Summit Cognitive, Inc.

Decision Receipt

Admissibility infrastructure for autonomous AI systems

decrec.summitcognitive.ai

The problem

Autonomous AI agents are executing at machine speed without admissibility evidence

Devin, Codex, Claude, Jules, and Copilot are writing code, merging PRs, modifying infrastructure, and deploying services. Most produce zero provenance, zero replay capability, and zero policy attestation.

If an AI-generated action cannot be replayed and verified independently, it should not reach production.

The solution

Every autonomous action gets a cryptographically signed receipt

Decision Receipt evaluates admissibility through 9 policy rules, deterministic replay, evidence provenance validation, and Ed25519 signing. The result: an independently verifiable proof that the action is allowed to matter.

Submit Evidence

CI results, code reviews, agent traces, security scans. Each source gets provenance metadata.

Evaluate Admissibility

9 deny-by-default rules: source diversity, provenance, replay, decision rights, confidence.

Receive Receipt

Signed proof with evidence hashes, replay verification, policy checks, and attestation chain.

Enforce

Block merge, halt deployment, escalate for review. No receipt, no production authority.

Production data

Running live on real repositories

119+

Receipts issued

59%

Acceptance rate

74

Webhook deliveries

5

Agents tracked

Processing real GitHub PRs from BrianCLong/summit. Agents: human, dependabot, Devin, Codex, Jules. Acceptance rate improving daily as evidence enrichment takes effect.

Integration

Works with your existing stack

Platform	Integration	Enforcement
GitHub	Webhook + Action	PR status checks + comments + merge gate
GitLab	Webhook	MR evaluation
Bitbucket	Webhook	PR evaluation
CI/CD	API + Action	Deployment gate
Slack/Teams	Outbound webhook	Real-time notifications
Security tools	SARIF export	Dashboard integration

Setup: one webhook URL. First receipt in under 60 seconds.

Strategic position

Cognition (Devin) optimizes for autonomous capability

Summit optimizes for admissible authority

Those are not the same market. As autonomous agents become more powerful, the need for reproducibility, auditability, and provenance increases nonlinearly. Decision Receipt becomes more valuable as autonomy scales.

Autonomy without admissibility is unauthorized execution.

Pricing

Start free. Prove value. Scale.

Tier	Price	Receipts	Features
Free	$0/mo	100/mo	Full API, signed receipts, replay, verify
Pilot	$99/mo	10,000/mo	+ Webhook, Trust Packs, custom policies, priority support
Enterprise	Custom	Unlimited	+ Sovereign deploy, NIST alignment, SLA, dedicated support

Get API Key — Free Schedule Pilot Conversation

Next step

Try it in 30 seconds

curl https://decrec.summitcognitive.ai/quickstart.sh | bash

Signs up, issues receipts (ALLOWED + BLOCKED), verifies, prints stats. No account required.

Visit decrec.summitcognitive.ai Try the Playground

Summit Cognitive, Inc. | brian@summitcognitive.ai | Alma, CO