89 curated builds·evidence labeled
COMMUNITY OBSERVED

Pi-Heed Tool Call Auditor

An agent security supervisor that audits side-effecting tool calls against the user's explicit request.

Overview & Result

Autonomous coding agents can hallucinate or exceed their mandate by deleting files or executing unexpected terminal commands. Pi-Heed acts as an in-line auditor: before any side-effecting tool runs, Jev compares the action against the user's prompt and halts unauthorized operations.

How Jev fits in the loop

  1. Listen for proposed agent tool calls (e.g. bash execution, file overwriting).
  2. Feed the user prompt and the tool invocation payload into Jev Score.
  3. Evaluate the alignment score: does the requested action reasonably fulfill the user goal?
  4. Auto-approve safe actions; prompt the user or abort if the score falls below threshold.

How to reproduce

  1. Clone Nyarlathoteppppp/pi-heed and hook it into the Pi agent runtime.
  2. Trigger an agent workflow that attempts file writes, bash commands, or network requests.
  3. Inspect how Pi-Heed scores tool parameter alignment and blocks unprompted destructive actions.

Why this build matters

Solves the primary trust barrier in autonomous coding agents by enforcing automated, low-latency oversight over dangerous tools.

Limitations

  • Relies on clear natural language descriptions of the tool's intended effect.
  • Cannot analyze deeply obfuscated shell scripts or complex binary executions.
  • Requires user confirmation for low-confidence boundary decisions.

Patterns