Autonomous decisions for regulated finance.
Cognance builds governed AI decision agents for banks and NBFCs. Our live KYC agent resolves the ambiguous cases legacy vendors dump into human queues — returning a definitive decision, with reasoning, in under a second.
The decision gap
Legacy vendors extract data. They dump the ambiguity into your queue.
Name-match tools like the incumbents read a PAN and an Aadhaar name — then, the moment the two don't line up exactly, they eject the case to a human reviewer. That manual gap is the real cost: slow onboarding, expensive review teams, and compliance exposure.
Legacy KYC utilities
Extract fields, then eject anything ambiguous to a human review queue. You keep paying for the review team — and onboarding stalls while cases wait.
₹250–450 ($3.00–$5.40) per contested case, in manual overhead
Cognance
Accepts the pre-extracted names and resolves the ambiguity itself, using governed LLM reasoning. Returns a definitive decision — approved, rejected, or held — with a confidence score and a reasoning log, via webhook.
No client-side human review. Sub-second decisions.
How it works
One API call in. A governed decision out.
A deterministic fast path resolves exact matches instantly. Only genuinely ambiguous cases reach the reasoner — and anything below the confidence threshold is routed to human review, never auto-rejected.
Client LOS
Authenticated call
Managed API
Auth + ingest
Durable queue
Reliability buffer
Decision engine
Governed reasoning
Amazon Bedrock
Model when needed
Audit store
Immutable record
// One authenticated call from your LOS{application_id: "LOAN-12345",pan_name: "Mohammed Khan",aadhaar_name: "Mohd. Khan"}// Two name strings. Nothing else.
{"event": "kyc.decision","application_id": "LOAN-12345","status": "approved","confidence_score": 95.0,"reasoning": "'Mohammed' and 'Mohd.'are common abbreviations…","execution_time_ms": 455}
Live today
Not a prototype. A deployed system.
The KYC agent runs today on AWS — a serverless pipeline behind an operational dashboard. These are measured facts from a small production test set, not projections.
~8 ms
Fast-path decision
Exact match, no LLM call
~455 ms
LLM reasoning path
For ambiguous name pairs
46
Golden-dataset examples
Real, PII-masked, growing
~$0.0003
Cost per verification
Calculated from AWS pricing
The operations console
Every decision, visible and auditable.
Operators review, override, and audit from a live dashboard — the same governance surface a compliance team uses at audit time.
Processed
105
Auto-resolved
54.3%
Pending review
48
Golden set
46
Throughput · 7-day
Reasoner
confidence: 95.0
path: fast_path
Illustrative representation of the live operations dashboard.
Who's building this
Built by a decade of regulated-FinTech engineering.
Cognance is founder-led by an engineer who has spent over ten years modernizing financial infrastructure and shipping compliance AI — the same problem, now solved independently for the NBFC sector.
10+ yrs
FinTech modernization & compliance AI
Multi-trillion $
AUM platform migration to AWS
Shipped compliance AI
98% precision, zero audit findings
Hyderabad
Where Cognance is based
The roadmap
KYC is the wedge. The suite is the moat.
KYC establishes trust inside a client. From there, the same governed decision infrastructure extends to the other back-office judgment calls that still bottleneck regulated lenders.
KYC Agent
Name-match decisioning. Deployed on AWS today.
Credit Underwriting
Autonomous credit assessment at a premium tier.
Compliance Monitor
Continuous, automated compliance scanning.
Collections Intelligence
Recovery prioritization and outreach.
Security & compliance
Built for the RBI audit.
Governance is the product. The compliance layer — isolation, audit, confidence routing, human fallback — is what separates a governed agent from a raw model call.
Data minimization
We receive only two name strings — no Aadhaar or PAN numbers, no DOB, no addresses, no documents, no biometrics.
7-day PII lifecycle
Name strings are scrubbed after 7 days. The non-PII decision record is retained for 5 years to satisfy PMLA.
Immutable audit trail
Every decision logs confidence, reasoning, timestamp, and model version — queryable for audits.
Never auto-rejects
Uncertain cases route to human review. Deterministic workflows and a zero-loss dead-letter queue guard against silent failure.
Regulatory mapping
Architected against DPDP, RBI KYC direction, and PMLA. SOC 2 readiness in progress (certification targeted).
Data residency
Hosted on AWS Asia Pacific today, with India-region residency on the roadmap.
FAQ
Questions a compliance team asks first.
What data do you actually receive?
Only an application reference and two name strings — the name on the PAN and the name on the Aadhaar. No ID numbers, no dates of birth, no addresses, no documents, no biometrics.
What happens when the AI is unsure?
It never auto-rejects. Cases below the confidence threshold are routed to human review. During early rollout, our team handles that review so the client carries zero operational burden.
How long does integration take?
About a day of client engineering: one authenticated API call and a webhook. No SDKs, no VPN, no database changes, no cloud lock-in.
Where is our data stored, and for how long?
On AWS in the Asia Pacific region today, with India-region residency on the roadmap. Name strings are scrubbed after 7 days; the non-PII decision record is retained for 5 years for PMLA.
How does pricing work?
Usage-based, per verification, with no setup fees. Pilots run free (30 days, up to 10,000 verifications). Commercial pricing is scoped per client after the pilot proves value.
Risk-free pilot
Run 10,000 verifications, free.
We integrate in about a day, run in shadow mode alongside your team, and only go live if accuracy meets the bar. Best fit: banks, NBFCs, and fintechs processing 5,000+ KYC verifications a month on an LOS or core system with a REST API.
- ~1 day of client engineering
- Shadow mode: parallel to your manual team
- You keep your brand — we're invisible backend infrastructure