format the summaries into a readable email body, with each guest's name and their summary.\n3. Add a subject line: 'Meeting Guest Research Summary'.\n4. Return the subject and body for the next step.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Use clear formatting (e.g., bullet points or sections per guest).\n🚫 Don'ts:\n- Do not send emails or interact with the user.",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 3
|
||||
},
|
||||
{
|
||||
"name": "Send Email Agent",
|
||||
"type": "pipeline",
|
||||
"description": "Sends the compiled guest research summary to the user's email using Gmail.",
|
||||
"disabled": false,
|
||||
"instructions": "## 🧑💼 Role:\nYou are a pipeline agent that sends the guest research summary email.\n\n---\n## ⚙️ Steps to Follow:\n1. Receive the subject, body, and recipient email address.\n2. Use [@tool:Send Email](#mention) to send the email.\n3. Return confirmation of sending.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Ensure the email is sent to the correct address.\n🚫 Don'ts:\n- Do not perform research or format the email body.",
|
||||
"model": "google/gemini-2.5-flash",
|
||||
"locked": false,
|
||||
"toggleAble": true,
|
||||
"ragReturnType": "chunks",
|
||||
"ragK": 3,
|
||||
"outputVisibility": "internal",
|
||||
"controlType": "relinquish_to_parent",
|
||||
"maxCallsPerParentAgent": 3
|
||||
}
|
||||
],
|
||||
"prompts": [
|
||||
{
|
||||
"name": "User's Email",
|
||||
"type": "base_prompt",
|
||||
"prompt": "<needs to be added>"
|
||||
}
|
||||
],
|
||||
"tools": [
|
||||
{
|
||||
"name": "Exa Answer",
|
||||
"description": "Get answers with citations using the exa api.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"content": {
|
||||
"description": "The user message content for the Exa answer API.",
|
||||
"examples": [
|
||||
"give me image of narendra modi"
|
||||
],
|
||||
"title": "Content",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"content"
|
||||
]
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "COMPOSIO_SEARCH_EXA_ANSWER",
|
||||
"noAuth": true,
|
||||
"toolkitName": "composio_search",
|
||||
"toolkitSlug": "composio_search",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master//composio-logo.png"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "Send Email",
|
||||
"description": "Sends an email via gmail api using the authenticated user's google profile display name, requiring `is html=true` if the body contains html and valid `s3key`, `mimetype`, `name` for any attachment.",
|
||||
"mockTool": false,
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"attachment": {
|
||||
"additionalProperties": false,
|
||||
"description": "File to attach; ensure `s3key`, `mimetype`, and `name` are set if provided. Omit or set to null for no attachment.",
|
||||
"file_uploadable": true,
|
||||
"properties": {
|
||||
"mimetype": {
|
||||
"title": "Mimetype",
|
||||
"type": "string"
|
||||
},
|
||||
"name": {
|
||||
"title": "Name",
|
||||
"type": "string"
|
||||
},
|
||||
"s3key": {
|
||||
"title": "S3Key",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"name",
|
||||
"mimetype",
|
||||
"s3key"
|
||||
],
|
||||
"title": "FileUploadable",
|
||||
"type": "object"
|
||||
},
|
||||
"bcc": {
|
||||
"default": [],
|
||||
"description": "Blind Carbon Copy (BCC) recipients' email addresses.",
|
||||
"examples": [
|
||||
[
|
||||
"auditor@example.com"
|
||||
]
|
||||
],
|
||||
"items": {
|
||||
"properties": {},
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Bcc",
|
||||
"type": "array"
|
||||
},
|
||||
"body": {
|
||||
"description": "Email content (plain text or HTML); if HTML, `is_html` must be `True`.",
|
||||
"examples": [
|
||||
"Hello team, let's discuss the project updates tomorrow.",
|
||||
"<h1>Welcome!</h1><p>Thank you for signing up.</p>"
|
||||
],
|
||||
"title": "Body",
|
||||
"type": "string"
|
||||
},
|
||||
"cc": {
|
||||
"default": [],
|
||||
"description": "Carbon Copy (CC) recipients' email addresses.",
|
||||
"examples": [
|
||||
[
|
||||
"manager@example.com",
|
||||
"teamlead@example.com"
|
||||
]
|
||||
],
|
||||
"items": {
|
||||
"properties": {},
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Cc",
|
||||
"type": "array"
|
||||
},
|
||||
"extra_recipients": {
|
||||
"default": [],
|
||||
"description": "Additional 'To' recipients' email addresses (not Cc or Bcc).",
|
||||
"examples": [
|
||||
[
|
||||
"jane.doe@example.com",
|
||||
"support@example.com"
|
||||
]
|
||||
],
|
||||
"items": {
|
||||
"properties": {},
|
||||
"type": "string"
|
||||
},
|
||||
"title": "Extra Recipients",
|
||||
"type": "array"
|
||||
},
|
||||
"is_html": {
|
||||
"default": false,
|
||||
"description": "Set to `True` if the email body contains HTML tags.",
|
||||
"title": "Is Html",
|
||||
"type": "boolean"
|
||||
},
|
||||
"recipient_email": {
|
||||
"description": "Primary recipient's email address.",
|
||||
"examples": [
|
||||
"john@doe.com"
|
||||
],
|
||||
"title": "Recipient Email",
|
||||
"type": "string"
|
||||
},
|
||||
"subject": {
|
||||
"default": null,
|
||||
"description": "Subject line of the email.",
|
||||
"examples": [
|
||||
"Project Update Meeting",
|
||||
"Your Weekly Newsletter"
|
||||
],
|
||||
"nullable": true,
|
||||
"title": "Subject",
|
||||
"type": "string"
|
||||
},
|
||||
"user_id": {
|
||||
"default": "me",
|
||||
"description": "User's email address; the literal 'me' refers to the authenticated user.",
|
||||
"examples": [
|
||||
"user@example.com",
|
||||
"me"
|
||||
],
|
||||
"title": "User Id",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"recipient_email",
|
||||
"body"
|
||||
]
|
||||
},
|
||||
"isComposio": true,
|
||||
"composioData": {
|
||||
"slug": "GMAIL_SEND_EMAIL",
|
||||
"noAuth": false,
|
||||
"toolkitName": "gmail",
|
||||
"toolkitSlug": "gmail",
|
||||
"logo": "https://cdn.jsdelivr.net/gh/ComposioHQ/open-logos@master/gmail.svg"
|
||||
}
|
||||
}
|
||||
],
|
||||
"pipelines": [
|
||||
{
|
||||
"name": "Meeting Prep Pipeline",
|
||||
"description": "Pipeline that researches meeting guests, compiles a summary, and sends it via email.",
|
||||
"agents": [
|
||||
"Research Guests Agent",
|
||||
"Compile Email Agent",
|
||||
"Send Email Agent"
|
||||
]
|
||||
}
|
||||
],
|
||||
"startAgent": "Meeting Prep Pipeline",
|
||||
"lastUpdatedAt": "2025-09-12T05:56:12.131Z",
|
||||
"name": "Meeting Prep Assistant",
|
||||
"description": "Assistant that researches meeting guests, compiles a summary, and sends it via email.",
|
||||
"category": "Work Productivity",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant. Also briefly tell me about how to setup a trigger for this assistant."
|
||||
}
|
||||
|
|
@ -293,5 +293,6 @@
|
|||
"lastUpdatedAt": "2025-09-09T17:48:53.292Z",
|
||||
"name": "Browse Reddit on Slack",
|
||||
"description": "Browses Reddit for topics of interest and sends them to a Slack channel.",
|
||||
"category": "News & Social"
|
||||
}
|
||||
"category": "News & Social",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant. Also briefly tell me about how to setup a scheduled trigger for this assistant."
|
||||
}
|
||||
|
|
@ -295,5 +295,6 @@
|
|||
"lastUpdatedAt": "2025-09-11T18:02:35.880Z",
|
||||
"name": "Viral Tweet Assistant",
|
||||
"description": "Research topics and create a tweet including generated images.",
|
||||
"category": "News & Social"
|
||||
}
|
||||
"category": "News & Social",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant."
|
||||
}
|
||||
|
|
@ -375,5 +375,6 @@
|
|||
"lastUpdatedAt": "2025-09-11T17:26:48.865Z",
|
||||
"name": "Twitter Sentiment",
|
||||
"description": "Searches Twitter for tweets about a company and analyzes their sentiment.",
|
||||
"category": "News & Social"
|
||||
}
|
||||
"category": "News & Social",
|
||||
"copilotPrompt": "Give me a brief explanation of this assistant. Also briefly tell me about how to setup a scheduled trigger for this assistant."
|
||||
}
|
||||
|
|
|
|||
|
|
@ -400,8 +400,8 @@ export function Chat({
|
|||
messages={[
|
||||
{
|
||||
role: 'assistant',
|
||||
content: 'Hi, how can I help you today?',
|
||||
agentName: 'Assistant',
|
||||
content: workflow.prompts.find(p => p.type === 'greeting')?.prompt || 'Hi, how can I help you today?',
|
||||
agentName: workflow.startAgent,
|
||||
responseType: 'external',
|
||||
},
|
||||
...optimisticMessages,
|
||||
|
|
|
|||
|
|
@ -55,6 +55,7 @@ interface EntityListProps {
|
|||
name: string;
|
||||
} | null;
|
||||
startAgentName: string | null;
|
||||
isLive?: boolean;
|
||||
onSelectAgent: (name: string) => void;
|
||||
onSelectTool: (name: string) => void;
|
||||
onSelectPrompt: (name: string) => void;
|
||||
|
|
@ -63,6 +64,10 @@ interface EntityListProps {
|
|||
onAddAgent: (agent: Partial<z.infer<typeof WorkflowAgent>>) => void;
|
||||
onAddTool: (tool: Partial<z.infer<typeof WorkflowTool>>) => void;
|
||||
onAddPrompt: (prompt: Partial<z.infer<typeof WorkflowPrompt>>) => void;
|
||||
onShowAddDataSourceModal?: () => void;
|
||||
onShowAddVariableModal?: () => void;
|
||||
onShowAddAgentModal?: () => void;
|
||||
onShowAddToolModal?: () => void;
|
||||
onUpdatePrompt: (name: string, prompt: Partial<z.infer<typeof WorkflowPrompt>>) => void;
|
||||
onAddPromptFromModal: (prompt: Partial<z.infer<typeof WorkflowPrompt>>) => void;
|
||||
onUpdatePromptFromModal: (name: string, prompt: Partial<z.infer<typeof WorkflowPrompt>>) => void;
|
||||
|
|
@ -315,6 +320,7 @@ interface PipelineCardProps {
|
|||
onSetMainAgent: (name: string) => void;
|
||||
selectedRef: React.RefObject<HTMLDivElement | null>;
|
||||
startAgentName: string | null;
|
||||
isLive?: boolean;
|
||||
dragHandle?: React.ReactNode;
|
||||
}
|
||||
|
||||
|
|
@ -330,6 +336,7 @@ const PipelineCard = ({
|
|||
onSetMainAgent,
|
||||
selectedRef,
|
||||
startAgentName,
|
||||
isLive,
|
||||
dragHandle,
|
||||
}: PipelineCardProps) => {
|
||||
// Get agents that belong to this pipeline
|
||||
|
|
@ -474,7 +481,12 @@ const PipelineCard = ({
|
|||
};
|
||||
|
||||
export const EntityList = forwardRef<
|
||||
{ openDataSourcesModal: () => void },
|
||||
{
|
||||
openDataSourcesModal: () => void;
|
||||
openAddVariableModal: () => void;
|
||||
openAddAgentModal: () => void;
|
||||
openAddToolModal: () => void;
|
||||
},
|
||||
EntityListProps & {
|
||||
projectId: string,
|
||||
onReorderAgents: (agents: z.infer<typeof WorkflowAgent>[]) => void
|
||||
|
|
@ -488,6 +500,7 @@ export const EntityList = forwardRef<
|
|||
workflow,
|
||||
selectedEntity,
|
||||
startAgentName,
|
||||
isLive,
|
||||
onSelectAgent,
|
||||
onSelectTool,
|
||||
onSelectPrompt,
|
||||
|
|
@ -496,6 +509,10 @@ export const EntityList = forwardRef<
|
|||
onAddAgent,
|
||||
onAddTool,
|
||||
onAddPrompt,
|
||||
onShowAddDataSourceModal,
|
||||
onShowAddVariableModal,
|
||||
onShowAddAgentModal,
|
||||
onShowAddToolModal,
|
||||
onUpdatePrompt,
|
||||
onAddPromptFromModal,
|
||||
onUpdatePromptFromModal,
|
||||
|
|
@ -701,6 +718,15 @@ export const EntityList = forwardRef<
|
|||
useImperativeHandle(ref, () => ({
|
||||
openDataSourcesModal: () => {
|
||||
setShowDataSourcesModal(true);
|
||||
},
|
||||
openAddVariableModal: () => {
|
||||
setShowAddVariableModal(true);
|
||||
},
|
||||
openAddAgentModal: () => {
|
||||
setShowAgentTypeModal(true);
|
||||
},
|
||||
openAddToolModal: () => {
|
||||
setShowToolsModal(true);
|
||||
}
|
||||
}));
|
||||
|
||||
|
|
@ -755,17 +781,17 @@ export const EntityList = forwardRef<
|
|||
<Eye className="w-4 h-4" />
|
||||
</Button>
|
||||
)}
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, agents: true }));
|
||||
setShowAgentTypeModal(true);
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Agent"
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, agents: true }));
|
||||
onShowAddAgentModal?.();
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Agent"
|
||||
>
|
||||
<PlusIcon className="w-4 h-4" />
|
||||
</Button>
|
||||
|
|
@ -803,6 +829,7 @@ export const EntityList = forwardRef<
|
|||
onSetMainAgent={onSetMainAgent}
|
||||
selectedRef={selectedRef}
|
||||
startAgentName={startAgentName}
|
||||
isLive={isLive}
|
||||
/>
|
||||
))}
|
||||
</SortableContext>
|
||||
|
|
@ -891,17 +918,17 @@ export const EntityList = forwardRef<
|
|||
<span>Tools</span>
|
||||
</div>
|
||||
<div className="flex items-center gap-1">
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, tools: true }));
|
||||
setShowToolsModal(true);
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Tool"
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, tools: true }));
|
||||
onShowAddToolModal?.();
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Tool"
|
||||
>
|
||||
<PlusIcon className="w-4 h-4" />
|
||||
</Button>
|
||||
|
|
@ -1039,17 +1066,17 @@ export const EntityList = forwardRef<
|
|||
<span>Data</span>
|
||||
</div>
|
||||
<div className="flex items-center gap-1">
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, data: true }));
|
||||
setShowDataSourcesModal(true);
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Data Source"
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, data: true }));
|
||||
onShowAddDataSourceModal?.();
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Data Source"
|
||||
>
|
||||
<PlusIcon className="w-4 h-4" />
|
||||
</Button>
|
||||
|
|
@ -1190,17 +1217,17 @@ export const EntityList = forwardRef<
|
|||
<PenLine className="w-4 h-4" />
|
||||
<span>Variables</span>
|
||||
</div>
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, prompts: true }));
|
||||
setShowAddVariableModal(true);
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Variable"
|
||||
<Button
|
||||
variant="secondary"
|
||||
size="sm"
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
setExpandedPanels(prev => ({ ...prev, prompts: true }));
|
||||
onShowAddVariableModal?.();
|
||||
}}
|
||||
className={`group ${buttonClasses}`}
|
||||
showHoverContent={true}
|
||||
hoverContent="Add Variable"
|
||||
>
|
||||
<PlusIcon className="w-4 h-4" />
|
||||
</Button>
|
||||
|
|
@ -1737,7 +1764,8 @@ const SortablePipelineItem = ({
|
|||
onAddAgentToPipeline,
|
||||
onSetMainAgent,
|
||||
selectedRef,
|
||||
startAgentName
|
||||
startAgentName,
|
||||
isLive
|
||||
}: {
|
||||
pipeline: z.infer<typeof WorkflowPipeline>;
|
||||
agents: z.infer<typeof WorkflowAgent>[];
|
||||
|
|
@ -1753,6 +1781,7 @@ const SortablePipelineItem = ({
|
|||
onSetMainAgent: (name: string) => void;
|
||||
selectedRef: React.RefObject<HTMLDivElement | null>;
|
||||
startAgentName: string | null;
|
||||
isLive?: boolean;
|
||||
}) => {
|
||||
const {
|
||||
attributes,
|
||||
|
|
@ -1783,6 +1812,7 @@ const SortablePipelineItem = ({
|
|||
onSetMainAgent={onSetMainAgent}
|
||||
selectedRef={selectedRef}
|
||||
startAgentName={startAgentName}
|
||||
isLive={isLive}
|
||||
dragHandle={
|
||||
<button className="cursor-grab" {...listeners}>
|
||||
<GripVertical className="w-4 h-4 text-gray-400" />
|
||||
|
|
|
|||
|
|
@ -238,6 +238,14 @@ export type Action = {
|
|||
type: "show_visualise";
|
||||
} | {
|
||||
type: "hide_visualise";
|
||||
} | {
|
||||
type: "show_add_datasource_modal";
|
||||
} | {
|
||||
type: "show_add_variable_modal";
|
||||
} | {
|
||||
type: "show_add_agent_modal";
|
||||
} | {
|
||||
type: "show_add_tool_modal";
|
||||
};
|
||||
|
||||
function reducer(state: State, action: Action): State {
|
||||
|
|
@ -1019,7 +1027,17 @@ export function WorkflowEditor({
|
|||
localStorage.setItem('workflow_view_mode', fromUrl);
|
||||
return fromUrl as ViewMode;
|
||||
}
|
||||
return (localStorage.getItem('workflow_view_mode') as ViewMode) || "three_all";
|
||||
|
||||
const storedViewMode = localStorage.getItem('workflow_view_mode') as ViewMode;
|
||||
const hasAgents = workflow.agents.length > 0;
|
||||
|
||||
// If workflow has agents and stored view mode is "Hide chat" (two_agents_skipper),
|
||||
// override to show all panels by default
|
||||
if (hasAgents && storedViewMode === 'two_agents_skipper') {
|
||||
return "three_all";
|
||||
}
|
||||
|
||||
return storedViewMode || "three_all";
|
||||
});
|
||||
|
||||
const updateViewMode = useCallback((mode: ViewMode) => {
|
||||
|
|
@ -1107,7 +1125,12 @@ export function WorkflowEditor({
|
|||
}
|
||||
}, [onChangeMode]);
|
||||
const copilotRef = useRef<{ handleUserMessage: (message: string) => void }>(null);
|
||||
const entityListRef = useRef<{ openDataSourcesModal: () => void } | null>(null);
|
||||
const entityListRef = useRef<{
|
||||
openDataSourcesModal: () => void;
|
||||
openAddVariableModal: () => void;
|
||||
openAddAgentModal: () => void;
|
||||
openAddToolModal: () => void;
|
||||
} | null>(null);
|
||||
|
||||
// Modal state for revert confirmation
|
||||
const { isOpen: isRevertModalOpen, onOpen: onRevertModalOpen, onClose: onRevertModalClose } = useDisclosure();
|
||||
|
|
@ -1194,7 +1217,7 @@ export function WorkflowEditor({
|
|||
// Expand Chat to full view: hide Copilot panel and collapse Agents panel
|
||||
updateViewMode('two_agents_chat');
|
||||
setIsLeftPanelCollapsed(true);
|
||||
}, [updateViewMode, viewMode]);
|
||||
}, [updateViewMode]);
|
||||
|
||||
// Load agent order from localStorage on mount
|
||||
// useEffect(() => {
|
||||
|
|
@ -1340,6 +1363,22 @@ export function WorkflowEditor({
|
|||
dispatchGuarded({ type: "add_prompt", prompt });
|
||||
}
|
||||
|
||||
function handleShowAddDataSourceModal() {
|
||||
dispatchGuarded({ type: "show_add_datasource_modal" });
|
||||
}
|
||||
|
||||
function handleShowAddVariableModal() {
|
||||
dispatchGuarded({ type: "show_add_variable_modal" });
|
||||
}
|
||||
|
||||
function handleShowAddAgentModal() {
|
||||
dispatchGuarded({ type: "show_add_agent_modal" });
|
||||
}
|
||||
|
||||
function handleShowAddToolModal() {
|
||||
dispatchGuarded({ type: "show_add_tool_modal" });
|
||||
}
|
||||
|
||||
function handleSelectPipeline(name: string) {
|
||||
dispatch({ type: "select_pipeline", name });
|
||||
}
|
||||
|
|
@ -1450,11 +1489,11 @@ export function WorkflowEditor({
|
|||
|
||||
// Modal-specific handlers that don't auto-select
|
||||
function handleAddPromptFromModal(prompt: Partial<z.infer<typeof WorkflowPrompt>>) {
|
||||
dispatch({ type: "add_prompt", prompt, fromCopilot: true });
|
||||
dispatchGuarded({ type: "add_prompt", prompt, fromCopilot: true });
|
||||
}
|
||||
|
||||
function handleUpdatePromptFromModal(name: string, prompt: Partial<z.infer<typeof WorkflowPrompt>>) {
|
||||
dispatch({ type: "update_prompt_no_select", name, prompt });
|
||||
dispatchGuarded({ type: "update_prompt_no_select", name, prompt });
|
||||
}
|
||||
|
||||
async function handleDeletePrompt(name: string) {
|
||||
|
|
@ -1671,7 +1710,7 @@ export function WorkflowEditor({
|
|||
}, [isLive, state.present.publishing, onChangeMode]);
|
||||
|
||||
const WORKFLOW_MOD_ACTIONS = useRef(new Set([
|
||||
'add_agent','add_tool','add_prompt','add_pipeline',
|
||||
'add_agent','add_tool','add_prompt','add_pipeline','show_add_datasource_modal','show_add_variable_modal','show_add_agent_modal','show_add_tool_modal',
|
||||
'update_agent','update_tool','update_prompt','update_prompt_no_select','update_pipeline',
|
||||
'delete_agent','delete_tool','delete_prompt','delete_pipeline',
|
||||
'toggle_agent','set_main_agent','reorder_agents','reorder_pipelines'
|
||||
|
|
@ -1684,6 +1723,26 @@ export function WorkflowEditor({
|
|||
setShowEditModal(true);
|
||||
return; // Block the action - it never reaches the reducer
|
||||
}
|
||||
|
||||
// Handle modal show actions when not in live mode
|
||||
const actionType = (action as any).type;
|
||||
if (actionType === "show_add_datasource_modal") {
|
||||
entityListRef.current?.openDataSourcesModal();
|
||||
return;
|
||||
}
|
||||
if (actionType === "show_add_variable_modal") {
|
||||
entityListRef.current?.openAddVariableModal();
|
||||
return;
|
||||
}
|
||||
if (actionType === "show_add_agent_modal") {
|
||||
entityListRef.current?.openAddAgentModal();
|
||||
return;
|
||||
}
|
||||
if (actionType === "show_add_tool_modal") {
|
||||
entityListRef.current?.openAddToolModal();
|
||||
return;
|
||||
}
|
||||
|
||||
dispatch(action); // Allow the action to proceed
|
||||
}, [WORKFLOW_MOD_ACTIONS, isLive, state.present.publishing, dispatch]);
|
||||
|
||||
|
|
@ -1947,6 +2006,7 @@ export function WorkflowEditor({
|
|||
workflow={state.present.workflow}
|
||||
selectedEntity={null}
|
||||
startAgentName={state.present.workflow.startAgent}
|
||||
isLive={isLive}
|
||||
onSelectAgent={handleSelectAgent}
|
||||
onSelectTool={handleSelectTool}
|
||||
onSelectPrompt={handleSelectPrompt}
|
||||
|
|
@ -1955,6 +2015,10 @@ export function WorkflowEditor({
|
|||
onAddAgent={handleAddAgent}
|
||||
onAddTool={handleAddTool}
|
||||
onAddPrompt={handleAddPrompt}
|
||||
onShowAddDataSourceModal={handleShowAddDataSourceModal}
|
||||
onShowAddVariableModal={handleShowAddVariableModal}
|
||||
onShowAddAgentModal={handleShowAddAgentModal}
|
||||
onShowAddToolModal={handleShowAddToolModal}
|
||||
onUpdatePrompt={handleUpdatePrompt}
|
||||
onAddPromptFromModal={handleAddPromptFromModal}
|
||||
onUpdatePromptFromModal={handleUpdatePromptFromModal}
|
||||
|
|
@ -2035,6 +2099,7 @@ export function WorkflowEditor({
|
|||
: null
|
||||
}
|
||||
startAgentName={state.present.workflow.startAgent}
|
||||
isLive={isLive}
|
||||
onSelectAgent={handleSelectAgent}
|
||||
onSelectTool={handleSelectTool}
|
||||
onSelectPrompt={handleSelectPrompt}
|
||||
|
|
@ -2043,6 +2108,10 @@ export function WorkflowEditor({
|
|||
onAddAgent={handleAddAgent}
|
||||
onAddTool={handleAddTool}
|
||||
onAddPrompt={handleAddPrompt}
|
||||
onShowAddDataSourceModal={handleShowAddDataSourceModal}
|
||||
onShowAddVariableModal={handleShowAddVariableModal}
|
||||
onShowAddAgentModal={handleShowAddAgentModal}
|
||||
onShowAddToolModal={handleShowAddToolModal}
|
||||
onUpdatePrompt={handleUpdatePrompt}
|
||||
onAddPromptFromModal={handleAddPromptFromModal}
|
||||
onUpdatePromptFromModal={handleUpdatePromptFromModal}
|
||||
|
|
|
|||
|
|
@ -39,10 +39,6 @@ const copilotPrompts = {
|
|||
"Reddit & HN assistant": {
|
||||
prompt: "Build an assistant that helps me with browsing Reddit and Hacker News",
|
||||
emoji: "🔍"
|
||||
},
|
||||
"CRM assistant": {
|
||||
prompt: "Build an assistant that helps me with my CRM",
|
||||
emoji: "📊"
|
||||
}
|
||||
};
|
||||
|
||||
|
|
@ -107,13 +103,14 @@ export function BuildAssistantSection() {
|
|||
};
|
||||
|
||||
// Handle template selection
|
||||
const handleTemplateSelect = async (templateId: string) => {
|
||||
const handleTemplateSelect = async (template: any) => {
|
||||
// Show a small non-blocking spinner on the clicked card
|
||||
setLoadingTemplateId(templateId);
|
||||
setLoadingTemplateId(template.id);
|
||||
try {
|
||||
await createProjectWithOptions({
|
||||
template: templateId,
|
||||
prompt: 'Explain this workflow',
|
||||
template: template.id,
|
||||
// Prefer a card-specific copilot prompt if present on the template JSON
|
||||
prompt: template.copilotPrompt || 'Explain this workflow',
|
||||
router,
|
||||
onError: () => {
|
||||
// Clear loading state if creation fails
|
||||
|
|
@ -499,7 +496,7 @@ export function BuildAssistantSection() {
|
|||
{items.map((template) => (
|
||||
<button
|
||||
key={template.id}
|
||||
onClick={() => handleTemplateSelect(template.id)}
|
||||
onClick={() => handleTemplateSelect(template)}
|
||||
disabled={loadingTemplateId === template.id}
|
||||
className={clsx(
|
||||
"relative block p-4 border border-gray-200 dark:border-gray-700 rounded-xl transition-all group text-left",
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ import { CopilotChatContext, CopilotMessage, DataSourceSchemaForCopilot } from "
|
|||
import { PrefixLogger } from "@/app/lib/utils";
|
||||
import zodToJsonSchema from "zod-to-json-schema";
|
||||
import { COPILOT_INSTRUCTIONS_EDIT_AGENT } from "./copilot_edit_agent";
|
||||
import { COPILOT_INSTRUCTIONS_MULTI_AGENT } from "./copilot_multi_agent";
|
||||
import { COPILOT_INSTRUCTIONS_MULTI_AGENT_WITH_DOCS as COPILOT_INSTRUCTIONS_MULTI_AGENT } from "./copilot_multi_agent";
|
||||
import { COPILOT_MULTI_AGENT_EXAMPLE_1 } from "./example_multi_agent_1";
|
||||
import { CURRENT_WORKFLOW_PROMPT } from "./current_workflow";
|
||||
import { USE_COMPOSIO_TOOLS } from "@/app/lib/feature_flags";
|
||||
|
|
@ -352,4 +352,4 @@ export async function* streamMultiAgentResponse(
|
|||
projectId,
|
||||
totalChunks: chunkCount
|
||||
});
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,270 +1,106 @@
|
|||
|
||||
export const COPILOT_INSTRUCTIONS_MULTI_AGENT = `
|
||||
|
||||
<core_identity>
|
||||
|
||||
You are a helpful co-pilot for designing and deploying multi-agent systems. Your goal is to help users build reliable, purpose-driven workflows that accurately fulfil their intended outcomes.
|
||||
|
||||
You can perform the following tasks:
|
||||
|
||||
1. Create a multi-agent system
|
||||
2. Add a new agent
|
||||
3. Edit an existing agent
|
||||
4. Improve an existing agent's instructions
|
||||
5. Add, edit, or remove tools
|
||||
6. Adding RAG data sources to agents
|
||||
7. Create and manage pipelines (sequential agent workflows)
|
||||
|
||||
Always aim to fully resolve the user's query before yielding. Only ask for clarification once, using up to 4 concise, bullet-point questions to understand the user’s objective and what they want the workflow to achieve.
|
||||
|
||||
You are encouraged to use searchRelevantTools to find tools matching user tasks — assume a relevant tool exists unless proven otherwise.
|
||||
|
||||
Plan thoroughly. Avoid unnecessary agents: combine responsibilities where appropriate, and only use multiple agents when distinct roles clearly improve performance and modularity.
|
||||
|
||||
While adding pipelines you must remember pipelineAgents are different from normal agents. They have a different format!
|
||||
|
||||
You are not equipped to perform the following tasks:
|
||||
|
||||
1. Setting up RAG sources in projects
|
||||
2. Connecting tools to an API
|
||||
3. Creating, editing or removing datasources
|
||||
4. Creating, editing or removing projects
|
||||
5. Creating, editing or removing Simulation scenarios
|
||||
|
||||
</core_identity>
|
||||
|
||||
<building_multi_agent_systems>
|
||||
|
||||
When the user asks you to create agents for a multi-agent system, you should follow the steps below:
|
||||
|
||||
1. Understand the user’s intent — what they want the workflow to achieve. Plan accordingly to build an elegant and efficient system.
|
||||
2. Identify required tools - if the user mentions specific tasks (e.g. sending an email, performing a search), use searchRelevantTools to find suitable tools the agent could use to solve their needs and add those tools to the project. Additionally, ask the users if these tools are what they were looking for at the end of your entire response.
|
||||
3. Create a first draft of a new agent for each step in the plan. You must always ensure to set a start agent when creating a multi-agent system. Attach all tools to the relevant agents.
|
||||
4. Describe your work — briefly summarise what you've done at the end of your turn.
|
||||
|
||||
It is good practice to add tools first and then agents
|
||||
When removing tools, make sure to remove them from all agents they were mentioned in (attached)
|
||||
|
||||
</building_multi_agent_systems>
|
||||
|
||||
<about_agents>
|
||||
|
||||
Agents fall into two main types:
|
||||
|
||||
1. Conversational Agents (user_facing)
|
||||
- These agents can interact with users.
|
||||
- The start agent is almost always a conversational agent, called the Hub Agent. It orchestrates the overall workflow and directs task execution.
|
||||
- If different agents handle completely different tasks that involve information from the user, you should make them conversational agents.
|
||||
- In simpler use cases, a single Hub Agent with attached tools may be enough — a full multi-agent setup is not always necessary.
|
||||
- Core responsibilities:
|
||||
- Break down the user's query into subtasks
|
||||
- Route tasks to internal agents with relevant context
|
||||
- Aggregate and return results to the user
|
||||
- Tools can be attached to conversational agents.
|
||||
|
||||
2. Task Agents (internal)
|
||||
- These are internal-only agents — they do not interact directly with the user.
|
||||
- Using tools is a key part of their task, can hae multiple tools attached
|
||||
- Each task agent is focused on a specific function and should be designed to handle just that task.
|
||||
- They receive only minimal, relevant context (not the full user prompt) and are expected to return clear, focused output that addresses their subtask.
|
||||
|
||||
IMPORTANT:
|
||||
When creating a task agent, you must set the outputVisibility to 'internal' and the controlType to 'relinquish_to_parent'.
|
||||
For pipeline agents, you must set the outputVisibility to 'internal' and the controlType to 'relinquish_to_parent'.
|
||||
For conversational agents, you must set the outputVisibility to 'user_facing' and the controlType to 'retain'
|
||||
|
||||
CRITICAL: Always include these required fields when creating agents:
|
||||
- For pipeline agents: "type": "pipeline", "outputVisibility": "internal", "controlType": "relinquish_to_parent"
|
||||
- For task agents: "outputVisibility": "internal", "controlType": "relinquish_to_parent"
|
||||
- For conversational agents: "outputVisibility": "user_facing", "controlType": "retain"
|
||||
|
||||
CRITICAL: When creating a multi-agent system, you MUST always set a start agent. Use the action "set_main_agent" or "edit" with "config_type": "start_agent" to set the start agent to the main conversational agent (usually the Hub agent).
|
||||
|
||||
However, there are some important things you need to instruct the individual agents when they call other agents (you need to customize the below to the specific agent and its):
|
||||
|
||||
- SEQUENTIAL TRANSFERS AND RESPONSES:
|
||||
A. BEFORE transferring to any agent:
|
||||
- Plan your complete sequence of needed transfers
|
||||
- Document which responses you need to collect
|
||||
|
||||
B. DURING transfers:
|
||||
- Transfer to only ONE agent at a time
|
||||
- Wait for that agent's COMPLETE response and then proceed with the next agent
|
||||
- Store the response for later use
|
||||
- Only then proceed with the next transfer
|
||||
- Never attempt parallel or simultaneous transfers
|
||||
- CRITICAL: The system does not support more than 1 tool call in a single output when the tool call is about transferring to another agent (a handoff). You must only put out 1 transfer related tool call in one output.
|
||||
|
||||
C. AFTER receiving a response:
|
||||
- Do not transfer to another agent until you've processed the current response
|
||||
- If you need to transfer to another agent, wait for your current processing to complete
|
||||
- Never transfer back to an agent that has already responded
|
||||
|
||||
- COMPLETION REQUIREMENTS:
|
||||
- Never provide final response until ALL required agents have been consulted
|
||||
- Never attempt to get multiple responses in parallel
|
||||
- If a transfer is rejected due to multiple handoffs:
|
||||
A. Complete current response processing
|
||||
B. Then retry the transfer as next in sequence
|
||||
X. Continue until all required responses are collected
|
||||
|
||||
- EXAMPLE: Suppose your instructions ask you to transfer to @agent:AgentA, @agent:AgentB and @agent:AgentC, first transfer to AgentA, wait for its response. Then transfer to AgentB, wait for its response. Then transfer to AgentC, wait for its response. Only after all 3 agents have responded, you should return the final response to the user.
|
||||
|
||||
--
|
||||
|
||||
## Section: Creating New Agents
|
||||
|
||||
When creating a new agent, strictly follow the format of this example agent. The user might not provide all information in the example agent, but you should still follow the format and add the missing information.
|
||||
|
||||
example agent:
|
||||
\`\`\`
|
||||
## 🧑💼 Role:\nYou are the hub agent responsible for orchestrating the evaluation of interview transcripts between an executive search agency (Assistant) and a CxO candidate (User).\n\n---\n## ⚙️ Steps to Follow:\n1. Receive the transcript in the specified format.\n2. FIRST: Send the transcript to [@agent:Evaluation Agent] for evaluation.\n3. Wait to receive the complete evaluation from the Evaluation Agent.\n4. THEN: Send the received evaluation to [@agent:Call Decision] to determine if the call quality is sufficient.\n5. Based on the Call Decision response:\n - If approved: Inform the user that the call has been approved and will proceed to profile creation.\n - If rejected: Inform the user that the call quality was insufficient and provide the reason.\n6. Return the final result (rejection reason or approval confirmation) to the user.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Orchestrating the sequential evaluation and decision process for interview transcripts.\n\n❌ Out of Scope:\n- Directly evaluating or creating profiles.\n- Handling transcripts not in the specified format.\n- Interacting with the individual evaluation agents.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Follow the strict sequence: Evaluation Agent first, then Call Decision.\n- Wait for each agent's complete response before proceeding.\n- Only interact with the user for final results or format clarification.\n\n🚫 Don'ts:\n- Do not perform evaluation or profile creation yourself.\n- Do not modify the transcript.\n- Do not try to get evaluations simultaneously.\n- Do not reference the individual evaluation agents.\n- CRITICAL: The system does not support more than 1 tool call in a single output when the tool call is about transferring to another agent (a handoff). You must only put out 1 transfer related tool call in one output.\n\n# Examples\n- **User** : Here is the interview transcript: [2024-04-25, 10:00] User: I have 20 years of experience... [2024-04-25, 10:01] Assistant: Can you describe your leadership style?\n - **Agent actions**: \n 1. First call [@agent:Evaluation Agent](#mention)\n 2. Wait for complete evaluation\n 3. Then call [@agent:Call Decision](#mention)\n\n- **Agent receives evaluation and decision (approved)** :\n - **Agent response**: The call has been approved. Proceeding to candidate profile creation.\n\n- **Agent receives evaluation and decision (rejected)** :\n - **Agent response**: The call quality was insufficient to proceed. [Provide reason from Call Decision agent]\n\n- **User** : The transcript is in a different format.\n - **Agent response**: Please provide the transcript in the specified format: [<date>, <time>] User: <user-message> [<date>, <time>] Assistant: <assistant-message>\n\n# Examples\n- **User** : Here is the interview transcript: [2024-04-25, 10:00] User: I have 20 years of experience... [2024-04-25, 10:01] Assistant: Can you describe your leadership style?\n - **Agent actions**: Call [@agent:Evaluation Agent](#mention)\n\n- **Agent receives Evaluation Agent result** :\n - **Agent actions**: Call [@agent:Call Decision](#mention)\n\n- **Agent receives Call Decision result (approved)** :\n - **Agent response**: The call has been approved. Proceeding to candidate profile creation.\n\n- **Agent receives Call Decision result (rejected)** :\n - **Agent response**: The call quality was insufficient to proceed. [Provide reason from Call Decision agent]\n\n- **User** : The transcript is in a different format.\n - **Agent response**: Please provide the transcript in the specified format: [<date>, <time>] User: <user-message> [<date>, <time>] Assistant: <assistant-message>\n\n- **User** : What happens after evaluation?\n - **Agent response**: After evaluation, if the call quality is sufficient, a candidate profile will be generated. Otherwise, you will receive feedback on why the call was rejected.
|
||||
\`\`\`
|
||||
|
||||
IMPORTANT: Use {agent_model} as the default model for new agents.
|
||||
|
||||
## Section: Editing or Improving an Existing Agent
|
||||
|
||||
When the user asks you to edit or improve an existing agent, follow these steps:
|
||||
|
||||
1. Understand the user’s intent.
|
||||
- If the request is unclear, ask one set of clarifying questions (maximum 4, in a bullet list). Keep this to a single turn.
|
||||
2. Preserve existing structure.
|
||||
- Retain as much of the original agent’s instructions as possible. Only change what is necessary based on the user’s request.
|
||||
3. Strengthen the agent’s clarity and reliability.
|
||||
- Review the instructions line by line. Identify any areas that are underspecified or ambiguous.
|
||||
- Create a few potential test cases and ensure the updated agent would respond correctly in each scenario.
|
||||
4. Return the full modified agent.
|
||||
- Always output the complete revised agent instructions, not just the changes.
|
||||
|
||||
### Section: Adding Examples to an Agent
|
||||
|
||||
When adding examples to an agent use the below format for each example you create. Add examples to the example field in the agent config. Always add examples when creating a new agent, unless the user specifies otherwise.
|
||||
|
||||
\`\`\`
|
||||
- **User** : <user's message>
|
||||
- **Agent actions**: <actions like if applicable>
|
||||
- **Agent response**: "<response to the user if applicable>
|
||||
\`\`\`
|
||||
|
||||
Action involving calling other agents
|
||||
1. If the action is calling another agent, denote it by 'Call [@agent:<agent_name>](#mention)'
|
||||
2. If the action is calling another agent, don't include the agent response
|
||||
|
||||
Action involving calling tools
|
||||
1. If the action involves calling one or more tools, denote it by 'Call [@tool:tool_name_1](#mention), Call [@tool:tool_name_2](#mention) ... '
|
||||
2. If the action involves calling one or more tools, the corresponding response should have a placeholder to denote the output of tool call if necessary. e.g. 'Your order will be delivered on <delivery_date>'
|
||||
|
||||
Style of Response
|
||||
1. If there is a Style prompt or other prompts which mention how the agent should respond, use that as guide when creating the example response
|
||||
|
||||
If the user doesn't specify how many examples, always add 5 examples.
|
||||
|
||||
### Section: Adding RAG data sources to an Agent
|
||||
|
||||
When rag data sources are available you will be given the information on it like this:
|
||||
\`\`\`
|
||||
The following data sources are available:
|
||||
|
||||
[{"id": "6822e76aa1358752955a455e", "name": "Handbook", "description": "This is a employee handbook", "active": true, "status": "ready", "error": null, "data": {"type": "text"}}]
|
||||
|
||||
User: "can you add the handbook to the agent"]
|
||||
\`\`\`
|
||||
|
||||
You should use the name and description to understand the data source, and use the id to attach the data source to the agent. Example:
|
||||
|
||||
'ragDataSources' = ["6822e76aa1358752955a455e"]
|
||||
|
||||
Once you add the datasource ID to the agent, add a section to the agent instructions called RAG. Under that section, inform the agent that here are a set of data sources available to it and add the name and description of each attached data source. Instruct the agent to use RAG search to pull information from any of the data sources before answering any questions on them'.
|
||||
|
||||
Note: the rag_search tool searches across all data sources - it cannot call a specific data source.
|
||||
|
||||
|
||||
</about_agents>
|
||||
|
||||
<agent_tools>
|
||||
|
||||
## Section: Adding / Editing / Removing Tools
|
||||
|
||||
1. Follow the user's request and output the relevant actions and data based on the user's needs.
|
||||
2. If you are removing a tool, make sure to remove it from all the agents that use it.
|
||||
3. If you are adding a tool, make sure to add it to all the agents that need it.
|
||||
|
||||
</agent_tools>
|
||||
|
||||
<about_pipelines>
|
||||
|
||||
## Section: Creating and Managing Pipelines
|
||||
|
||||
Pipelines are sequential workflows that execute agents in a specific order. They are useful for complex multi-step processes where each step depends on the output of the previous step.
|
||||
|
||||
### Pipeline Structure:
|
||||
- **Pipeline Definition**: A pipeline contains a name, description, and an ordered list of agent names
|
||||
- **Pipeline Agents**: Agents with type: "pipeline" that are part of a pipeline workflow
|
||||
- **Pipeline Properties**: Pipeline agents have specific properties:
|
||||
- outputVisibility: "internal" - They don't interact directly with users
|
||||
- controlType: "relinquish_to_parent" - They return control to the calling agent
|
||||
- maxCallsPerParentAgent: 3 - Maximum calls per parent agent
|
||||
|
||||
### Creating Pipelines:
|
||||
1. **Plan the Pipeline**: Identify the sequential steps needed for the workflow
|
||||
2. **Create Pipeline Agents**: Create individual agents for each step with type: "pipeline" and these REQUIRED properties:
|
||||
- type: "pipeline" (MUST be "pipeline", not "conversation")
|
||||
3. **Create Pipeline Definition**: Define the pipeline with the ordered list of agent names
|
||||
4. **Connect to Hub**: Reference the pipeline from the hub agent using pipeline syntax
|
||||
|
||||
### Pipeline Agent Instructions:
|
||||
Pipeline agents should follow this structure:
|
||||
- Focus on their specific step in the process
|
||||
- Process input from the previous step
|
||||
- Return clear output for the next step
|
||||
- Use tools as needed for their specific task
|
||||
- Do NOT transfer to other agents (only use tools)
|
||||
|
||||
### Example Pipeline Usage:
|
||||
When a hub agent needs to execute a pipeline, it should:
|
||||
1. Call the pipeline using pipeline syntax
|
||||
2. Pass the required input to the pipeline
|
||||
3. Wait for the pipeline to complete all steps
|
||||
4. Receive the final result from the pipeline
|
||||
|
||||
</about_pipelines>
|
||||
|
||||
<general_guidlines>
|
||||
|
||||
The user will provide the current config of the multi-agent system and ask you to make changes to it. Talk to the user and output the relevant actions and data based on the user's needs. You should output a set of actions required to accomplish the user's request.
|
||||
|
||||
Note:
|
||||
1. The main agent is only responsible for orchestrating between the other agents.
|
||||
2. You should not edit the main agent unless absolutely necessary.
|
||||
3. Make sure the there are no special characters in the agent names.
|
||||
4. After providing the actions, add a text section with something like 'Once you review and apply the changes, you can try out a basic chat first. I can then help you better configure each agent.'
|
||||
5. If the user asks you to do anything that is out of scope, politely inform the user that you are not equipped to perform that task yet. E.g. "I'm sorry, adding simulation scenarios is currently out of scope for my capabilities. Is there anything else you would like me to do?"
|
||||
6. Always speak with agency like "I'll do ... ", "I'll create ..."
|
||||
7. In agent instructions, make sure to mention that when agents need to take an action, they must just take action and not preface it by saying "I'm going to do X". Instead, they should just do X (e.g. call tools, invoke other agents) and respond with a message that comes about as a result of doing X.
|
||||
|
||||
If the user says 'Hi' or 'Hello', you should respond with a friendly greeting such as 'Hello! How can I help you today?'
|
||||
|
||||
**NOTE**: If a chat is attached but it only contains assistant's messages, you should ignore it.
|
||||
|
||||
## Section: In-product Support
|
||||
|
||||
Below are FAQ's you should use when a use asks a questions on how to use the product (Rowboat).
|
||||
|
||||
User Question : How do I connect an MCP server?
|
||||
Your Answer: Refer to https://docs.rowboatlabs.com/add_tools/ on how to connect MCP tools. Once you have imported the tools, I can help you in adding them to the agents.
|
||||
|
||||
User Question : How do I connect an Webhook?
|
||||
Your Answer: Refer to https://docs.rowboatlabs.com/add_tools/ on how to connect a webhook. Once you have the tools setup, I can help you in adding them to the agents.
|
||||
|
||||
User Question: How do I use the Rowboat API?
|
||||
Your Answer: Refer to https://docs.rowboatlabs.com/using_the_api/ on using the Rowboat API.
|
||||
|
||||
User Question: How do I use the SDK?
|
||||
Your Answer: Refer to https://docs.rowboatlabs.com/using_the_sdk/ on using the Rowboat SDK.
|
||||
|
||||
User Question: I want to add RAG?
|
||||
Your Answer: You can add data sources by using the data source menu in the left pane. You can fine more details in our docs: https://docs.rowboatlabs.com/using_rag.
|
||||
|
||||
</general_guidlines>
|
||||
`;
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import { COPILOT_INSTRUCTIONS_MULTI_AGENT } from './copilot_multi_agent_build';
|
||||
|
||||
function findUsingRowboatDocsDir(): string | null {
|
||||
const candidates = [
|
||||
path.resolve(process.cwd(), '../docs/docs/using-rowboat'),
|
||||
path.resolve(process.cwd(), 'apps/docs/docs/using-rowboat'),
|
||||
];
|
||||
for (const p of candidates) {
|
||||
try {
|
||||
if (fs.existsSync(p) && fs.statSync(p).isDirectory()) return p;
|
||||
} catch {}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function stripFrontmatter(content: string): { title: string | null; body: string } {
|
||||
let title: string | null = null;
|
||||
if (content.startsWith('---')) {
|
||||
const end = content.indexOf('\n---', 3);
|
||||
if (end !== -1) {
|
||||
const fm = content.slice(3, end).trim();
|
||||
const tMatch = fm.match(/\btitle:\s*"([^"]+)"|\btitle:\s*'([^']+)'|\btitle:\s*(.+)/);
|
||||
if (tMatch) {
|
||||
title = (tMatch[1] || tMatch[2] || tMatch[3] || '').trim();
|
||||
}
|
||||
content = content.slice(end + 4);
|
||||
}
|
||||
}
|
||||
return { title, body: content };
|
||||
}
|
||||
|
||||
function sanitizeMdxToPlain(md: string): string {
|
||||
const lines = md
|
||||
.split('\n')
|
||||
.filter(l => !/^\s*(import|export)\b/.test(l))
|
||||
.map(l => l.replace(/<[^>]+>/g, ''));
|
||||
let inFence = false;
|
||||
const out: string[] = [];
|
||||
for (const line of lines) {
|
||||
if (/^\s*```/.test(line)) {
|
||||
inFence = !inFence;
|
||||
continue;
|
||||
}
|
||||
out.push(line);
|
||||
}
|
||||
return out.join('\n').replace(/\n{3,}/g, '\n\n').trim();
|
||||
}
|
||||
|
||||
function extractOverview(body: string): string {
|
||||
const ovIndex = body.indexOf('\n## Overview');
|
||||
if (ovIndex !== -1) {
|
||||
const slice = body.slice(ovIndex + 1);
|
||||
const nextHeader = slice.search(/\n#{1,6}\s+/);
|
||||
const section = nextHeader === -1 ? slice : slice.slice(0, nextHeader);
|
||||
return section.trim();
|
||||
}
|
||||
const first = body.split('\n').slice(0, 20).join('\n');
|
||||
return first.length > 1200 ? first.slice(0, 1200) + '…' : first;
|
||||
}
|
||||
|
||||
function collectDocsSummaries(): string {
|
||||
const dir = findUsingRowboatDocsDir();
|
||||
if (!dir) return '';
|
||||
|
||||
const entries: string[] = [];
|
||||
try {
|
||||
for (const name of fs.readdirSync(dir)) {
|
||||
const full = path.join(dir, name);
|
||||
const stat = fs.statSync(full);
|
||||
if (stat.isFile() && name.endsWith('.mdx')) entries.push(full);
|
||||
if (stat.isDirectory()) {
|
||||
for (const sub of fs.readdirSync(full)) {
|
||||
const subFull = path.join(full, sub);
|
||||
if (fs.statSync(subFull).isFile() && sub.endsWith('.mdx')) entries.push(subFull);
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
return '';
|
||||
}
|
||||
|
||||
const items: string[] = [];
|
||||
for (const file of entries.sort()) {
|
||||
try {
|
||||
const raw = fs.readFileSync(file, 'utf8');
|
||||
const { title, body } = stripFrontmatter(raw);
|
||||
const plain = sanitizeMdxToPlain(body);
|
||||
const summary = extractOverview(plain);
|
||||
const fname = path.basename(file, '.mdx');
|
||||
const header = title || fname.replace(/[-_]/g, ' ').replace(/\b\w/g, c => c.toUpperCase());
|
||||
items.push(`- ${header}:\n${summary}`);
|
||||
} catch {}
|
||||
}
|
||||
|
||||
if (!items.length) return '';
|
||||
return `\n\nAdditional Reference (auto-loaded from docs):\n${items.join('\n\n')}\n`;
|
||||
}
|
||||
|
||||
const USING_ROWBOAT_DOCS = collectDocsSummaries();
|
||||
|
||||
// Inject auto-loaded docs, if available
|
||||
export const COPILOT_INSTRUCTIONS_MULTI_AGENT_WITH_DOCS =
|
||||
COPILOT_INSTRUCTIONS_MULTI_AGENT.replace('{USING_ROWBOAT_DOCS}', USING_ROWBOAT_DOCS);
|
||||
|
|
|
|||
|
|
@ -0,0 +1,261 @@
|
|||
export const COPILOT_INSTRUCTIONS_MULTI_AGENT = `
|
||||
|
||||
<core_identity>
|
||||
|
||||
You are a helpful co-pilot for designing and deploying multi-agent systems. Your goal is to help users build reliable, purpose-driven workflows that accurately fulfil their intended outcomes.
|
||||
|
||||
You can perform the following tasks:
|
||||
|
||||
1. Create a multi-agent system
|
||||
2. Add a new agent
|
||||
3. Edit an existing agent
|
||||
4. Improve an existing agent's instructions
|
||||
5. Add, edit, or remove tools
|
||||
6. Adding RAG data sources to agents
|
||||
7. Create and manage pipelines (sequential agent workflows)
|
||||
|
||||
Always aim to fully resolve the user's query before yielding. Only ask for clarification once, using up to 4 concise, bullet-point questions to understand the user’s objective and what they want the workflow to achieve.
|
||||
|
||||
You are encouraged to use searchRelevantTools to find tools matching user tasks — assume a relevant tool exists unless proven otherwise.
|
||||
|
||||
Plan thoroughly. Avoid unnecessary agents: combine responsibilities where appropriate, and only use multiple agents when distinct roles clearly improve performance and modularity.
|
||||
|
||||
While adding pipelines you must remember pipelineAgents are different from normal agents. They have a different format!
|
||||
|
||||
You are not equipped to perform the following tasks:
|
||||
|
||||
1. Setting up RAG sources in projects
|
||||
2. Connecting tools to an API
|
||||
3. Creating, editing or removing datasources
|
||||
4. Creating, editing or removing projects
|
||||
5. Creating, editing or removing Simulation scenarios
|
||||
|
||||
</core_identity>
|
||||
|
||||
<building_multi_agent_systems>
|
||||
|
||||
When the user asks you to create agents for a multi-agent system, you should follow the steps below:
|
||||
|
||||
1. Understand the user’s intent — what they want the workflow to achieve. Plan accordingly to build an elegant and efficient system.
|
||||
2. Identify required tools - if the user mentions specific tasks (e.g. sending an email, performing a search), use searchRelevantTools to find suitable tools the agent could use to solve their needs and add those tools to the project. Additionally, ask the users if these tools are what they were looking for at the end of your entire response.
|
||||
3. Create a first draft of a new agent for each step in the plan. You must always ensure to set a start agent when creating a multi-agent system. Attach all tools to the relevant agents.
|
||||
4. Describe your work — briefly summarise what you've done at the end of your turn.
|
||||
|
||||
It is good practice to add tools first and then agents
|
||||
When removing tools, make sure to remove them from all agents they were mentioned in (attached)
|
||||
|
||||
</building_multi_agent_systems>
|
||||
|
||||
<about_agents>
|
||||
|
||||
Agents fall into two main types:
|
||||
|
||||
1. Conversational Agents (user_facing)
|
||||
- These agents can interact with users.
|
||||
- The start agent is almost always a conversational agent, called the Hub Agent. It orchestrates the overall workflow and directs task execution.
|
||||
- If different agents handle completely different tasks that involve information from the user, you should make them conversational agents.
|
||||
- In simpler use cases, a single Hub Agent with attached tools may be enough — a full multi-agent setup is not always necessary.
|
||||
- Core responsibilities:
|
||||
- Break down the user's query into subtasks
|
||||
- Route tasks to internal agents with relevant context
|
||||
- Aggregate and return results to the user
|
||||
- Tools can be attached to conversational agents.
|
||||
|
||||
2. Task Agents (internal)
|
||||
- These are internal-only agents — they do not interact directly with the user.
|
||||
- Using tools is a key part of their task, can hae multiple tools attached
|
||||
- Each task agent is focused on a specific function and should be designed to handle just that task.
|
||||
- They receive only minimal, relevant context (not the full user prompt) and are expected to return clear, focused output that addresses their subtask.
|
||||
|
||||
IMPORTANT:
|
||||
When creating a task agent, you must set the outputVisibility to 'internal' and the controlType to 'relinquish_to_parent'.
|
||||
For pipeline agents, you must set the outputVisibility to 'internal' and the controlType to 'relinquish_to_parent'.
|
||||
For conversational agents, you must set the outputVisibility to 'user_facing' and the controlType to 'retain'
|
||||
|
||||
CRITICAL: Always include these required fields when creating agents:
|
||||
- For pipeline agents: "type": "pipeline", "outputVisibility": "internal", "controlType": "relinquish_to_parent"
|
||||
- For task agents: "outputVisibility": "internal", "controlType": "relinquish_to_parent"
|
||||
- For conversational agents: "outputVisibility": "user_facing", "controlType": "retain"
|
||||
|
||||
CRITICAL: When creating a multi-agent system, you MUST always set a start agent. Use the action "set_main_agent" or "edit" with "config_type": "start_agent" to set the start agent to the main conversational agent (usually the Hub agent).
|
||||
|
||||
However, there are some important things you need to instruct the individual agents when they call other agents (you need to customize the below to the specific agent and its):
|
||||
|
||||
- SEQUENTIAL TRANSFERS AND RESPONSES:
|
||||
A. BEFORE transferring to any agent:
|
||||
- Plan your complete sequence of needed transfers
|
||||
- Document which responses you need to collect
|
||||
|
||||
B. DURING transfers:
|
||||
- Transfer to only ONE agent at a time
|
||||
- Wait for that agent's COMPLETE response and then proceed with the next agent
|
||||
- Store the response for later use
|
||||
- Only then proceed with the next transfer
|
||||
- Never attempt parallel or simultaneous transfers
|
||||
- CRITICAL: The system does not support more than 1 tool call in a single output when the tool call is about transferring to another agent (a handoff). You must only put out 1 transfer related tool call in one output.
|
||||
|
||||
C. AFTER receiving a response:
|
||||
- Do not transfer to another agent until you've processed the current response
|
||||
- If you need to transfer to another agent, wait for your current processing to complete
|
||||
- Never transfer back to an agent that has already responded
|
||||
|
||||
- COMPLETION REQUIREMENTS:
|
||||
- Never provide final response until ALL required agents have been consulted
|
||||
- Never attempt to get multiple responses in parallel
|
||||
- If a transfer is rejected due to multiple handoffs:
|
||||
A. Complete current response processing
|
||||
B. Then retry the transfer as next in sequence
|
||||
X. Continue until all required responses are collected
|
||||
|
||||
- EXAMPLE: Suppose your instructions ask you to transfer to @agent:AgentA, @agent:AgentB and @agent:AgentC, first transfer to AgentA, wait for its response. Then transfer to AgentB, wait for its response. Then transfer to AgentC, wait for its response. Only after all 3 agents have responded, you should return the final response to the user.
|
||||
|
||||
--
|
||||
|
||||
## Section: Creating New Agents
|
||||
|
||||
When creating a new agent, strictly follow the format of this example agent. The user might not provide all information in the example agent, but you should still follow the format and add the missing information.
|
||||
|
||||
example agent:
|
||||
\`\`\`
|
||||
## 🧑💼 Role:\nYou are the hub agent responsible for orchestrating the evaluation of interview transcripts between an executive search agency (Assistant) and a CxO candidate (User).\n\n---\n## ⚙️ Steps to Follow:\n1. Receive the transcript in the specified format.\n2. FIRST: Send the transcript to [@agent:Evaluation Agent] for evaluation.\n3. Wait to receive the complete evaluation from the Evaluation Agent.\n4. THEN: Send the received evaluation to [@agent:Call Decision] to determine if the call quality is sufficient.\n5. Based on the Call Decision response:\n - If approved: Inform the user that the call has been approved and will proceed to profile creation.\n - If rejected: Inform the user that the call quality was insufficient and provide the reason.\n6. Return the final result (rejection reason or approval confirmation) to the user.\n\n---\n## 🎯 Scope:\n✅ In Scope:\n- Orchestrating the sequential evaluation and decision process for interview transcripts.\n\n❌ Out of Scope:\n- Directly evaluating or creating profiles.\n- Handling transcripts not in the specified format.\n- Interacting with the individual evaluation agents.\n\n---\n## 📋 Guidelines:\n✔️ Dos:\n- Follow the strict sequence: Evaluation Agent first, then Call Decision.\n- Wait for each agent's complete response before proceeding.\n- Only interact with the user for final results or format clarification.\n\n🚫 Don'ts:\n- Do not perform evaluation or profile creation yourself.\n- Do not modify the transcript.\n- Do not try to get evaluations simultaneously.\n- Do not reference the individual evaluation agents.\n- CRITICAL: The system does not support more than 1 tool call in a single output when the tool call is about transferring to another agent (a handoff). You must only put out 1 transfer related tool call in one output.\n\n# Examples\n- **User** : Here is the interview transcript: [2024-04-25, 10:00] User: I have 20 years of experience... [2024-04-25, 10:01] Assistant: Can you describe your leadership style?\n - **Agent actions**: \n 1. First call [@agent:Evaluation Agent](#mention)\n 2. Wait for complete evaluation\n 3. Then call [@agent:Call Decision](#mention)\n\n- **Agent receives evaluation and decision (approved)** :\n - **Agent response**: The call has been approved. Proceeding to candidate profile creation.\n\n- **Agent receives evaluation and decision (rejected)** :\n - **Agent response**: The call quality was insufficient to proceed. [Provide reason from Call Decision agent]\n\n- **User** : The transcript is in a different format.\n - **Agent response**: Please provide the transcript in the specified format: [<date>, <time>] User: <user-message> [<date>, <time>] Assistant: <assistant-message>\n\n# Examples\n- **User** : Here is the interview transcript: [2024-04-25, 10:00] User: I have 20 years of experience... [2024-04-25, 10:01] Assistant: Can you describe your leadership style?\n - **Agent actions**: Call [@agent:Evaluation Agent](#mention)\n\n- **Agent receives Evaluation Agent result** :\n - **Agent actions**: Call [@agent:Call Decision](#mention)\n\n- **Agent receives Call Decision result (approved)** :\n - **Agent response**: The call has been approved. Proceeding to candidate profile creation.\n\n- **Agent receives Call Decision result (rejected)** :\n - **Agent response**: The call quality was insufficient to proceed. [Provide reason from Call Decision agent]\n\n- **User** : The transcript is in a different format.\n - **Agent response**: Please provide the transcript in the specified format: [<date>, <time>] User: <user-message> [<date>, <time>] Assistant: <assistant-message>\n\n- **User** : What happens after evaluation?\n - **Agent response**: After evaluation, if the call quality is sufficient, a candidate profile will be generated. Otherwise, you will receive feedback on why the call was rejected.
|
||||
\`\`\`
|
||||
|
||||
IMPORTANT: Use {agent_model} as the default model for new agents.
|
||||
|
||||
## Section: Editing or Improving an Existing Agent
|
||||
|
||||
When the user asks you to edit or improve an existing agent, follow these steps:
|
||||
|
||||
1. Understand the user’s intent.
|
||||
- If the request is unclear, ask one set of clarifying questions (maximum 4, in a bullet list). Keep this to a single turn.
|
||||
2. Preserve existing structure.
|
||||
- Retain as much of the original agent’s instructions as possible. Only change what is necessary based on the user’s request.
|
||||
3. Strengthen the agent’s clarity and reliability.
|
||||
- Review the instructions line by line. Identify any areas that are underspecified or ambiguous.
|
||||
- Create a few potential test cases and ensure the updated agent would respond correctly in each scenario.
|
||||
4. Return the full modified agent.
|
||||
- Always output the complete revised agent instructions, not just the changes.
|
||||
|
||||
### Section: Adding Examples to an Agent
|
||||
|
||||
When adding examples to an agent use the below format for each example you create. Add examples to the example field in the agent config. Always add examples when creating a new agent, unless the user specifies otherwise.
|
||||
|
||||
\`\`\`
|
||||
- **User** : <user's message>
|
||||
- **Agent actions**: <actions like if applicable>
|
||||
- **Agent response**: "<response to the user if applicable>
|
||||
\`\`\`
|
||||
|
||||
Action involving calling other agents
|
||||
1. If the action is calling another agent, denote it by 'Call [@agent:<agent_name>](#mention)'
|
||||
2. If the action is calling another agent, don't include the agent response
|
||||
|
||||
Action involving calling tools
|
||||
1. If the action involves calling one or more tools, denote it by 'Call [@tool:tool_name_1](#mention), Call [@tool:tool_name_2](#mention) ... '
|
||||
2. If the action involves calling one or more tools, the corresponding response should have a placeholder to denote the output of tool call if necessary. e.g. 'Your order will be delivered on <delivery_date>'
|
||||
|
||||
Style of Response
|
||||
1. If there is a Style prompt or other prompts which mention how the agent should respond, use that as guide when creating the example response
|
||||
|
||||
If the user doesn't specify how many examples, always add 5 examples.
|
||||
|
||||
### Section: Adding RAG data sources to an Agent
|
||||
|
||||
When rag data sources are available you will be given the information on it like this:
|
||||
\`\`\`
|
||||
The following data sources are available:
|
||||
|
||||
[{"id": "6822e76aa1358752955a455e", "name": "Handbook", "description": "This is a employee handbook", "active": true, "status": "ready", "error": null, "data": {"type": "text"}}]
|
||||
|
||||
User: "can you add the handbook to the agent"]
|
||||
\`\`\`
|
||||
|
||||
You should use the name and description to understand the data source, and use the id to attach the data source to the agent. Example:
|
||||
|
||||
'ragDataSources' = ["6822e76aa1358752955a455e"]
|
||||
|
||||
Once you add the datasource ID to the agent, add a section to the agent instructions called RAG. Under that section, inform the agent that here are a set of data sources available to it and add the name and description of each attached data source. Instruct the agent to use RAG search to pull information from any of the data sources before answering any questions on them'.
|
||||
|
||||
Note: the rag_search tool searches across all data sources - it cannot call a specific data source.
|
||||
|
||||
|
||||
</about_agents>
|
||||
|
||||
<agent_tools>
|
||||
|
||||
## Section: Adding / Editing / Removing Tools
|
||||
|
||||
1. Follow the user's request and output the relevant actions and data based on the user's needs.
|
||||
2. If you are removing a tool, make sure to remove it from all the agents that use it.
|
||||
3. If you are adding a tool, make sure to add it to all the agents that need it.
|
||||
|
||||
</agent_tools>
|
||||
|
||||
<about_pipelines>
|
||||
|
||||
## Section: Creating and Managing Pipelines
|
||||
|
||||
Pipelines are sequential workflows that execute agents in a specific order. They are useful for complex multi-step processes where each step depends on the output of the previous step.
|
||||
|
||||
### Pipeline Structure:
|
||||
- **Pipeline Definition**: A pipeline contains a name, description, and an ordered list of agent names
|
||||
- **Pipeline Agents**: Agents with type: "pipeline" that are part of a pipeline workflow
|
||||
- **Pipeline Properties**: Pipeline agents have specific properties:
|
||||
- outputVisibility: "internal" - They don't interact directly with users
|
||||
- controlType: "relinquish_to_parent" - They return control to the calling agent
|
||||
- maxCallsPerParentAgent: 3 - Maximum calls per parent agent
|
||||
|
||||
### Creating Pipelines:
|
||||
1. **Plan the Pipeline**: Identify the sequential steps needed for the workflow
|
||||
2. **Create Pipeline Agents**: Create individual agents for each step with type: "pipeline" and these REQUIRED properties:
|
||||
- type: "pipeline" (MUST be "pipeline", not "conversation")
|
||||
3. **Create Pipeline Definition**: Define the pipeline with the ordered list of agent names
|
||||
4. **Connect to Hub**: Reference the pipeline from the hub agent using pipeline syntax
|
||||
|
||||
### Pipeline Agent Instructions:
|
||||
Pipeline agents should follow this structure:
|
||||
- Focus on their specific step in the process
|
||||
- Process input from the previous step
|
||||
- Return clear output for the next step
|
||||
- Use tools as needed for their specific task
|
||||
- Do NOT transfer to other agents (only use tools)
|
||||
|
||||
### Example Pipeline Usage:
|
||||
When a hub agent needs to execute a pipeline, it should:
|
||||
1. Call the pipeline using pipeline syntax
|
||||
2. Pass the required input to the pipeline
|
||||
3. Wait for the pipeline to complete all steps
|
||||
4. Receive the final result from the pipeline
|
||||
|
||||
</about_pipelines>
|
||||
|
||||
<general_guidlines>
|
||||
|
||||
The user will provide the current config of the multi-agent system and ask you to make changes to it. Talk to the user and output the relevant actions and data based on the user's needs. You should output a set of actions required to accomplish the user's request.
|
||||
|
||||
Note:
|
||||
1. The main agent is only responsible for orchestrating between the other agents.
|
||||
2. You should not edit the main agent unless absolutely necessary.
|
||||
3. Make sure the there are no special characters in the agent names.
|
||||
4. After providing the actions, add a text section with something like 'Once you review and apply the changes, you can try out a basic chat first. I can then help you better configure each agent.'
|
||||
5. If the user asks you to do anything that is out of scope, politely inform the user that you are not equipped to perform that task yet. E.g. "I'm sorry, adding simulation scenarios is currently out of scope for my capabilities. Is there anything else you would like me to do?"
|
||||
6. Always speak with agency like "I'll do ... ", "I'll create ..."
|
||||
7. In agent instructions, make sure to mention that when agents need to take an action, they must just take action and not preface it by saying "I'm going to do X". Instead, they should just do X (e.g. call tools, invoke other agents) and respond with a message that comes about as a result of doing X.
|
||||
|
||||
If the user says 'Hi' or 'Hello', you should respond with a friendly greeting such as 'Hello! How can I help you today?'
|
||||
|
||||
**NOTE**: If a chat is attached but it only contains assistant's messages, you should ignore it.
|
||||
|
||||
## Section: Help me create my first agent.
|
||||
|
||||
If the user says 'Help me create my first agent.', you should ask the user for more details about what they want to achieve and then create a new agent or multi-agent system for them.
|
||||
|
||||
## Section: In-product Support
|
||||
|
||||
Below are details you should use when a user asks questions on how to use the product (Rowboat).
|
||||
|
||||
|
||||
{USING_ROWBOAT_DOCS}
|
||||
|
||||
</general_guidlines>
|
||||
`;
|
||||
Loading…
Add table
Add a link
Reference in a new issue