Open Source·10 min read
deja-vu Syncs Coding Agent Memory
deja-vu turns local coding-agent session logs into searchable memory, MCP recall, redaction, and SSH-friendly sync.
July 16, 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.
Open Source·10 min read
Juggler Makes Coding Agents Visible
Juggler is an open-source GUI coding agent that turns agent sessions into inspectable trees instead of chat scrollback.
July 15, 2026·Rogier Muller
Open Source·9 min read
Clawk Gives Coding Agents a Throwaway VM
Clawk gives coding agents a disposable Linux VM so they can work without reaching your laptop.
July 14, 2026·Rogier Muller
Open Source·9 min read
searxng-ai-kit Runs SearXNG Without Servers
searxng-ai-kit packages SearXNG as a CLI and MCP server, and shows how to connect search safely in Cursor.
July 12, 2026·Rogier Muller
Open Source·8 min read
local-motion Runs Cursor Agents Locally
local-motion helps Cursor users run a local coding model on macOS and avoid the usual memory and setup traps.
July 11, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Databricks Benchmarked Coding Agents at Scale
Databricks benchmarked coding agents on a huge repo; the lesson is to measure task cost, not token price.
July 10, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Kastra Enforces Policies for Cursor Agents
Kastra intercepts coding-agent tool calls before they run. Learn where runtime policy helps Cursor users and where it is too much.
July 10, 2026·Rogier Muller
Open Source·10 min read
ultralytics-mcp Connects YOLO to Cursor
ultralytics-mcp lets agents control YOLO datasets and training through MCP, with a safe Cursor setup boundary.
July 9, 2026·Rogier Muller
Cursor Features·10 min read
Local MCP Connects Mac Apps to Agents
Local MCP connects AI assistants to Mac-only context, and the safe first test is a narrow, read-only MCP boundary.
July 8, 2026·Rogier Muller
Open Source·10 min read
Rowboat vs Claude Desktop for AI Work
Rowboat turns the desktop AI assistant into local work surfaces. Here is where it beats Claude Desktop, and where it does not.
July 8, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Code Cleanliness Changes Coding Agent Footprints
A 2026 arXiv study found clean code changed coding-agent cost and navigation more than pass rate.
July 7, 2026·Rogier Muller
Open Source·9 min read
Whyline: Company Memory for Cursor
Whyline connects company decisions to Cursor through MCP so agents can answer “why” with receipts, not guesses.
July 7, 2026·Rogier Muller
Open Source·8 min read
TikZ Editor Makes LaTeX Figures Draggable
TikZ Editor makes LaTeX figures visual without hiding the source, with a practical fit table for Cursor users.
July 6, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Dan Luu on Agentic Coding: Keep the Loop Bounded
Dan Luu wrote field notes on coding with AI agents. This piece pulls out his bounded-loop lesson and turns it into a reviewable Cursor workflow.
July 5, 2026·Rogier Muller
Open Source·8 min read
Scopewalker MCP Measures Code Complexity
scopewalker-mcp gives Cursor agents local, read-only complexity metrics before they edit your repo.
July 5, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Manufact (YC S25) MCP Cloud
Manufact (YC S25) turns MCP servers into hosted apps, with a practical boundary for Cursor users connecting agents to real systems.
July 3, 2026·Rogier Muller
Open Source·11 min read
Router Picks Models Inside Cursor
A story-first look at workweave/router, smart model routing, and the Cursor skill rubric worth keeping.
July 3, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Cursor Shared Workflows for Teams
A practical Cursor-first rollout plan for agentic coding training, MCP boundaries, repo rules, and safer reviews.
July 2, 2026·Rogier Muller
Cursor Features·8 min read
Cursor Guardrails for Real Teams
A practical guide to Cursor team workflows with rules, skills, MCP, subagents, and a rollout checklist.
July 2, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Safer Coding Agents for Teams
A practical rollout plan for Cursor teams adding rules, MCP boundaries, and review guardrails to coding agents.
July 1, 2026·Rogier Muller
Cursor Features·8 min read
Team Cursor Rules That Scale
A practical convention for Cursor rules, skills, and agent handoffs that engineering teams can adopt this week.
July 1, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Teach AI Coding With Guardrails
A practical team rollout plan for Cursor users: rules, MCP boundaries, workshops, and review guardrails for agentic coding.
June 30, 2026·Rogier Muller
Cursor Features·8 min read
Use Cursor Agents With Guardrails
A practical Cursor team workflow for agents, rules, skills, AGENTS.md, MCP, and reviewable background-agent work.
June 30, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Align AI Code Review
A team convention for safer AI-assisted review with Cursor rules, AGENTS.md boundaries, MCP checks, and one checklist.
June 29, 2026·Rogier Muller
Cursor Features·8 min read
A Team Rubric for Cursor Skills
A practical Cursor convention for accepting skills, subagents, and rules before they become team defaults.
June 29, 2026·Rogier Muller
AI-Assisted Coding·7 min read
Shared Workflows for Safer Review
A practical Cursor team convention for safer agent reviews, MCP boundaries, and repeatable AI coding adoption.
June 28, 2026·Rogier Muller
Cursor Features·10 min read
Roll Out Cursor Team Training
A practical team rollout for Cursor rules, AGENTS.md, subagents, skills, MCP, and review habits.
June 28, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Govern Coding Agents as a Team
A team convention for running coding agents with scoped rules, MCP boundaries, and reviewable Cursor workflows.
June 27, 2026·Rogier Muller
Cursor Features·9 min read
Train Cursor Agents as a Team
A practical Cursor team rollout plan for rules, skills, subagents, and reviewable AI coding workflows.
June 27, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Choose Code Review Agents by Receipts
Use Cursor rules, AGENTS.md, and review receipts to make AI code review safer across coding agents.
June 26, 2026·Rogier Muller
Cursor Features·8 min read
Cursor Agents Need Team Conventions
A practical Cursor team convention for agents, rules, skills, AGENTS.md, and safer reviewable workflows.
June 26, 2026·Rogier Muller
AI-Assisted Coding·11 min read
Compare AI Coding Agents Safely
A practical governance matrix for comparing Cursor, Claude Code, and Codex in enterprise ai code generation workflows.
June 25, 2026·Rogier Muller
Cursor Features·8 min read
Use Cursor Rules as Team Rails
A practical Cursor rules workflow for teams using subagents, skills, AGENTS.md, and reviewable coding habits.
June 25, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Team Boundaries for Coding Agents
A practical workflow for setting AI coding boundaries, signed benchmark checks, and review guardrails in Cursor.
June 24, 2026·Rogier Muller
Cursor Features·10 min read
Train Your Team on Cursor 3.9
Use Cursor 3.9’s Customize page to roll out rules, skills, subagents, MCPs, and team habits.
June 24, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Rules for Autonomous Coding Agents
A practical Cursor-first convention for agentic coding governance, MCP boundaries, and reviewable autonomous changes.
June 23, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Govern Autonomous Coding Agents
A team convention for agentic coding governance: boundaries, MCP permissions, and review checks Cursor users can adopt.
June 23, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Guardrails for Autonomous Coding Agents
A practical Cursor team convention for autonomous coding agents, with rules, MCP limits, and review guardrails.
June 23, 2026·Rogier Muller
Cursor Features·8 min read
Cursor MCP Integration Checklist
A practical Cursor Workshop guide for adding MCP safely with rules, skills, custom agents, and review habits.
June 23, 2026·Rogier Muller
Cursor Features·9 min read
Cursor MCP Team Setup
A practical Cursor MCP guide for team rules, skills, custom agents, and reviewable integrations.
June 23, 2026·Rogier Muller
Cursor Features·8 min read
Harden Cursor MCP Workflows
A Cursor MCP setup guide for teams using rules, skills, subagents, and a copyable checklist to keep integrations reviewable.
June 23, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Govern Coding Agents by Skill
A Cursor-first convention for training mixed-skill teams to use coding agents with safer reviews.
June 22, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Agentic Coding for Mixed-Skill Teams
A practical team convention for matching coding agents to skill levels, Cursor rules, MCP access, and review guardrails.
June 22, 2026·Rogier Muller
Cursor Features·8 min read
Make Cursor Reviews Leave a Trail
A practical Cursor review workflow using rules, skills, automations, and a copyable review receipt.
June 22, 2026·Rogier Muller
Cursor Features·7 min read
Review Workflows in Cursor 3.8
A practical Cursor 3.8 guide for team code reviews using Automations, rules, skills, MCP, and review receipts.
June 22, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Code Review Agents Need Receipts
A practical review workflow for Cursor teams using agents, review receipts, MCP boundaries, and shared rules.
June 21, 2026·Rogier Muller
Cursor Features·9 min read
Cursor Automation Team Conventions
A practical Cursor team convention for using /automate, rules, skills, AGENTS.md, and review habits safely.
June 21, 2026·Rogier Muller
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 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
Cursor Features·6 min read
Cursor MCP: Add a Server Safely
Cursor MCP setup for engineering teams: add one server, scope rules, and review agent work without losing control.
June 15, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Shared agent workflows for review risk reduction
A practical read on the workflow, tradeoffs, and next steps. Read the workflow, review rules, and team training patterns for AI coding tooling.
June 14, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Skills for Team Workflows
A team guide for cursor skills, subagents, rules, and one review rubric for Cursor teams.
June 14, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Agent Review Loop
Use cursor agent with rules, subagents, and review checks to ship safer code faster in Cursor teams.
June 13, 2026·Rogier Muller
Cursor Features·5 min read
Cursor Rules for Team Workflows
Cursor rules help teams keep scoped .cursor/rules files, subagents, and reviews aligned in Cursor.
June 12, 2026·Rogier Muller
AI-Assisted Coding·6 min read
AI code review habits
A practical read on the workflow, tradeoffs, and next steps. Read the workflow, review rules, and team training patterns for AI coding tooling.
June 11, 2026·Rogier Muller
·6 min read
AI coding training and compliance regulations: a working model
AI coding training and compliance regulations as one operational system: scope rules, secret boundaries, review evidence, and escalation points that survive audit.
June 3, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Safer Agents for Legacy Code
ai coding training for legacy codebases with review guardrails, MCP boundaries, and phased rollout steps.
May 31, 2026·Rogier Muller
Cursor Features·6 min read
Cursor 3.6 auto-review and rules
Use Cursor 3.6 auto-review with cursor rules, subagents, and a team rule file for safer reviews.
May 31, 2026·Rogier Muller
Cursor Features·6 min read
Cursor in Jira: tighter scope, cleaner handoffs
How Cursor in Jira scopes work, where cursor mcp fits, and the team checklist that keeps agent work reviewable.
May 29, 2026·Rogier Muller
AI-Assisted Coding·7 min read
Onsite or Virtual AI Coding Training
Practical guidance for distributed engineering teams choosing onsite ai coding training for distributed teams or virtual delivery.
May 28, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Jira review workflow
A Cursor code review workflow for Jira handoffs, rules, subagents, and a review receipt teams can use this week.
May 28, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Training agents without chaos
Practical ai coding training cost for engineering teams: guardrails, review checks, and a budget worksheet.
May 27, 2026·Rogier Muller
Cursor Features·7 min read
Cursor in Jira, with clear handoffs
Cursor in Jira tightens handoff, review, and governance for cursor ide agent plugin cline deepseek 2026 workflows.
May 27, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Jira workflows without chaos
A practical Cursor workflow for Jira-linked work, MCP, rules, and reviewable agent handoff.
May 25, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Automations in the Agents Window
Cursor 3.5 moves Automations into the Agents Window, with multi-repo and no-repo workflows for cursor ai teams.
May 22, 2026·Rogier Muller
Cursor Features·7 min read
Cursor Automations, without drift
A practical Cursor guide to cursor mcp, rules, subagents, and a team checklist for reviewable automations.
May 21, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Govern AI Coding Before It Drifts
Practical ai coding governance for engineering teams: review guardrails, MCP boundaries, and shared rules across tools.
May 20, 2026·Rogier Muller
Cursor Features·7 min read
Cursor Jira handoffs without drift
Practical Cursor skills, subagents, and rules for Jira handoffs that stay scoped and reviewable.
May 20, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Composer 2.5 team guide
A practical Cursor team guide for agents, rules, subagents, skills, and one copyable checklist.
May 19, 2026·Rogier Muller
Cursor Features·6 min read
Cursor 3.4 cloud agents
A workflow note on Cursor 3.4 cloud agents: connector stewards, glob diets, prompt expiry tags, and receipts that survive remote runs.
May 15, 2026·Rogier Muller
Cursor Features·5 min read
Cursor Bugbot effort levels as review policy
Cursor Bugbot effort levels mapped to review risk: lanes, an escalation list, and a triage table so deadline pressure stops deciding review depth.
May 15, 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
Cursor Features·5 min read
Cursor subagents and skills for teams
Cursor subagents and skills for team repos: glob diets, prompt expiry tags, skill preambles, and mutex paths that keep parallel work explainable.
May 13, 2026·Rogier Muller
Cursor Features·6 min read
Cursor subagents and skills for teams
An operational memo on Cursor subagents and skills for teams: mutex paths, skill preambles, prompt expiry tags, and review receipts in the repo.
May 9, 2026·Rogier Muller
Cursor Features·6 min read
Composer 2 for Cursor teams
A measurement guide for Composer 2: known-case evals, acceptance gates, and the review notes that separate faster drafts from better ones.
May 8, 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
Cursor Features·5 min read
Cursor 3.3 context for subagents and skills
Cursor 3.3 context for subagents and skills: review receipts, connector stewards, glob diets, and expiry tags that cut merge-queue fatigue.
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
Cursor Features·6 min read
Cursor 3 subagents and skills
An operational memo for Cursor 3 subagents and skills: connector stewards, glob diets, prompt expiry tags, and skill preambles that hold in review.
May 6, 2026·Rogier Muller
Cursor Features·6 min read
Cursor team controls for admins
Cursor team controls for admins as an operating guide: connector stewards, mutex paths, review receipts, and rules that stay trustworthy.
May 5, 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·5 min read
Cursor Canvases for team workflows
A guide for using Cursor Canvases as decision artifacts that bind owners, paths, and rules, instead of diagrams that drift away from review.
May 4, 2026·Rogier Muller
Cursor Features·6 min read
Cursor Security Review beta
A playbook for Cursor Security Review: red-folder routing, finding triage, and the PR evidence a named human owner still signs.
May 3, 2026·Rogier Muller
Cursor Features·6 min read
Cursor team marketplace: rules with named owners
A Cursor team marketplace works when shared rules, skills, and MCP connectors carry named owners: review receipts, stewards, glob diets, expiry tags.
May 2, 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
Cursor Features·6 min read
Cursor 3.2: subagents, worktrees, multi-root
A migration memo for Cursor 3.2 teams deciding how to use subagents, worktrees, and multi-root workspaces without losing review ownership.
April 29, 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
Methodology·6 min read
Morning signal review: an AI code review checklist
Run a morning signal review with an AI code review checklist: precedence files, replay proof, connector owners, and receipts checked before merge.
April 25, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Headless SaaS for agents: APIs before dashboards
An operational memo on headless SaaS for agents: scope ledgers, decision stubs, and replay receipts for vendor APIs without dashboards.
April 24, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Agent drift: how to read coding agent output
How to spot agent drift in coding output: the reading habits, receipts, and scope checks that catch it before the merge.
April 23, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Local first: why local checks before CI win for agents
Local checks before CI, argued for agent work: replay sandwiches, connector cards, and child receipts created where the work happens.
April 22, 2026·Rogier Muller
AI-Assisted Coding·5 min read
MCP for team workflows: scopes, owners, receipts
MCP for team workflows means treating every connector as a production dependency: declared scope, named owner, written rollback, reviewable receipts.
April 21, 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
Specs for coding agents that hold up in review
A field guide to specs for coding agents: five-line scope ledgers, decision stubs, and connector cards that a tired reviewer can check.
April 19, 2026·Rogier Muller
Methodology·6 min read
Stop adding a regression test for every bug
Why a regression test for every bug fails as strategy: guard failure classes, keep replay receipts, and stop growing suites that prove nothing.
April 18, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Why functional programming for coding agents works
A workflow note on functional programming for coding agents: declared inputs, scope ledgers, and receipts that keep Cursor agent diffs reviewable.
April 17, 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
AI-Assisted Coding·6 min read
An AI coding workflow that holds up under audit
An AI coding workflow built on receipts: child receipt blocks, decision stubs, scope ledgers, and precedence files that survive audit.
April 15, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Lead sourcing with agents that survives review
A field guide to lead sourcing with agents: connector cards, replay receipts, and review evidence for outreach pipelines built on Cursor and MCP.
April 14, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Narrow skills for coding agents beat broad ones
Skills for coding agents stay reviewable when each one has a single job, a declared scope, and a pinned verification command. Broad skills hide drift.
April 13, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Plain-English agent updates reviewers can replay
Plain-English agent updates put intent, transcript, and diff summary in the PR, so reviewers follow agent work without replaying chat sessions.
April 12, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Evaluating AI coding tools that hold up
Evaluating AI coding tools by the audit trail they leave: connector cards, child receipts, decision stubs, and scope ledgers a stranger could review.
April 11, 2026·Rogier Muller
AI-Assisted Coding·6 min read
MCP for UI components: boundaries before the demo
MCP for UI components without silent rework: connector cards, CLAUDE.md precedence, replay records, and child receipts for design-system agent work.
April 10, 2026·Rogier Muller
Methodology·6 min read
Fast evals for better coding agent decisions
Fast evals for coding agent workflows: replace review archaeology with receipt checks, decision stubs, and scope ledgers reviewers can run in minutes.
April 9, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Keep parallel coding agents from colliding
Parallel coding agents clog merge trains when scopes overlap. Scope ledgers, CLAUDE.md precedence, and replay receipts keep streams out of each other.
April 8, 2026·Rogier Muller
Methodology·6 min read
Specs and tests: the stable stack for AI coding
Specs and tests as the stable stack for agent work: four named fixes that turn fuzzy scopes into reviewable, parallel-safe delivery.
April 7, 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
A better bug-finding prompt for coding agents
A better bug-finding prompt is one reviewers can replay: receipts, precedence, and connector boundaries for agent-led debugging.
April 5, 2026·Rogier Muller
Methodology·6 min read
Agentic team workflows that survive review
A field guide to agentic team workflows: the scope, ownership, and verification receipts that keep parallel agent output reviewable after the session ends.
April 4, 2026·Rogier Muller
AI-Assisted Coding·6 min read
AI coding tools that keep working after rollout
Why AI coding tools degrade after rollout, and the file-backed contracts, precedence, replay receipts, connector cards, that keep them working.
April 3, 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
Headless agent runs in CI need receipts
Headless agent runs in CI work when AGENTS.md mandates replay receipts, connectors carry owner cards, and child agents report exactly what they touched.
April 1, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Long-running agent loops you can still review
How to keep long-running agent loops reviewable: replay contracts, connector boundaries, and receipts that outlive the session.
March 31, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Coding agent loops for messy code
Coding agent loops survive messy code when scope ledgers, CLAUDE.md precedence, replay receipts, and connector cards keep every iteration reviewable.
March 30, 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
AI coding team workflow beats prompt tuning
An AI coding team workflow built on child receipts, decision stubs, and scope ledgers outperforms prompt tuning, and it survives the people who wrote it.
March 28, 2026·Rogier Muller
Methodology·6 min read
Markdown files for coding agents: the real interface
Markdown files for coding agents, CLAUDE.md, AGENTS.md, rules, and connector cards, are the contract layer that keeps agent work reviewable and owned.
March 27, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Browser checks for coding agents that reviewers can replay
Browser checks for coding agents: turn UI claims into replayable receipts with intent lines, command transcripts, connector cards, and decision stubs.
March 26, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Keep the AI coding stack current and agents bounded
Updating the AI coding stack without losing agent bounds: connector cards, child receipts, decision stubs, and scope ledgers that survive upgrade weeks.
March 25, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Reviewing AI generated code defensively
Reviewing AI generated code defensively: decision stubs, scope ledgers, and replay receipts that let reviewers defend a merge without replaying the chat.
March 24, 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·6 min read
AI coding tool rollout without surprise rework
An AI coding tool rollout survives scale when discipline travels as artifacts: replay sandwiches, connector cards, and decision stubs every team can audit.
March 18, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Reliable AI coding workflows under pressure
Reliable AI coding workflows run on receipts, not autonomy: scope ledgers, replay sandwiches, and connector cards that keep agent streams reviewable.
March 16, 2026·Rogier Muller
AI-Assisted Coding·5 min read
AI coding workflow patterns that survive review
Four AI coding workflow patterns that keep agent work reviewable: CLAUDE.md precedence, replay sandwiches, connector cards, and child receipts.
March 15, 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
MCP integrations that make iteration faster
MCP integrations earn their speed when connector ownership, scoped access, and review logs stay visible. The receipts that keep fast loops traceable.
March 12, 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
Cursor Features·6 min read
Playwright MCP: faster agent loops with receipts
A Playwright MCP workflow note for faster agent loops, focused on connector ownership, scoped access, review logs, and test evidence.
March 9, 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