AI Agents Need More Than Logs: Why I Built NovaFabric

Description and use

NovaFabric provides tamper‑evident evidence of AI agent runs, enabling auditors, researchers, and security engineers to replay, diff, and verify past executions.

Problem

After an AI agent finishes its work, can we prove what it actually did? Traditional logs are not sufficient evidence for audit, security, or reproducibility.

Outcome

NovaFabric provides tamper‑evident, portable evidence of AI agent runs, enabling audit, forensic replay, and structural diffing. Evaluation showed 100% capture of model and tool calls, detection of all tampering classes, and localization of 140 injected mutations.

Workflow

• 1. Run nova capture python my_agent.py to record the execution into a Run Capsule.
• 2. Seal the capsule with nova seal to add cryptographic signatures and timestamps.
• 3. Replay the capsule using nova replay --mode forensic, mocked, exact, or semantic to reconstruct or test the run.
• 4. Diff two capsules with nova diff to locate changes.
• 5. Package the sealed capsule into an Evidence Bundle for auditors or researchers.

Evidence

NovaFabric captures a run into something called a Run Capsule: a structured folder describing one execution.

Source

NovaFabric combines established technologies: DSSE for signing, RFC 3161 trusted timestamps, Merkle logs for append‑only history, cryptographic redaction records.

Source

In the paper’s controlled experiment, structural diff correctly localized all 140 injected mutations across seven tested mutation classes.

Source

Mocked replay avoided live model calls in 10/10 tested scenarios, but only 2/10 tool‑using workloads completed, because tool responses were not yet being substituted in the evaluated version.

Source