Insights
Articles and tutorials for people who buy and build AI.
What AI changes in a business process and what it costs, written so a founder and an engineer can read the same page. Each piece starts with a short answer and ends with its sources.
Articles
Arguments with numbers: what works, what it costs, and when not to do it.
- Article
When AI cuts the hours, a fixed milestone price on published rates splits the saving instead of hiding it
Hourly billing hands every saved hour to the client, an opaque fixed price hands it to the vendor; a worked example shows a middle that both sides can check.
11 min read - Article
With an AI pair in every repository, we automate the checks and keep five decisions human
How the engineering team works with AI coding assistants: what runs automatically on every change, what a person always decides, and what we have not measured yet.
8 min read - Article
Why every case study here carries an evidence label
Numbers on this site now say where they come from — measured, estimated or illustrative — and whether anyone will vouch for them.
2 min read - Article
What gets a company cited by ChatGPT and Perplexity: evidence and mentions, not markup
What published research says about being cited in AI answers, which tactics have measured effects, which are hygiene, and a checklist for the engineer who has to implement it.
9 min read - Article
Do not do ML yet: five signs a rule, a report or a spreadsheet beats a model
Five conditions under which a machine learning project costs more than it returns, what to build instead, and how to tell when a model starts to pay.
9 min read - Article
95% of AI pilots show no P&L impact, by one count. Agree the metric before you build the model.
Four studies from 2025 and early 2026 agree that most companies see little measurable return from AI, and the common failure sits on the business side, so the fix is a metric, a baseline and a decision rule written before anything is built.
8 min read - Article
A vibe-coded prototype costs a weekend. Production costs the rest.
AI made prototypes nearly free, but the work that turns a demo into a system people rely on did not shrink, so a prototype should be budgeted as a specification rather than as most of the product.
9 min read - Article
AI made writing code cheaper. It did not make software projects cheaper by default.
Controlled measurements show modest or negative speed-ups from AI coding tools, and coding is a minority of project time, so an honest AI discount is small and can be placed phase by phase.
9 min read
Tutorials
Step-by-step builds with code, for the engineer who will maintain the system.
- Tutorial
Recommendations for an online store: ship a co-view baseline first, add two-tower retrieval only when a test says it pays
A two-stage plan for product recommendations, with the business case, working pandas code for the baseline, the architecture that comes after it, and how to prove either one in an A/B test.
11 min read - Tutorial
An AI agent is a model, a loop and a permission list, and the limits belong in code
What an AI agent is in plain terms, an 80-line agent with three tools and hard limits, how to test it on past cases, and how to estimate what it costs to build and run.
12 min read - Tutorial
For a company knowledge base, start with RAG and a test set, and fine-tune only for format
A decision table for RAG versus fine-tuning, and a two-week test that shows whether retrieval over your own documents answers your own questions well enough.
11 min read