# Minimal Verifiable Agent Execution Demo POP + CrewAI + Audit Evidence

**URL:** <https://forum.langchain.com/t/minimal-verifiable-agent-execution-demo-pop-crewai-audit-evidence/3124>\
**Category:** Talking Shop\
**Created:** [March 10, 2026, 8:07pm UTC](https://forum.langchain.com/t/minimal-verifiable-agent-execution-demo-pop-crewai-audit-evidence/3124 "2026-03-10T20:07:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![joy7758](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/joy7758/32/2553_2.png) [@joy7758](https://forum.langchain.com/u/joy7758)\
**Post date:** [March 10, 2026, 8:07pm UTC](https://forum.langchain.com/t/minimal-verifiable-agent-execution-demo-pop-crewai-audit-evidence/3124/1 "2026-03-10T20:07:02Z")

</div>

Hi everyone,

I’ve been experimenting with a minimal governance pipeline for AI agents.

The idea is simple: if agents are going to execute real tasks and call tools, we need a way to audit what actually happened.

This demo demonstrates a minimal architecture:

Persona (POP)  
→ Agent Runtime  
→ Execution Trace  
→ Audit Evidence (ARO-style record)

Key points:

• deterministic demo (no API key required)  
• CrewAI agent workflow  
• append-only audit evidence  
• minimal governance pipeline

Repo name:  
joy7758 / verifiable-agent-demo

Run locally:

bash scripts/run\_demo.sh