←back to thread

Agentic QA – Open-source middleware to fuzz-test agents for loops

32 points Saurabh_Kumar_ | 1 comments | 03 Dec 25 14:38 UTC | HN request time: 0.195s | source

I built this because I watched my LangChain agent burn ~$50 in OpenAI credits overnight due to an infinite loop.

It's a middleware API that acts as a 'Flight Simulator'. You send it your agent's prompt, and it runs adversarial attacks (Red Teaming) to catch loops and PII leaks before deployment.

Code & Repo: https://github.com/Saurabh0377/agentic-qa-api Live Demo: https://agentic-qa-engine.onrender.com/docs

Would love feedback on other failure modes you've seen!

1. Saurabh_Kumar_ ◴[03 Dec 25 14:42 UTC] No.46135018[source]▶
HN, OP here. I built this because I recently watched my LangChain agent burn through ~$50 of OpenAI credits overnight. It got stuck in a semantic infinite loop (repeating "I am checking..." over and over) which my basic max_iterations check didn't catch because the phrasing was slightly different each time. Realizing that "Pre-Flight" testing for agents is surprisingly hard, I built a small middleware API (FastAPI + LangChain) to automate this. What it does: It acts as an adversarial simulator. You send it your agent's system prompt, and it spins up a 'Red Team' LLM to attack it. Currently checks for: Infinite Loops: Semantic repetition detection. PII Leaks: Attempts social engineering ('URGENT AUDIT') to force the agent to leak fake PII, then checks if it gets blocked. Prompt Injection: Basic resistance checks. Tech Stack: Python, FastAPI, Supabase (for logs). It's open-source and I hosted a live instance on Render if you want to try curl it without installing: https://agentic-qa-api.onrender.com/docs Would love feedback on what other failure modes you've seen your agents fall into!