Artificial Intelligence
Everything we publish on building with AI, from retrieval and agents to the evaluation practice that decides whether any of it can be trusted in production.
AI
What artificial intelligence can and cannot do in a business, stated plainly, and how to tell the difference before you spend money.
Machine Learning
Models that learn from your data: when they beat simple rules, what they need to work, and how they fail.
AI Agents
Software that plans and takes actions rather than answering questions. What changes when a system can act on your behalf.
Prompt Engineering
Getting reliable output from a language model, and treating the prompt as production code rather than a text box.
RAG
Retrieval-Augmented Generation: making an AI answer from YOUR documents instead of guessing from memory.
MCP
Model Context Protocol: the emerging standard for connecting AI models to your tools and data without bespoke glue for every integration.
AI Engineering & Product
Evaluation, guardrails, cost per outcome and how much a feature may do unsupervised.
AI Strategy & Transformation
Where AI is applied, where it is refused, and whether the change actually paid.
How we approach Artificial Intelligence
The model is rarely the reason it failed
Most AI work that stalls does not stall on model quality. It stalls because nobody agreed what a correct answer looks like, so there is no way to tell whether the last change helped. Evaluation is the first thing cut for time and the one thing that decides whether the system can be improved at all. We build the evaluation set before the pipeline, because a system you cannot measure is a system you can only have opinions about.
Retrieval is a data problem wearing an AI costume
Retrieval augmented generation fails on chunking, freshness, access control and duplicate documents far more often than on the model reading them. If two versions of a policy are in the index, the answer is a coin toss, and no amount of prompt work fixes it. The work is nearly always upstream, in the content and its permissions, which is unglamorous and is where the result actually comes from.
Agents multiply the blast radius, not just the capability
The moment a system can act rather than answer, every weakness it had becomes a change to something real. That shifts the question from accuracy to authority: what is it allowed to do, what needs a human, and what is the reversal path when it is wrong. We would rather ship a narrow agent with a hard boundary than a general one with a warning in the documentation.
Every page above is written to be used rather than skimmed, and each links back here and across to the others. Nothing on this page exists only to hold a keyword.
Other topics: Cloud, Cybersecurity, Enterprise Infrastructure, Oracle, Data and Analytics.