Blog
Notes on trusted AI, production AI and engineering.
-
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. -
AI trusted by design: governance built into the operation
AI governance by design builds permissions, approval gates, traceability and monitoring into an AI system before go-live. The six principles, step by step. -
From AI pilot to production: the path, the gates and the owners
AI pilot to production in four stages, each closed by a written gate with named owners who sign it. The path, the gates and who owns each one. -
Forward-deployed engineering: what it is, how it works and when you need it
Forward-deployed engineering moves an AI system from pilot to production: senior engineers work with your teams, own the path and stay until it runs. -
Why do AI pilots stall, and what moves them to production?
Why do AI pilots fail? Most stall on five open decisions: integration, security review, measurement, approvals and ownership. Here is what moves them. -
AI production readiness checklist: define production for an AI system on one page
An AI production readiness checklist starts with one signed page that defines production: scope, criteria, evaluation, security, approvals and go-live. -
Forward-deployed engineer vs solutions engineer: what each one owns
Forward-deployed engineer vs solutions engineer: one helps win the deal, the other owns getting the AI system into production. Who owns what, side by side. -
How a forward-deployed engineering engagement works, week by week
A forward-deployed engineering engagement moves an AI pilot to production in four phases, each closed by a written gate. What happens, week by week. -
AI is easy to demo. We bring your AI pilot to production.
Johnny Saffar on seventeen years of software and AI in production at OrNsoft: three lessons from our clients on what it takes to run a system for years.
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