← Projets
Agent Autopsy — Forensic Debugger for Failed AI Agent Runs
15-second product demo
Problem
Most AI agent failures are silent — the run completes, the status code is green, and the result is still wrong. Observability platforms show you the trace, but never the cause of death.
Business Impact
Teams ship agents that fail silently and only hear about it from angry users. Agent Autopsy turns an opaque transcript into a one-line cause of death, so engineers stop guessing and start fixing — without shipping private traces to a third-party SaaS.
System Approach
- Next.js 16 App Router app with the forensic engine in lib/autopsy.ts
- scan + diagnose API routes: heuristic classifier first, optional LLM pass second
- Five explicit failure signatures detected from transcript structure, not vibes
- Optional local Ollama (qwen3:14b) pathologist's note for root cause
- 6 Vitest tests covering the signature classifier
Key Decisions & Trade-offs
- Heuristics-first for an instant verdict — the LLM is an optional deepening, not the critical path
- Local LLM over cloud — agent traces are sensitive and stay on the machine
- Five named signatures over a black-box score — engineers want a cause they can act on
- Zero runtime dependencies in the engine — rebuilt from a v1 single-file prototype with no shortcuts
Current Status
Public and open source (MIT) at github.com/rohitguta2432/agent-autopsy. Heuristic verdicts plus optional local qwen3:14b diagnosis working; 6 Vitest tests passing. The 15-second demo diagnoses the app's own sample corpse on camera.
Roadmap
- Add more failure signatures (silent truncation, tool-arg drift)
- Framework adapters to import LangChain / CrewAI transcripts directly
- Shareable report links for team triage
What I'd Improve Next
- A hosted demo with a bundled small model so no local setup is needed
- Batch autopsy mode to run inside CI on every failed agent run
Explore More
- MyFinancial — Personal Financial Advisor — Financial planning in India is fragmented across banks, insurance, and tax documents.
- PropCheck — AI Property Trust Score for India — Indian property buyers lose lakhs to fraudulent listings on Magicbricks, 99acres, Housing.
- StellarMIND — Chat-to-SQL with RAG — Business users need to query databases without knowing SQL.
- ClinicAI — WhatsApp AI Clinic Assistant — India has 12 lakh+ small clinics running on phone calls and paper diaries.
- MicroItinerary — AI Travel Planner — Travel apps optimize for proximity and ratings.
- SanatanApp — Hindu Devotional App — Devotional users in India juggle 5+ separate apps for Chalisa, Gita, Aarti, Ramayan, and Mahabharat.
- SynFlow — Enterprise Intelligence Platform — Private deal networks rely on manual introductions and spreadsheets.
- FinBaby (Jama) — Personal Finance Tracker — Indian middle-class families track expenses across UPI apps, bank statements, and paper notebooks.
- RetailOS — Multi-Tenant Retail SaaS — Indian kirana stores and small retailers use paper registers or basic billing software with no inventory tracking, no GST compliance, and no offline support.
- TripHive — Offline-First Collaborative Trip Planner — Group trip planning is fragmented across WhatsApp, Google Docs, Maps, Splitwise, and email.
- ScamRakshak — On-Device AI Scam Detector — Indians lose thousands of crores annually to digital scams via WhatsApp, SMS, and social media.
- PaisaGuard — Family Budget Survival App — Middle-class families worldwide track expenses inconsistently — UPI apps show transactions but don't enforce budgets.
- rohitraj.tech — Engineering work is often invisible.
- tinyvoice — Fine-Tune a Model in Your Own Voice in an Afternoon — Training your own language model sounds like a PhD job that needs a GPU cluster, so most developers never try.
- snap3d — One Photo In, an Editable 3D Model Out — A photo shows you one side of an object; the other five sides are a guess.
- Reliability & Production Readiness — Load testing, observability, and API contracts.
- Open Source Repos — Browse the source code behind these projects.