Making Agent Autonomy Safe and Accountable

TrustRelay exists because AI coding agents are writing more code than ever — and the review process wasn't designed for autonomous software contribution.

Our Mission

We believe AI coding agents will transform software development, but trust must be earned through independent verification, not assumed. TrustRelay provides the authorization layer that makes agent autonomy safe, accountable, and economically useful for enterprises.

Our hypothesis is that platform and security teams will allow TrustRelay to replace some mandatory manual review for low-risk, agent-authored pull requests — when it provides reliable attribution, required evidence, a reproducible policy decision, an understandable explanation, and a customer-controlled recovery path.

Our Values

Safety by Default

Every design decision defaults to the safe path. BLOCK always takes precedence over APPROVE. Safety is architectural, not aspirational.

Accountability

Every decision is attributed, signed, and immutably recorded. There is no action without a traceable authorization path.

Transparency

Authorization decisions are reproducible, explainable, and independently verifiable. The evidence is available for inspection by any authorized party.

Customer Control

You define the policy. You control the recovery path. TrustRelay provides the deterministic framework, but your organization retains authority.

Our Team

TrustRelay is built by a team with deep experience in authorization, platform engineering, and AI safety.

Chris DiPesa

Founder & CEO

Deep experience in platform engineering, developer tools, and AI infrastructure.