apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-02 04:12:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

2 loop refactor

Browse source
This commit is contained in:
Ahmed Burney 2026-02-21 07:33:47 +05:00
parent 334f902e4a
commit e58e6dae9b
4 changed files with 175 additions and 1164 deletions
Download patch file Download diff file Expand all files Collapse all files

30
demos/use_cases/credit_risk_case_copilot/config.yaml
View file

@ -49,23 +49,26 @@ listeners:
agents:
- id: loan_intake_agent
description: |
Loan Intake Agent - Extracts and normalizes loan application data for downstream analysis.
Loan Intake Agent - Step 1 of 4 in the credit risk pipeline. Run first.
CAPABILITIES:
* Normalize applicant data and calculate derived fields (e.g., DTI)
* Identify missing or inconsistent fields
* Produce structured intake JSON for other agents
* Produce structured intake JSON for downstream agents
USE CASES:
* "Normalize this loan application"
* "Extract and validate applicant data"
When requests focus on intake or data normalization for loan applications, route here.
OUTPUT REQUIREMENTS:
* Return JSON with step="intake" and normalized_data/missing_fields
* Do not provide the final decision memo
* This output is used by risk_scoring_agent next
filter_chain:
- pii_security_filter
- id: risk_scoring_agent
description: |
Risk Scoring Agent - Produces risk band, confidence score, and top drivers.
Risk Scoring Agent - Step 2 of 4. Run after intake.
CAPABILITIES:
* Evaluate credit score, DTI, delinquencies, utilization
@ -76,12 +79,15 @@ listeners:
* "Score the risk for this applicant"
* "Provide risk band and drivers"
When requests focus on risk scoring or drivers, route here.
OUTPUT REQUIREMENTS:
* Use intake output from prior assistant message
* Return JSON with step="risk" and risk_band/confidence_score/top_3_risk_drivers
* This output is used by policy_compliance_agent next
filter_chain:
- pii_security_filter
- id: policy_compliance_agent
description: |
Policy Compliance Agent - Checks lending policy rules and required documents.
Policy Compliance Agent - Step 3 of 4. Run after risk scoring.
CAPABILITIES:
* Verify KYC, income, and address checks
@ -92,12 +98,15 @@ listeners:
* "Check policy compliance"
* "List required documents"
When requests focus on policy checks or exceptions, route here.
OUTPUT REQUIREMENTS:
* Use intake + risk outputs from prior assistant messages
* Return JSON with step="policy" and policy_checks/exceptions/required_documents
* This output is used by decision_memo_agent next
filter_chain:
- pii_security_filter
- id: decision_memo_agent
description: |
Decision Memo Agent - Summarizes findings and recommends actions.
Decision Memo Agent - Step 4 of 4. Final response to the user.
CAPABILITIES:
* Create concise decision memos
@ -107,7 +116,10 @@ listeners:
* "Draft a decision memo"
* "Recommend a credit decision"
When requests focus on final memo or recommendation, route here.
OUTPUT REQUIREMENTS:
* Use intake + risk + policy outputs from prior assistant messages
* Return JSON with step="memo", recommended_action, decision_memo
* Provide the user-facing memo as the final response
filter_chain:
- pii_security_filter