Evidence infrastructure for AI in finance

When someone asks why your AI decided, hand them proof.

AI agents now approve refunds, flag transactions, and decide credit. SwornTrace seals every decision they make into a tamper-evident record, verifiable by auditors and regulators without trusting you.

Runs in your infrastructure. Records never leave your perimeter.

Records mapped to SEC 17a-4 GDPR Art. 22 MiFID II EU AI Act Art. 12

The problem

Logs persuade people who already trust you. Auditors are not those people.

Your engineering logs were built for debugging. They miss the reasoning behind every decision, and because you can edit them, they prove nothing to a skeptical outsider. Three moments expose the gap.

01

The regulator examines

Regulators have fined firms over $2B for business happening in unrecorded channels. An AI agent is the newest unrecorded channel, and EU AI Act logging obligations for high-risk systems are now enforceable.

02

The customer disputes

GDPR Article 22 gives customers the right to an explanation of automated decisions. When the lawyer asks for proof of what your AI did, a debugging trace won't settle it. A sealed record will.

03

The auditor reviews

Annual audits ask for evidence, not architecture diagrams. Decision records with retention, integrity, and clause mapping built in turn a week of scrambling into a single export.

How it works

Capture. Seal. Map. Verify.

A lightweight SDK sits inside your agent. Everything else follows automatically.

01 · Capture

Every decision, complete

Inputs, retrieved policies, rules evaluated, tool calls, alternatives considered, outcome, confidence. All recorded at the moment of decision.

02 · Seal

Tamper-evident by construction

Records join a hash chain, are signed, and anchored to storage you don't control. Any alteration, even by you, is detectable.

03 · Map

Regulation packs

Each record is evaluated against specific clauses (SEC 17a-4, GDPR 22, MiFID II, EU AI Act 12), reporting evidence or gaps per decision.

04 · Verify

By anyone, without you

Auditors replay decisions and verify integrity with an open verifier: no access to your systems, no trust in your software required.

The SDK

Five lines inside your agent. Evidence forever.

  • Framework adapters. LangGraph and LangChain hooks stream decisions automatically.
  • Failures are evidence too. Exceptions are sealed, never lost.
  • Independent corroboration. A tool gateway keeps a second ledger that must agree with the first.
  • GDPR erasure without breaking the chain, via crypto-shredding.
  • Decision replay. Reconstruct any decision in plain language.
refund_agent.py
from sworntrace import SwornTrace

st = SwornTrace(agent="refund-agent")

with st.decision(action="approve_refund", risk_level="high") as d:
    d.add_input(request)
    d.add_context(policy, source="kb://refund-policy", role="policy")
    d.check_policy("refund-policy/section-1", passed=True)
    d.add_alternative("escalate", rejected_because="within limits")
    d.set_retention_years(6)
    d.set_outcome("approved", confidence=0.92)

# sealed, chained, anchored, verifiable by anyone

Where SwornTrace sits

Not observability. Not GRC paperwork. Evidence.

Observability tools answer "is my agent working?" for engineers. Governance platforms answer "do we have policies?" for boards. SwornTrace answers the question the other two can't: prove what this decision was, and why.

ObservabilityGRC platformsSwornTrace
Built forEngineersCompliance programsAuditors & regulators
Unit of recordTraces & spansPolicies & questionnairesComplete decisions
Captures the reasoningPartiallyNoYes
Tamper-evidentNo, editableNoYes, sealed & anchored
Clause-level mappingNoProgram-level onlyPer decision
Independent verificationNoNoOffline, open verifier

Early access

Deploying agents in a regulated workflow?

We're running shadow-mode pilots with a small number of financial firms: our SDK against one live agent workflow, in your environment, producing sealed records and a compliance report from your own traffic.

Talk to us