Notes from the field.
Essays on forward deployed engineering, eval work, and the messy path from AI pilot to production.
What is a Forward Deployed Engineer?
A Forward Deployed Engineer embeds inside a customer organization to learn the domain, ship governed AI systems in production, and transfer capability, closing the gap between demo and go-live.
The eval engineer role nobody talks about
Forward Deployed Eval Engineers keep production agents accurate, safe, and compliant after go-live through continuous evaluation, guardrails, and drift monitoring.
Why most AI pilots never reach production
Most enterprise AI pilots fail to reach production because teams lack embedded engineers who combine domain context, integration skill, security fluency, and operational eval discipline.
Context engineering across enterprise systems
Context engineering is the practice of designing and governing the information layer agents use: unifying data from source systems through MCP, retrieval, and policy filters inside the client perimeter.
Why pods beat traditional consulting
FDE pods embed certified builders and eval engineers who ship in production and transfer capability: unlike traditional consulting models that often exit at go-live.
Would it survive inside a real organization?
FDE Factory grades every capstone on one question: would this survive inside a real organization? Partner feedback on security, evals, operability, and handoff determines certification.