+ 
+ 
+ 
+
+ 
+ 
+
+## 📄 ライセンス
+
+Dograh AI は [BSD 2-Clause License](LICENSE) のもとで公開されています。Dograh AI の構築に使われたプロジェクトと同じライセンスであり、互換性と、利用・変更・配布の自由を確保しています。
+
+## 🏢 私たちについて
+
+**Dograh** (Zansat Technologies Private Limited) が ❤️ を込めて開発しています。
+創業チームは YC 卒業生と事業売却を経験した創業者で構成され、音声 AI をオープンで誰もが利用できるものに保つことに取り組んでいます。
+
+
-`gathered_context` is returned in the run record after the call completes and is available in [webhook payloads](/developer/webhooks) for downstream processing. It is **not** available as a template variable in Agent prompts — prompts can only reference `initial_context` fields.
+When the conversation reaches that node, the LLM reads the transcript so far and fills in each variable based on its `prompt`. If a value can't be determined from the conversation, the variable is left empty rather than guessed — leave the `prompt` specific enough that the LLM knows exactly what counts as a match.
+
+You can add extraction to more than one node. Each node's extracted variables are merged into the same `gathered_context` object as the call progresses, keyed by `name` — reuse a `name` at a later node if you want to overwrite an earlier value.
+
+#### How to reference it downstream
+
+`gathered_context` is **not available in Agent prompts** — a prompt can only reference `initial_context` fields, because extraction typically happens after the conversation that would use it. To act on extracted data, send it out via a node instead:
+
+| Where | Syntax | Notes |
+|---|---|---|
+| [Webhook node](/voice-agent/webhook) payload | `{{gathered_context.field_name}}` | Prefixed, since the payload template can also reference `initial_context` |
+| [Run record](/developer/webhooks#payload-context-variables) (API / dashboard) | `gathered_context` object | Returned after the run completes, alongside `recording_url` and `transcript_url` |
+
+```json
+{
+ "customer": "{{initial_context.customer_name}}",
+ "resolution": "{{gathered_context.resolution}}",
+ "callback_requested": "{{gathered_context.wants_callback}}"
+}
+```
+
+See [Webhook Payloads](/developer/webhooks) for the full list of variables available alongside `gathered_context` in a payload template.
## Data flow example
diff --git a/docs/core-concepts/how-dograh-works.mdx b/docs/core-concepts/how-dograh-works.mdx
index 2b5eba13..688a10a1 100644
--- a/docs/core-concepts/how-dograh-works.mdx
+++ b/docs/core-concepts/how-dograh-works.mdx
@@ -38,22 +38,22 @@ sequenceDiagram
## Key components
-**Workflows (Agents)**
+**[Workflows (Agents)](/core-concepts/workflows-and-agents)**
The conversation logic. A workflow is a graph of nodes (conversation steps) connected by edges (conditional transitions). You define what the agent says, when it moves on, and what data it collects.
-**Runs**
+**[Runs](/core-concepts/calls-and-runs)**
Every execution of a workflow creates a run. The run record holds the transcript, recording, extracted data, and cost information.
-**Telephony**
+**[Telephony](/integrations/telephony/overview)**
The phone infrastructure. Dograh connects to your telephony provider (Twilio, Vonage, etc.) to place and receive calls. The audio streams between the caller and Dograh in real time.
-**Transcriber (STT)**
+**[Transcriber (STT)](/configurations/transcriber)**
Converts the caller's speech to text in real time. Dograh sends the audio stream to your configured speech-to-text provider and uses the transcript to drive both the LLM and the final run record.
-**LLM Provider**
+**[LLM Provider](/configurations/llm)**
Processes the transcript and the active node's prompt to generate the agent's next response. It also evaluates edge conditions to decide when to move the conversation forward.
-**Voice Synthesizer (TTS)**
+**[Voice Synthesizer (TTS)](/configurations/voice)**
Converts the LLM's text response to audio and streams it back to the caller. The choice of TTS provider and voice is configurable per agent.
## How it fits together
diff --git a/docs/deployment/custom-domain.mdx b/docs/deployment/custom-domain.mdx
index 7cc050c5..2ab1048d 100644
--- a/docs/deployment/custom-domain.mdx
+++ b/docs/deployment/custom-domain.mdx
@@ -5,6 +5,10 @@ description: "Deploy Dograh AI with custom domain names and SSL certificates"
Deploy Dograh AI with your own custom domain name for a professional production setup. By now, you should be able to create and test a voice agent by following the previous guide to setup the platform on a remote server using [Docker](docker#option-2%3A-remote-server-deployment)
+
+
+Next, set the **Indicator Name**. This is the billing event identifier you will pass from Dograh (e.g. `per-minute-call`) to tell Paygent which rate to apply for this agent's calls:
+
+
+
+Finally, you will configure your **Pricing Strategy**. Paygent allows you to set custom markup rates (rate cards) for every modality. You can define exact margins for Speech-to-Text (STT) seconds, LLM tokens, Text-to-Speech (TTS) characters, and total call minutes:
+
+
+
+Once your pricing is configured, confirm your setup. You will use the **Agent ID** and **Indicator** from this process to connect your Dograh workflow.
+
+### 2. Gather your Paygent credentials
+
+You'll need three core values from your Paygent dashboard to link your Dograh agent:
+
+| Credential | Where to find it / Description |
+|---|---|
+| **Paygent API Key** | Your workspace API key used to authenticate requests (`pg_live_...`) |
+| **Agent ID** | The unique identifier configured for your agent in Step 1 |
+| **Customer ID** | Your Paygent organisation or customer ID |
+
+### 3. Add the Paygent node to your workflow
+
+In your Dograh workflow editor, click **Add node** and scroll to the **Integrations** section. Select **Paygent**. The node will appear on your canvas with a **Not configured** badge.
+
+### 4. Configure the node
+
+Click on the Paygent node and fill in the following fields:
+
+- **Paygent API Key** — Your `pg_live_...` secret key
+- **Agent ID** — The unique agent identifier from Paygent
+- **Customer ID** — Your Paygent organisation ID
+- **Indicator** — The billing event name (defaults to `per-minute-call`)
+- **Enabled** — Toggle on to activate the export
+
+Click **Save**, then **Publish** your workflow.
+
+### 5. Verify the connection
+
+Make a test call through your agent. Once the call completes, check your Paygent dashboard. The billing event and detailed multimodal usage breakdown should appear under your configured Agent ID within a few moments, with your configured pricing margins automatically applied.
+
+## Disabling the integration
+
+To temporarily stop exporting usage data to Paygent, open the Paygent node configuration and toggle **Enabled** off. Your credentials are preserved — toggle it back on anytime to resume tracking.
+
+## Troubleshooting
+
+| Issue | Solution |
+|---|---|
+| Usage data not appearing in Paygent | Verify all credentials are correct with no extra whitespace |
+| Node shows "Not configured" | Open the node and fill in API Key, Agent ID, Customer ID, and Indicator |
+| Workflow not sending data | Make sure the workflow is published, not just saved as a draft |
+| Missing realtime STS tokens | For OpenAI Realtime or Google Live models, verify the pipeline is running in realtime mode (`is_realtime=True`) |
+
+## Learn more
+
+- [Paygent](https://withpaygent.com) — Usage-based billing platform for AI agents
diff --git a/docs/integrations/telephony/agent-stream.mdx b/docs/integrations/telephony/agent-stream.mdx
index f08a6b66..e4c82eb5 100644
--- a/docs/integrations/telephony/agent-stream.mdx
+++ b/docs/integrations/telephony/agent-stream.mdx
@@ -5,7 +5,7 @@ description: "Stream audio to a Dograh agent over a WebSocket"
## Overview
-Agent Stream is a WebSocket endpoint that lets a telephony provider point its media stream at a single URL and drive a Dograh agent run. The agent UUID in the URL selects the agent; provider-specific identifiers in the query string (for Cloudonix: `Domain`) tell Dograh which stored telephony configuration to use for that call. The bearer token and other credentials are never passed in the URL — they live in the stored configuration and are used by Dograh to validate the session and to issue provider API calls (hangup, transfer) during the call.
+Agent Stream is a WebSocket endpoint that lets a telephony provider point its media stream at a single URL and drive a Dograh agent run. The agent UUID in the URL selects the agent, and the provider path segment selects the streaming protocol. Provider-specific identifiers come from the stream protocol itself. For Cloudonix, Dograh reads the domain from the `start.accountSid` field, then uses the matching stored telephony configuration to validate the session and issue provider API calls (hangup, transfer) during the call.
This is useful when:
@@ -23,15 +23,15 @@ This is useful when:
## Endpoint
```
-wss://app.dograh.com/api/v1/agent-stream/{agent_uuid}
+wss://api.dograh.com/api/v1/agent-stream/{provider}/{agent_uuid}
```
-`{agent_uuid}` is the agent's stable UUID (see [Get the Agent UUID](#get-the-agent-uuid) below). On self-hosted deployments, replace `app.dograh.com` with your backend host.
+`{provider}` is the registered provider name, currently `cloudonix`. `{agent_uuid}` is the agent's stable UUID (see [Get the Agent UUID](#get-the-agent-uuid) below). On self-hosted deployments, replace `api.dograh.com` with your backend host.
## Prerequisites
- A Dograh agent (workflow) — published or in draft is fine
-- A Cloudonix telephony configuration in your Dograh organization whose `domain_id` matches the `Domain` you pass on the URL. Dograh uses the bearer token from this configuration to validate the call session and to issue provider API calls (hangup, transfer).
+- A Cloudonix telephony configuration in your Dograh organization whose `domain_id` matches the `accountSid` Cloudonix sends in the stream `start` message. Dograh uses the bearer token from this configuration to validate the call session and to issue provider API calls (hangup, transfer).
## Get the Agent UUID
@@ -41,25 +41,17 @@ To find and copy it in the UI, see [Agent UUID](/configurations/agent-uuid).
## Connect to the WebSocket
-### URL parameters
+### Path parameters
| Param | Required | Description |
| --- | --- | --- |
| `provider` | Yes | Provider name. Currently only `cloudonix` is supported. |
-| `Domain` | Yes (cloudonix) | Cloudonix domain ID. Dograh uses this to look up the matching stored telephony configuration and retrieve the bearer token used for provider API calls. |
-| `callId` / `CallSid` | No | Call identifier from your side; persisted on the workflow run's `gathered_context` as `call_id`. The Cloudonix call SID used for streaming is taken from the `start` event payload, not this param. |
-| `from` | No | Caller phone number, persisted on the workflow run as `caller_number`. |
-| `to` | No | Called phone number, persisted on the workflow run as `called_number`. |
+| `agent_uuid` | Yes | Stable UUID of the Dograh agent to run. |
### Cloudonix example
```
-wss://app.dograh.com/api/v1/agent-stream/{agent_uuid}
- ?provider=cloudonix
- &Domain={CLOUDONIX_DOMAIN_ID}
- &callId={CALL_ID}
- &from=+15555550100
- &to=+15555550199
+wss://api.dograh.com/api/v1/agent-stream/cloudonix/{agent_uuid}
```
Use this URL inside the CXML `Superadmin Dashboard
Manage users and view system-wide data
- {/* User Impersonation Card */}
- User Impersonation
+ Provider User ID
- Impersonate a user account for debugging or support purposes
+ Impersonate with the Stack provider user ID
-
- {/* Workflow Runs Card */}
+
+ Email
+
+ Impersonate with a primary email address
+
+
+
+
+
+
+
+
Workflow Runs
@@ -110,19 +183,13 @@ export default function SuperadminPage() {
-
diff --git a/ui/src/app/superadmin/runs/page.tsx b/ui/src/app/superadmin/runs/page.tsx
index eedf2373..c909d65c 100644
--- a/ui/src/app/superadmin/runs/page.tsx
+++ b/ui/src/app/superadmin/runs/page.tsx
@@ -1,6 +1,6 @@
"use client";
-import { AlertTriangle, ArrowDown, ArrowUp, ArrowUpDown, CheckCircle, ChevronLeft, ChevronRight, ExternalLink, Info, Loader2, RefreshCw } from 'lucide-react';
+import { AlertTriangle, ArrowDown, ArrowUp, ArrowUpDown, CheckCircle, ChevronLeft, ChevronRight, ExternalLink, FileText, Info, Loader2, RefreshCw } from 'lucide-react';
import Image from 'next/image';
import { useRouter, useSearchParams } from 'next/navigation';
import { useCallback, useEffect, useState } from "react";
@@ -493,7 +493,7 @@ export default function RunsPage() {
{
field: 'extra.run_id',
op: '==',
- value: run.id,
+ value: String(run.id),
},
],
field: '',
@@ -541,25 +541,38 @@ export default function RunsPage() {
/>
- {/* Quick-link to open the workflow inside the *regular* app after
- successfully impersonating the owner of the workflow. */}
+ {/* Quick links open the regular app after impersonating the
+ owner of the workflow run. */}
+
+
-
+
+
+
- Access detailed information about all workflow runs, including status, - recordings, transcripts, and usage data. -
- - - -