RI

AGT-1175 · Retail Lending

Loan Approval Agent · Region West

Recommends approve/decline and limits on unsecured retail loans.

critical riskcompliant

Trust score

87

grounding, fairness, oversight

Requests / 30d

21,783

model Azure OpenAI · gpt-4.1

Human approval

Required

data class Restricted

Last audit

2026-06-03

version v2.5

Agent architecture

Request path from the surface the customer or staff member touches, through the governance gateway, to the model and its wired systems

Entry surfaces

Internal service call

Service mesh · mTLS identity

Governance gateway

Truint policy enforcement point

9-stage filter chain · p99 54 ms

Evidence ledger writer

Hash-chained, RFC-3161 anchored

Agent runtime

Loan Approval Agent · Region West

AGT-1175 · v2.5 · trust 87

Azure OpenAI · gpt-4.1

 

LLM / model endpoint · Central India

Tools & data

sanctions.match.adjudicate

 

Tool / function · Restricted

core.accounts.read

 

Tool / function · Restricted

Customer 360 (Restricted)

 

Data source · Restricted

Enforcement chain on every request

  1. 1Identity & entitlementCaller identity resolved; agent entitlement checked against the registry record.
  2. 2Kill switchEstate and per-agent revocation state for AGT-1175 evaluated before any spend.
  3. 3Manifest checkOnly integrations on the signed manifest below are reachable.
  4. 4Budget & rateToken, cost and concurrency budgets for Retail Lending.
  5. 5Injection screenPrompt and retrieved context screened for untrusted-content patterns.
  6. 6DLP & maskingRestricted payloads masked or tokenised inline.
  7. 7Policy decisionCompiled policy bundle evaluated; allow, warn or block.
  8. 8Human in the loopRestricted actions parked for a named approver before execution.
  9. 9Ledger barrierDecision hash-chained into the audit ledger before the response is released.

Registry record

Source of truth for this agent

Registry ID
AGT-1175
Business owner
K. Menon
Department
Retail Lending
Model endpoint
Azure OpenAI · gpt-4.1
Version
v2.5
Data classification
Restricted
Human-in-the-loop
Enforced on restricted actions

Trust composition

Grounding & citations91
Fairness81
Security posture89
Oversight coverage96

Wired integrations

Signed manifest — nothing else is reachable

Azure OpenAI · gpt-4.1connected

LLM / model endpoint · Microsoft Azure · scopes chat.completions, embeddings

sanctions.match.adjudicateconnected

Tool / function · In-house matcher v9 · scopes adjudicate

Customer 360 (Restricted)connected

Data source · Snowflake · scopes read

core.accounts.readconnected

Tool / function · Core banking (Finacle) · scopes balance, statement

Policies in force

POL-001 · No customer PII outside IndiaPOL-002 · No account closure without approvalPOL-004 · No customer data sent to public LLMPOL-006 · PII masking requiredPOL-011 · Narrative grounding required

Recent decisions

Live gateway stream filtered to this agent

No gateway traffic for this agent in the current buffer.

Open risks

Drill into the investigation

No open risks on this agent.

Ledger entries

Hash-chained decision records

No ledger entries surfaced in the current window.

Governance obligations

  • Quarterly attestation by K. Menon under MB-04
  • Restricted actions parked for a named human approver
  • Kill switch tested; revocation propagates in under 30 seconds
  • Evidence retained ten years for regulator inspection