Topics

Each topic gathers the articles and the tools attached to it.

Coding agents

Agents that write, run and fix code: real autonomy, orchestration of several agents, permissions granted, and measured effects on software teams.

Editors supercharged with AI: completion, built-in agents, project memory, and what these features really change in a developer's day-to-day work.

The models themselves: families, price per million tokens, code benchmarks, open weights, and the criteria teams use to pick a supplier.

The infrastructure behind the agents: model hosting, APIs, managed services, running costs, and how much of it depends on a few suppliers.

Emerging building blocks: reasoning, autonomous agent use, embedding inside tools, evaluation methods, and announcements that really move the market.

Bets worth watching: usage scenarios, working methods, process redesigns, and hypotheses that have not yet proven themselves in the field.