01 / Production
Anomaly detection at scale
A Z-score-based price anomaly system running over 1M+ Amazon FBA records, surfacing outliers automatically rather than via manual scanning.
FBA Research PlatformAll services
Primary practice· 01
AI Automation & Agents
Custom workflows, RAG pipelines, agent systems, and LLM integrations. Built to hold up under production load, not just demo well on a laptop.
The shape
The pain· 01
Your team spends hours each week on repetitive work that doesn't need a human. Manual data scanning, document parsing, customer triage, copy and paste between tools. Work that's both tedious and high stakes if missed.
Approach· 02
We don't drop in a chatbot and call it done. We map the workflow first. What's the actual decision sequence, where's the cognitive load, what does failure look like?
Initiatives· 03
Concrete things we've built or are building, against this kind of pain.
02 / Pattern
Document & data processing pipelines
Pattern: messy unstructured input (PDFs, spreadsheets, emails) into a queryable structured store with an LLM doing the parsing and an audit trail behind it.
03 / Pattern
Internal copilots & knowledge agents
RAG over a client's internal documents so their team can ask questions in plain language instead of digging through files.
Roadmap· 04
How an engagement typically unfolds. Not rigid, but the shape repeats.
Phase 01
Map the workflow. Find what's actually slow and where mistakes happen. Decide what to skip.
Built with· 05
OpenAI · Anthropic · LangChain · Vector DBs · Python · TS