# Evidence engineering

The design of versioned, queryable evidence linking requirements, decisions, implementations, tests, evaluations, approvals, deployments, runtime signals, and lifecycle actions.

core-concept · Evaluation & verification · maturing · Reviewed 2026-08-09

## 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



## Related knowledge

- [Intent engineering](https://aisdlc.ai/agentic-engineering/intent-engineering) — The practice of turning goals into versioned specifications, constraints, interfaces, invariants, decision rights, acceptance criteria, and testable outcomes before agents implement them.
- [Independent verifier systems](https://aisdlc.ai/agentic-engineering/multi-agent-verification) — A separation-of-judgment architecture in which builder agents, evaluator agents, deterministic checks, domain experts, and authorization authorities challenge different failure surfaces.
- [Observability & control](https://aisdlc.ai/agentic-engineering/observability-control) — The combined telemetry and enforcement architecture for tracing agent behavior, evaluating policy, obtaining approval, constraining action, revoking authority, quarantining execution, and stopping systems.

## Sources and further study

- [SLSA — SLSA provenance specification v1.2](https://slsa.dev/spec/v1.2/provenance) — An established software-supply-chain foundation for attributable build provenance. **Use:** Standard or protocol. **Limitation:** A specification defines an interface or control pattern; conformance alone does not establish authorization, security, or fitness for a use case.
- [OpenAI — Harness engineering: leveraging Codex in an agent-first world](https://openai.com/index/harness-engineering/) — A production case study in designing repositories, tools, feedback loops, and environments for agent-first delivery. **Use:** First-party case study. **Limitation:** This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.
- [OpenAI — Building self-improving tax agents with Codex](https://openai.com/index/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:** First-party case study. **Limitation:** This first-party account documents one organization, product, or implementation context and should not be generalized without local evidence.

---

This library synthesizes cited research, standards, official documentation, and clearly attributed practitioner perspectives. Maturity describes the state of a concept—not vendor endorsement, production readiness, or permission to deploy. Benchmarks and demonstrations do not replace use-case evaluation, governed controls, independent verification, or named human release authority.