Agent process evidence improves safety and accountability in ai software development
Agentic process evidence
Artificial IntelligenceSoftware Engineering
Summary
AI agents are now helping write and manage software but their work disappears after each session, making it hard to track what they did or hold them responsible. This causes problems for security and compliance because we can't see their decisions or ensure they follow company rules. The authors propose Agentic Process Evidence (APE), a system that securely records what AI agents do and links their actions to outcomes. This helps companies keep control, audit, and govern AI contributions like they do for human developers.
What this means in practice
- •For software security teams: Detect and govern autonomous AI coding activities to reduce supply chain vulnerabilities and improve compliance.
- •For devops engineers: Use tamper-evident process records to integrate AI agents safely into infrastructure changes with policy enforcement.
- •For financial compliance officers: Maintain detailed, auditable AI process logs to meet regulatory standards in automated software development.$Commercial implications: Enables regulatory-compliant AI governance tools for industries requiring strict audit trails.
Authors
Yuval Kainan, Carmit Hershman
Abstract
The way software gets built is changing dramatically. AI agents now create pull requests, select dependencies, refactor codebases, interpret test failures, and execute infrastructure changes across the entire Software Development Life Cycle (SDLC). AI agents are autonomous team members, but unlike human engineers, they are ephemeral - their reasoning, decisions, and tool calls vanish the moment the session ends. Modern Security incidents involving intent mismatch or injection are becoming increasingly common - forcing us to address AI Agents as an insider threat. No widely adopted standard yet enables agentic provenance and governance and its obvious that you can't hold an ephemeral process accountable. The git log was designed for human commits. It shows what changed. It does not show what an AI agent did, which model it used, which tools it called, or whether anyone was accountable for the outcome. Every governance framework, every audit trail, every compliance control in the SDLC was built around one assumption: a human made the decision. That assumption no longer holds. This shift introduces 3 main procedural problems (not addressing scale) - Supply-chain vector - The agentic coder is software, so it is a supply-chain security risk. Policy guardrails - How to ensure the agentic coder is compliant with the policies of the organization. Task-alignment - How to align the agentic coder on its tasks and goals. We introduce Agentic Process Evidence (APE), a signed, tamper-evident, machine-readable attestation of agentic processes, linking the sessions to their outcome (process-aware logging). APE enables Policy-as-Code control over the agentic processes, allowing for human in the loop only when it's needed. We support the in-toto style attestation framework, and the protocol is aligned with the relevant regulations