Blog
Notes on trusted AI, production AI and engineering.
Where does your pilot stand? AI production readiness scorecard.
-
How to scope an AI engagement from pilot to production
Scope an AI engagement from pilot to production on one page: what live means, the systems involved, acceptance targets, owners and gates. A buyer's guide. -
RAG vs fine-tuning for production AI: how to choose
RAG vs fine-tuning for production AI: RAG supplies current facts, fine-tuning changes behavior. How to choose, and what RAG needs in production. -
Signs your operation has outgrown off-the-shelf software
Outgrown off the shelf software? Seven signs, how to choose between configuring, extending or building, and how to move in steps without a big bang. -
What does it cost to run an AI system in production? Seven budget lines
What it costs to run an AI system in production: the token math with official prices dated November 2026, and the seven budget lines a pilot never carried. -
How to scale an AI pilot from one team to the whole company
To scale an AI pilot beyond one team, write down what that team did by hand, fix five things, then add one team at a time. The steps, in order. -
Human in the loop vs human on the loop: choosing the control model
Human in the loop vs human on the loop: a person confirms before the action, or supervises after it starts. How to choose by consequence, with a stop path. -
Workshop: can a stranger read your data? The 10-minute check before go-live
Online workshop, December 1, 2026, 12:00 ET, 50 minutes: the 10-minute check that shows what a stranger can read in your app before go-live. Register here. -
How we work: we test our own demo before we ask you to test your app
Two checks on our own demo app, with invented data: what a stranger could read before go-live, and a restore drill. What we saw, and what it does not prove. -
Agentic AI from pilot to production: what changes when agents act
Agentic AI from pilot to production: five decisions that change when an agent can act, from tool access and approvals to evaluating steps and ownership. -
Integrating an AI pilot with the systems you already run
AI integration with existing systems: map what the pilot touches, set read and write access, decide who it acts as, plan for failure and test on a copy. -
LLM observability vs monitoring: what each one tells you
LLM observability vs monitoring: monitoring tells you something is wrong, observability helps you find why. What each tracks, and what to set up first. -
How to choose a forward-deployed engineering company: 12 questions
How to choose a forward-deployed engineering company: 12 questions on ownership, production, governance and the first 30 days, and the answers to expect.
From the archive
All archived articles →-
AI Governance Is Not a Constraint — It’s the Only Way to Scale
-
AI Agents, Automation, and the Myth of Autonomous Workflows
-
Build, Buy, or Orchestrate? Rethinking Enterprise AI Strategy in 2025
-
From AI Tools to AI Systems: The Architectural Shift Enterprises Can’t Ignore
-
Why Most Enterprise AI Initiatives Quietly Fail After the Demo