Blog

AI in production, in practice.

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

FeaturedJul 30, 2026

The AI Bill Tells You What You Spent. Not What the Spend Accomplished.

Your AI invoice reports what you consumed, not what it accomplished. Rate card, benchmark task cost, and cost per accepted result are three different numbers.

Read the article
Two printed records lie side by side on a slate desk: a uniform machine-set billing statement whose rows all look alike, and a hand-kept run ledger whose final column carries small ink checkmarks and one crossed-out mark.

All Articles

Latest from our team

A glass office wall with a hand-drawn seven-stage software delivery lifecycle diagram, the evaluation stage circled in red marker
Agentic Engineering

What an AI-Native SDLC Actually Looks Like, Phase by Phase

Code got cheap. The process that governs it still charges the old price.

Read article →
Overhead flat-lay of five printed evaluation sheets on a slate worktop, labelled Task Fit, Latency, Total Cost, Residency and Exit Cost
Agentic Engineering

How to Choose Between GPT, Claude, Gemini and Open Source

A model comparison written in March is a historical document by September. The benchmark table that justified it is stale. The model that won has been…

Read article →
Overhead flat-lay of five printed requirement pages on a slate desk labelled Intent, Evaluation, Failure Modes, Safety and Cost, linked by an ink line
Agentic Engineering

What Your PRD Is Missing When the Product Is Probabilistic

"The assistant returns an accurate summary of the ticket." That sentence passes review, gets signed off, and cannot be verified, because there is no single run…

Read article →
A monitor showing an AI assistant answer with visible source citations, an open reference panel, and approve, edit and reject controls
AI Adoption

The AI UX patterns that decide whether anyone uses your feature

AI UX patterns that earn trust: transparency, explainability, confidence indicators and review loops, plus a build order ranked by real stakes.

Read article →
A glass office wall with a hand-drawn LLM architecture diagram in marker, labelled orchestration, model, retrieval and observability, one box crossed out and redrawn
Agentic Engineering

The AI Product Architecture Decisions You Cannot Cheaply Undo

Architecture diagrams for AI products have converged on the same picture. Four stacked boxes, orchestration over model over retrieval over observability, with…

Read article →
A cork planning board with five pinned phase cards reading discovery, MVP, production readiness, scaling and enterprise rollout with week ranges
AI Adoption

How Long It Really Takes to Build an AI Product

Every published answer to "how long does it take to build an AI product" was measured on something that isn't an AI product. The numbers are real: 20 to 40…

Read article →
Overhead flat-lay of five printed job specifications on slate, labelled Software, AI, Agent, Evaluation and Product, joined by an ink line
Agentic Engineering

What Skills Your AI Development Team Actually Needs

Five people answer the same job ad. A researcher who fine-tunes vision models. An engineer who has shipped three retrieval systems into production. A data…

Read article →
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 →