# AgentShield

- **Event:** [The Harness Engineering & Model Wrangling #SFTechWeek Hackathon](https://cerebralvalley.ai/e/mongodb-sftw-hackathon)
- **When:** Sun, Oct 11 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Akhil Vallala](https://cerebralvalley.ai/u/Akhil_v_krishna)
- **GitHub:** https://github.com/Akhilvallala1/agentshield
- **Demo video:** https://youtu.be/rxwgwG6DUzY
- **Gallery:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/7

AgentShield is a self-evolving guardrail layer for agent-to-agent (A2A) traffic. When AI agents pass customer data to each other, off-the-shelf PII filters catch names and SSNs but miss company-specific identifiers like policy numbers and adjuster badges (0% recall at baseline).

AgentShield sits between agents as a gateway. The inline path is fast and cheap: compiled regex rules plus Presidio NER, no LLM, ~16 ms. Asynchronously, an LLM auditor reviews forwarded traffic and records what leaked, storing only the shape, never the value. A synthesizer writes a new regex rule, and a validator gates it on hard metrics: recall on 300 labeled messages and false positives on 500 lookalike clean messages. A human approves in the terminal, and a MongoDB change stream hot-loads the rule into the live gateway with no restart. Every change writes a new eval generation (recall 0.51 → 0.75 in the demo, zero new false alarms). It also prunes itself: rules that drift into false positives across independent sessions are proposed for retirement, again with human approval. Recursive self-improvement that is measured, not claimed.

## More from The Harness Engineering & Model Wrangling #SFTechWeek Hackathon

- [DrawTalk Harness](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/4)
- [Bayflow](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/5)
- [Procurator](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/6)
- [SuperBid](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/8)
- [Team Tesfa](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/9)
- [Routemind](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/10)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/7. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt
