The language of AI code provenance.
Clear definitions of the terms behind tracking AI-authored code — who wrote which line, with what model, and how that record is signed and audited. Start with the concept you need, or read the full provenance guide.
Line-level provenance is a record of the origin of each individual line of code — which author, AI agent, model, and prompt produced it.
AI code attribution is the practice of recording which AI coding agent produced which code, so that AI-generated lines can be distinguished from human-written ones.
Agent attribution is the assignment of code changes to the specific AI agent that produced them, across all the coding tools a team uses.
AI code governance is the set of policies and controls a team applies to AI-generated code — defining where AI may write, what evidence must be recorded, and when human review is required before AI-authored changes can merge.
Signed code provenance is an authorship record protected by a cryptographic signature, so it can be verified and is tamper-evident.
An AI code audit trail is a durable, queryable record of AI-authored changes over a codebase's history — which agent wrote what, when, under what policy, and whether that record was signed.
An AgentTrace is a single structured record of one AI agent's contribution to a commit: the agent, model identifier, files and line ranges changed, an optional prompt excerpt, the commit revision, and an ed25519 signature.
See line-level provenance on a real repo.
AgentDiff records which agent wrote which line, signs it, and keeps it in your git history. Open the live dashboard or book a walkthrough.