Coding agents

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

Articles

Practical guides

How to run a coding model locally with Ollama

Install Ollama on macOS, Linux or Windows, pick a model suited to code, set the context window and connect OpenCode or Cline, according to the official documentation.

· 5 min read

Coding agents

Week of October 12: coding agents go team-mode

OpenCode, Codex CLI and Claude Code shipped multi-agent updates between Oct 11 and 16, after VS Code, while Meta unveiled a huge coding model.

· 3 min read

Surveys

Stack Overflow 2026: agents in, production off-limits

Stack Overflow's 2026 survey: 66% of developers using agents cite Claude Code, yet only 19.9% of respondents already use AI for production work.

· Updated on · 3 min read

Security

AI-generated code: a known flaw in 45% of tasks

Veracode's 2025 GenAI Code Security Report and a METR study are reminders that speed is not enough without a change in method.

· Updated on · 3 min read

Coding agents

Gartner's first Magic Quadrant for coding agents

Gartner's first Magic Quadrant for coding agents names Anthropic, Cursor, GitHub and OpenAI Leaders, and expects the IDE to become optional for most teams.

· Updated on · 3 min read

Tools