AI-Assisted Coding·8 min read
AI Coding ROI With Guardrails
A practical governance workflow for measuring AI coding ROI with Cursor rules, MCP boundaries, and review guardrails.
June 20, 2026·Rogier Muller
Cursor Research
Field notes on Cursor rules, subagents, MCP setup, AI code review, and team adoption habits that hold up in production repositories.
Start with Cursor subagents, MCP training, and team conventions.
Cursor Features·8 min read
Cursor Rules for Team Automations
A practical Cursor team convention for rules, skills, AGENTS.md, and safe always-on automations.
June 20, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Train Coding Agents Safely
A Cursor-first training guide for rolling out coding agents with rules, MCP boundaries, and review guardrails.
June 19, 2026·Rogier Muller
Cursor Features·9 min read
Cursor MCP for Team Workflows
A practical Cursor MCP guide for teams using rules, skills, automations, and reviewable agent workflows.
June 19, 2026·Rogier Muller
Cursor Features·7 min read
Cursor Review Workflows With Subagents
A practical Cursor 3.7 review workflow for teams using cloud agents, rules, skills, and review receipts.
June 18, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Agents Team Checklist
A Cursor Workshop guide for using Cursor agents, rules, skills, and Bugbot in reviewable team workflows.
June 17, 2026·Rogier Muller
Cursor Features·6 min read
Cursor AI: Is Cursor Suitable for Teams and Large Codebases?
A practical cursor ai guide for teams using rules, skills, agents, and Bugbot without giving up code ownership.
June 16, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex workspace agents need repo rules
Codex workspace agents and Cursor cloud agents need repo rules: scoped boundary files, connector cards, and replay receipts reviewers can check.
May 14, 2026·Rogier Muller
Cursor Features·6 min read
Cursor cloud agent setup: the environment contract
A cloud-agent environment guide for Cursor teams: reproducible setup, a secret boundary, and review evidence before remote agents edit code.
May 14, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Agentic coding governance for engineering teams
Agentic coding governance for engineering teams: the written contracts, decision stubs, scope ledgers, and replay receipts, that keep agent diffs explainable.
May 7, 2026·Rogier Muller
AI-Assisted Coding·7 min read
The AI code review workflow that survives green CI
An AI code review workflow for agentic teams: connector ownership, scoped fixes, decision stubs, and replay evidence that hold up when CI is green.
May 6, 2026·Rogier Muller
AI-Assisted Coding·5 min read
AI agent guardrails: why every harness needs them
Why agent harnesses need guardrails: AI agent guardrails that turn complete-sounding summaries into receipts reviewers can actually verify.
May 4, 2026·Rogier Muller
Cursor Features·6 min read
Cursor subagents official docs and the missing contract
A governance guide for Cursor SDK agents: what the official docs cover, and the contract of owners, permissions, harness tests, and release gates.
May 1, 2026·Rogier Muller
AI-Assisted Coding·6 min read
How to clean up agent-written code
A working memo on how to clean up agent-written code: restore visible scope, ownership, and verification receipts to agent diffs before review.
April 26, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Coding plans that lower agent cost
A field guide to coding plans that lower agent cost: scope ledgers, decision stubs, and replay receipts that cut rework, not corners.
April 20, 2026·Rogier Muller
AI-Assisted Coding·6 min read
An agent-friendly codebase beats a clever prompt
An agent-friendly codebase keeps scopes, receipts, and verification commands in files, so agent diffs stay reviewable and delegation stays safe.
April 16, 2026·Rogier Muller
Methodology·6 min read
Stop using CSS selectors in E2E tests
CSS selectors in E2E tests churn every time an agent regenerates markup. Durable selectors, decision stubs, and scope ledgers keep the suite reviewable.
April 6, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Cursor Composer layers in agentic coding
A field guide to Cursor Composer layers in agentic coding: decision stubs, scope ledgers, and precedence files that keep work reviewable.
April 2, 2026·Rogier Muller
AI-Assisted Coding·7 min read
AI coding tools that last past the demo
AI coding tools last when their output survives review: CLAUDE.md precedence, replay sandwiches, connector cards, and child receipts, applied in practice.
March 29, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Browser automation for coding agents needs an owner
Browser automation for coding agents buys faster loops with a wider blast radius: give every connector a card, a named owner, and a rollback path.
March 23, 2026·Rogier Muller
AI-Assisted Coding·6 min read
AI coding wrappers that hold up under review
A governance guide to AI coding wrappers: the repo contracts Cursor, Claude Code, and Codex need so agent work stays reviewable.
March 22, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Subagent prompts: why every fork needs its own brief
Why subagent prompts need their own scope, paths, and verification: four named fixes that keep forked agent work explainable in review.
March 20, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Async subagents that speed up AI coding workflows
Async subagents speed up AI coding workflows when every fork returns receipts: paths touched, commands run, and tests that prove regression guards.
March 14, 2026·Rogier Muller
AI-Assisted Coding·6 min read
How returning Markdown from docs shapes agentic coding
Returning markdown from docs gives Cursor, Claude Code, and Codex one reviewable contract: scope, constraints, verification, and owner on every run.
March 13, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Agent-readable media assets: AGENTS.md, CLAUDE.md, .mdc rules
Markdown files are the agent-readable media assets that govern coding agents: AGENTS.md for Codex, CLAUDE.md for Claude Code, and .mdc rules for Cursor.
March 11, 2026·Rogier Muller
AI-Assisted Coding·6 min read
What to do when AI coding tools regress
When AI coding tools regress, the teams that recover fastest are the ones whose receipts survive the update: connector cards, child receipts, decision stubs.
March 7, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Running multi-agent teams without losing the review trail
Running multi-agent teams across Cursor, Claude Code, and Codex: scope ledgers, precedence files, and replay records that keep every diff reviewable.
March 1, 2026·Rogier Muller
Cursor Features·5 min read
Cursor subagents and skills for engineering teams
An operating model for Cursor subagents and skills: scope ledgers, rule precedence, artifact-first review, and a one-branch training drill.
January 28, 2026·Rogier Muller