Evidence engineering

Definition

The design of versioned, queryable evidence linking requirements, decisions, implementations, tests, evaluations, approvals, deployments, runtime signals, and lifecycle actions. The durable handoff is not the conversation. It is the attributable chain from intent to deployed outcome.

Software provenance is established; complete AI and agent lifecycle evidence models are emerging.

Why it matters

The durable handoff is not the conversation. It is the attributable chain from intent to deployed outcome.

The operating shift is from “Screenshots and chat transcripts” to “Machine-readable chain of proof.”

System anatomy

Practice 1

Bind evidence to the exact released artifact

Practice 2

Preserve verifier identity and decision authority

Practice 3

Carry runtime outcomes into recertification

Important distinctions

Screenshots and chat transcripts

This concept moves the engineering system toward machine-readable chain of proof.

Implementation signals

• Bind evidence to the exact released artifact
• Preserve verifier identity and decision authority
• Carry runtime outcomes into recertification

Failure modes

• Evidence assembled after the decision
• Artifacts that cannot be traced to what actually ran

Sources and further study

1. SLSA — SLSA provenance specification v1.2

   An established software-supply-chain foundation for attributable build provenance.

   Use in this library: Standard or protocol. A specification defines an interface or control pattern; conformance alone does not establish authorization, security, or fitness for a use case.

   standard · standard · Published 2026
2. OpenAI — Harness engineering: leveraging Codex in an agent-first world

   A production case study in designing repositories, tools, feedback loops, and environments for agent-first delivery.

   Use in this library: First-party case study. This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.

   engineering · engineering · Published 2026-02-11
3. OpenAI — Building self-improving tax agents with Codex

   A feedback-loop pattern that turns practitioner corrections and production traces into evaluations and scoped engineering work.

   Use in this library: First-party case study. This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.

   engineering · engineering · Published 2026-05-27