Blog
Notes on trusted AI, production AI and engineering.
-
Build vs buy an AI platform: when AI needs the system around it
Build vs buy an AI platform: buy what is standard, build the system around the AI that runs your operation. Five questions to decide, and when to wait. -
Forward-deployed engineering for operators whose AI pilot has stalled
AI pilot stalled? Forward-deployed engineering takes it through four phases and four written gates, from a signed production definition to your team running it. -
AI go-live checklist: 25 questions to answer before launch
An AI go-live checklist of 25 questions in five groups: definition, data, measurement, security and approvals, operation. Answer them before you launch. -
Forward-deployed engineer vs consultant: who does what on an AI project
Forward-deployed engineer vs consultant: the consultant frames the problem and the business case, the forward-deployed team builds and runs the system. -
The forward-deployed engineering model: how it works when the system has to run
The forward-deployed engineering model: engineers work with your teams, decide what to build and own it until it runs. How it works, and when it fits. -
How to move an AI pilot to production: 7 steps
How to move an AI pilot to production in 7 steps: production definition, integration, evaluation, security review, approval gates, release and ownership. -
How do you evaluate AI agents before and after go-live?
How to evaluate AI agents: score whole tasks, not single answers, on outcome, tool calls, policy, cost and escalation, before go-live and on live runs. -
How do you design approval gates for sensitive automated AI actions?
Human-in-the-loop approval for AI agents: decide which actions are sensitive, who approves, what they see, and what happens on refusal or timeout. -
What are LLM evals, and why does production AI need them?
What are LLM evals? Repeatable tests that score an AI system against cases and criteria your owners agree on, and decide whether a change can ship. -
What does a forward-deployed engineer do in the first 30 days?
Forward-deployed engineer responsibilities in the first 30 days: a two-week diagnosis ending in a signed production definition, then the build. -
Why forward-deployed engineering is rising in 2026
Why AI companies need forward-deployed engineers in 2026: the hard part of AI moved from the model to production, and someone has to own that gap. -
How enterprises use forward-deployed engineering to move AI from pilot to production
How enterprises use forward-deployed engineers to take AI pilots to production: who they work with, what they own and how the security review gets done.