Blog

AI in production, in practice.

Real workflows, measured outcomes, and the lessons from an 18-month internal rollout — no hype.

All Articles

Latest from our team

A monitor showing a review queue of identical rows with amber status pills, the list running past the bottom of the screen
AI Adoption

Your Engineers Have Copilot. Your Delivery Speed Did Not Change.

The same tool has been measured making developers 55% faster and 19% slower, and both studies were carefully run.

Read article →
A monitor on a wooden desk showing an operations dashboard where every status tile is green and every trend line is flat
Agentic Engineering

Your AI Feature Passed Every Eval and Is Failing Right Now

Every test passed and the feature has been wrong for six weeks. The six signals a production AI feature needs, which of them should page a human, and who owns the response.

Read article →
Glass wall in an engineering room with a hand-drawn five-part acceptance criterion in marker: metric, threshold, sample, reviewer, fail action
Agentic Engineering

How to Test AI Features When Outputs Are Non-Deterministic

Somebody in your organization is signing off on releases using a definition of "passing" that stopped describing the system. If you run engineering or QA at a…

Read article →
AI Adoption

How Much Does AI Product Development Cost in 2026

The model API bill is usually the smallest of seven budget lines. What an AI product costs to build and to run in 2026, with realistic ranges and the driver behind each one.

Read article →
Overhead flat-lay of three printed documents on a slate desk headed Employment Offer Letter, Agency Statement of Work and Monthly Engagement Agreement, connected by a drawn ink line
AI Adoption

Should You Hire an AI Team, Outsource It, or Go Fractional?

Two companies approve the same AI budget in the same quarter. Twelve weeks later, one has a claims-triage workflow running in production and a second one…

Read article →
Overhead flat-lay of four printed evaluation sheets on slate, labelled CFO, CTO, COO and CISO, connected by a thin ink line
AI Adoption

Why Your AI Business Case Dies in the Second Meeting

A CFO and a CISO can read the same AI proposal and reach opposite conclusions without either of them being wrong. One is reading a payback horizon. The other…

Read article →
A monitor on an operations desk showing a work-queue interface with severity, assignee and due-time columns and amber status flags
Agentic Engineering

Nobody Designs the Screen Where AI Agent Failures Land

Somewhere in the deployment there is a spreadsheet called something like "agent issues (temp)". It has no schema and no owner. Somebody made it in week two,…

Read article →
A hand-drawn seven-box workflow diagram on an office glass wall, labelled Trigger, Context, Model, Validate, Action, Human and Log
AI Adoption

What Is AI Workflow Automation, and When Does It Pay Off?

Rule-based automation breaks in your face. That turns out to be its best feature, and it is the one thing an AI workflow quietly takes away.

Read article →
A glass office wall with a hand-drawn seven-box architecture diagram labelled retrieval, tools, orchestration, evals, permissions, observability and owner
Agentic Engineering

Why RAG Is No Longer Enough for Enterprise AI

The retrieval pilot works. It answers questions about the policy library, the contract archive, the support history. It demos beautifully. Eleven months later…

Read article →