Research
Practical research on AI coding, agent workflows, and software delivery. Methods, evidence, and lessons for teams working in existing codebases.
Articles
661 articlesNo articles match your search.
AI Code Review Receipts for Teams
Claude Code Subagents for Team Workflows
Codex CLI Tool for Team Workflows
Cursor Code Review Workflows for Teams
AI coding maturity: five levels and where your team stands
Evaluate AI Coding Agents as a Team
Claude Code Skills for Team Workflows
OpenAI Codex CLI Team Workflow
Using Cursor MCP Servers Safely- AI Code Review With Receipts
Claude Code Review Workflow
Codex CLI with GitHub Repos- Cursor MCP Support for Team Workflows
- AI Software Development Teams Can Trust
Add MCP to Codex CLI Workflows- Codex CLI Workflows from GitHub
Cursor Agent Conventions for Teams- Set Up Claude Code MCP Safely
Cursor AI for Team Workflows
jev-mcp Packages Agent Judgments as Tools- typesafe-mcp Adds Typed Agent Judgments
Living docs in ChatGPT Pages: accuracy rules for agent edits- OpenAI Agents API computer use: risk controls for UI agents
- Budgeting ChatGPT Pro 500 seats for a developer team
Getting ready for ChatGPT collaborative slides: a team plan- Governing ChatGPT dots agents: permissions and a first pilot
ChatGPT meeting notes: a consent and data policy for teams- ChatGPT profile visibility: what workspace admins should decide
- ChatGPT Sites for internal apps: access, data and ownership
- Adopting ChatGPT Space: ownership and hygiene for team knowledge
- Codex automatic code review in your team review policy
- Codex CLI /agents and worktrees: a review load your team can hold
Shared Codex Cloud environments as a team governance control- Codex Security Cloud findings: who owns the fix?
- OpenAI Decisions API as a control point for agent workflows
A GPT-6.1 Sol model policy: default, escalate, measure
Internal tools as ChatGPT plugin extensions: who approves what
MCP Events and unattended agents: guardrails before rollout
OpenAI agents on AWS: governing Bedrock Managed Agents- Consolidating AI tool spend with the OpenAI Marketplace
OpenAI Private Intelligence: a data decision for regulated teams- Rolling out ChatGPT in Slack and Microsoft Teams with approvals
Sign in with ChatGPT at work: identity and AI spend policy- Vetting ChatGPT plugins before your team installs them
When Codex Ultrafast is worth paying for in a team
Who owns a ChatGPT team task? A rollout guide
Agents API computer use: build a browser agent step by step
Bedrock Managed Agents OpenAI vs the Agents API
Build a ChatGPT plugin extension: sidebar, panels and file viewers
ChatGPT collaborative slides for sprint and incident reviews- ChatGPT in Slack: turn a bug thread into a pull request
ChatGPT Meetings plugin: from design review to Codex tasks
ChatGPT Pages: build a self-updating engineering status page
ChatGPT Plugin Creator: from idea to a submitted plugin
ChatGPT Pro 500 for Codex: Pro 100, 200 and 500 compared
ChatGPT shareable profiles: Codex usage, Sites and skills
ChatGPT Sites plugins: deploy a Codex project with live data
ChatGPT Space for Codex users: setup, sharing and context
ChatGPT team tasks for a weekly engineering update
Codex CLI Update: Voice, the /agents View, Resume and Worktrees
Codex Cloud Setup: Reusable Environments and Cloud Tasks
Codex Code Review in the ChatGPT Desktop App: Setup and Use
Codex Security Cloud setup: connect GitHub and run a first scan
GPT-6.1 Sol pricing, model id, and Sol vs Astra in Codex
MCP Events: build an event-emitting MCP server for ChatGPT
OpenAI Decisions API: where Luna fits in an agent pipeline
OpenAI dots for developers: bug reports to tested PRs
OpenAI Marketplace partners for engineering teams
OpenAI Private Intelligence: set up Private Safety Processing
OpenAI Ultrafast in Codex and the API: plans, setup, cost
Sign in with ChatGPT: use your plan in Devin, Warp and T3- json-render Adds AI Component Selection
- fast-jev-compaction Replaces Summaries With Verbatim Context
- jev-ultrafast Narrows Browser Agent Actions
- Harness Design for Coding Agents, Measured
Jev: probabilistic decisions for agent harnesses
claude-code v2.1.268 Fixes Gateway Edges
gpty Puts Agent Terminals in Godot
graphify-csharp Gives Agents C# Find Usages
holaOS vs Claude Code and Codex
KyttoMCP Manages MCP Server Configs
Usero MCP Gives Agents User Feedback
homestead-memory Logs Claude Tool Calls
JavaScript Grids Built for Coding Agents
MaruCheck Checks AI-Generated Code
nightshift Orchestrates GitHub Issues With DAGs
Security Cards Reduce Insecure AI Code
Symphony Maps AI Coding Agents
From AI-generated code to a reviewable change
How to measure an AI workflow before scaling it
Google DeepMind Ships WeatherNext 3
oto-dock Runs Codex Agents on Your Server
Remoot Runs Cursor Agent From Your Phone
Simon Willison’s Browser .blend Viewer
Why Human Syntax Breaks LLMs- Felan Makes Coding Agents Spend Less
- i-have-adhd Makes Agents Answer First
Remarc Gives Coding Agents Contextual Feedback
crew Lets Claude, Codex, and opencode Talk- DashClaw Adds Remote Approvals to Agents
Ditch Tracks Multiple Codex Agents- How Coding Agents Choose Tools
Keyclasp Keeps Tokens Out of Prompts- A Cursor Workshop on Agent PRs
coop Runs Codex and Claude Code in VMs- MaskShift: Zero-Dependency Coding Agent Harness
- OpenAI Monitors Coding Agents for Misalignment
- Simon Willison on OpenAI’s Agentic Research Acceleration
Cursor Self-Hosted Machines Run Agents Locally- fast-cutvid Cuts Video for Agents
- okf-agent-memory Adds Git-Native Agent Memory
Spotify Portal Cut Claude Tokens 90%
Why Coding Agents Fake Completion
Ardent Ships a Code-First Office Agent- Engram Shares AI Agent Runbooks via MCP
- Profound Academy’s Hands-On Course Agent
- Rubato_Device Turns AI Waits Into Breaks
Show HN: APIMatic’s Context Registry for Coding Agents
17K Runs of Claude, Codex, and Cursor
Adchestra’s Google Ads MCP Writes Campaigns- Claude Ported a 1993 Amiga Game
GPT-6 Astra and Coding Agents
Grep Beats LSP for Coding Agents?- Kit: Claude Code but Concise
Git Hijack Lets Repos Run Code in Agents
price Tracks LLM Inference Costs- Sensez Catches Agent Code Smells
spire-agent Plays Slay the Spire
Supercov Brings MC/DC Coverage to Coding Agents- Manzanas Leases iOS Simulators to Agents
- Shed Manages Git for Terminal Agents
Simon Willison on Paint.NET’s AI Direct2D Rewrite
Supafork Shares Agent Sessions
Why ChatGPT/Codex Bundles LibreOffice
Blume Turns Agent Corrections Into Rules
Breaking Claude Code Opus 5 Auto Mode
Codex Skin Themes the Codex CLI
Cursor Starts Cloud Agents Without Repos
Decispher Gives Coding Agents Memory- rta-smriti-brain Keeps Agent Memory Local
Leadcode Isolates Client Coding Accounts
MaCcyP Adds a Clipboard Agents View
ShevtoneAudio Orchestrator Turns MIDI Into Orchestration
Skills MCP Searches Thousands of Agent Skills- DeepSeekGUI Brings Harness to Windows
- rysh-cli-code Connects Codex Agents
stop-that-shit Stops Agent Hashes
VibeGuard Security Linting for AI Code
AgentCloud Gives Cloud Agents iOS Simulators
Coordination Layer for Coding Agents
dmx MCP Server Adds Gated Agent Loops- grith Supervises Coding Agents on Linux
Rundown Summarizes Hacker News with Codex
concord-mcp Lets Coding Agents Talk
Experiential’s Open Model Gateway for Agents
Harden.run Beats GPT5.5-xhigh on Agent Guards
Open Session’s Open-Source Cloud Agent Orchestrator
Simon Willison on Breaking Claude Code Auto Mode
Z Brings Minimal Agentic Coding to Terminals
Code Review Habits for AI Code
TaskShell Bridges AI Coding Agents
Termux-Dev Brings Agents to Android
The $40 Open-Source Codex Micro
CoolPlugz Turns Jira Tickets Into PRs
Cursor Now Runs on iPad- Google AI Adds Search Study Tools
- Google DeepMind Explains Full-Stack AI
OpenAI Restores Codex’s 5-Hour Limit
Codex Opens Its Agent Harness- Create a Cursor Plugin You Can Install
Prism Reviewer Action Splits Code Review
Sloppie Is a Linux Agentic Coding Environment
Will AI Reliance Collapse Coding Expertise?
Continue Is Archived: What Replaces It
Hands Lets MCP Click Real Chrome
Meetless Agent Tracks Coding Agents- Simon Willison on Coding Agent Review
Zuse Runs 20 Linear Issues in Worktrees
A Week Choosing Codex Over Claude
Cursor Origin Hosts Code Repos
fx Is a Tiny Native Coding Agent
New MCP Roadmap for Agent Integrations
TechSkills Gives Coding Agents Skill Files
claude-code 2.1.238 Adds Header Helpers
Codex CLI 0.149.0 Adds Agent Dashboard
desktop-vibe-fly Sniffs Out Vibe Code
Heimdall Adds Trust Verdicts to Agent Memory
Proliferate Is a Self-Hostable AI IDE
Show HN: Frugal Tokens Shows Agent Costs
Codex on AWS Bedrock 10x Charges
Cursor Cloud Agents Get Longer Leashes
Huzzah Makes AI Coding Less Chatty
machine0 Gives Coding Agents Persistent Cloud VMs
Speko Launches Voice AI Router
claude-code 2.1.229 Repairs Remote Sessions- Cursor Cloud Agents Start Faster With Builds
Does AI Coding Feel Like Leadership?
neal Runs Claude and Codex Together
Remarc: contextual feedback for coding agents
Waku Is a Native Coding-Agent App
Agentic AI workshop cost and curriculum, explained plainly
Agentic AI workshop for beginners with no coding experience
Agentic AI workshop for developers using LangChain
Agentic AI workshop for enterprise architects
Agentic AI workshop for marketing teams in Austin
Agentic coding is a review problem
Agentic coding workshop for senior developers- AI code review that engineers stop ignoring
AI coding workshops for non-technical managers
Best AI coding training for career growth- Best AI coding training for remote teams under $3000
Best practices for running OpenAI Codex with a team
Claude Code workshop vs GitHub Copilot training
Compare AI coding workshops from OpenAI, Google, and Microsoft
Finding an agentic AI workshop near me for startups
How to become an AI coding expert in six months
How to learn AI coding with Claude for free
How to run a hHands-on agentic AI workshop with real projects
The best AI coding training for Python developers
What changes in AI software development, and what does not
Which AI coding workshop is best for a budget of $2000
A Claude CLI workflow for tasks longer than an hour
A CLI workflow that survives a real working day
A Codex CLI workflow that holds up on a Tuesday
A Codex workflow that survives contact with a real repo- Agent teams in Codex and when the extra agents pay off
agentic-ship Runs Lovable-Style Builds on Your Agent
AI code governance without a policy nobody reads
AI coding assistant governance without a 40-page policy
Artifex Gives Agents a Media Graph
Brainless GitHub panels and the trust they borrow
Brainless UI, and why agents work better against it
Choosing between Codex models on real work
Claude Code hooks that earn their place in a repo
Claude Code skills, and when they beat a prompt
Claude Code subagents are a context tool
Claude Code vs GitHub Copilot for engineering teams
cliclaw Runs Coding CLIs From Telegram
code review tools with team governance and policies- Codex agent teams and the review bottleneck
Codex agents, and when they stop helping
Codex AI training that changes what a team merges
Codex cls, and why clearing context is a real skill
Codex delegate patterns that survive a real codebase
Codex GitHub reviews without the noise
Codex MCP servers, and when they are worth the tokens
Codex opt out of training, and what to verify
Codex subagents and skills, honestly compared- Codex subagents: what they buy you
Codex training that survives contact with your repo
Codex vs Claude Code, What Teams Running Both Actually Say
Cursor agents and the work they are actually good at
Cursor AI, what it is good at and where it breaks
Cursor MCP servers that are worth the context
Cursor MCP support and the Model Context Protocol in practice
Cursor skills your team should build first
Designing a Codex agent team for one feature- Four Codex workflows that hold up under load
- Getting a Claude Code review worth reading
Governance for AI-generated code that engineers accept
How .cursor/rules works, past the Cursor rules documentation
How agents in Codex actually decide what to do
How Codex works, and where it stops working
How MCP servers actually behave in a real repo
How to brief a Cursor agent properly
How to merge AI code safely on a busy team
How to pick between Codex courses for a working team
Looking for Codex CLI? Start with a bounded task
Making agent-readable media assets in a real codebase- Maximizing Claude Code Sessions
Mole Puts a Budget on Terminal Research
Offsite training for engineering teams, done properly
Onsite programming sessions that survive contact with agents
OpenKnowledge vs Obsidian for a team Claude can read
Reading the Anthropic Claude Code hooks documentation properly
Rogier Muller, AI coding agent trainer in Amsterdam
Rolling out Codex to teams without losing the review gate
Running a Claude Code security review that finds real bugs
Running a Codex team of agents without a mess
Running an agent team in Codex without chaos
Running Codex across a team without chaos
Running Codex team agents without stepping on each other
Searched curs or and meant Cursor? Start here
self-bench Turns Private PRs Into Evals
Setting a codex SLI your team will actually watch
Setting up Codex CLI MCP without regret
Setting up one Codex team agent everyone shares
Standardising Codex agents across an engineering team
The best MCP servers for Claude Code are the few you keep- The Claude Code CLI workflow after the novelty wears off
The Cursor rules that are worth writing
What a Codex bootcamp should cover, and what to skip
What a Codex course should teach your engineers
What codex team mode actually means for a shared repo
What good MCP technical training actually covers- What the claude mcp command actually configures
When Claude Code MCP servers help, and when they hurt
When Codex sub agents help and when they hurt
Working with Opus 5 in Claude Code without burning budget
Your CLAUDE.md is probably too long
/show-me Makes Coding Agents Draw
claude-code 2.1.232 Enables Agent Forks
Codex in ChatGPT Linux Preview
Hearth Turns Family Notes Into Apps
Kery Shows PR Features Working
Read it easy Is a Read-Only Code Editor
brave-devtools-mcp Connects Brave to Agents- Claude Code 2.1.229 Stabilizes Remote Control
Discovered Materials Uses Agents for Chip Heat
FEDERaiDE Routes Agents in Your Terminal
Simon Willison Ships alchemy-utils Alpha
tmux-agent-switcher Watches Coding Agents
Best Programming Language for Coding Agents?
Claude Code User-Agent Email Leak Report
Hoplite YC S26 Brings Coding Agents to the Cloud
keen-code: A Go Coding Agent
Parley Lets Coding Agents Talk
Airship Visually Edits Your Running App
Ante Ships Offline Coding in One Binary
Claude Code Makes Auto Mode Default- Oqoqo Measures Agents on Real Tasks
Try Benzi Tests Code Maps Against Claude Code
Vibsync Shares Memory Across Cursor, Claude, Codex
Managing AI Coding Costs at Scale, Is It Worth It?
Mirafold Gives Terminal Agents a Browser UI- aident-skill Connects Codex and Claude Code to Apps
mcp-use v2 Gets a Stateless Rebuild
mcp-use v2 Goes Stateless
mcp-use v2 Rebuilds for Stateless MCP
adlc-team-skills Teaches Agents Team Rules
claude-code 2.1.223 Tightens Marketplace Permissions
Frontrun Tests Python Races
Armature Shows MCP Session Analytics
book-skills Turns Work Books Into Claude Skills
Cursor Adds Google Workspace Plugins
Rudder Measures Your Input on AI Code
claude-code-meter Tracks Claude Code Usage Pace
MicroCodex: Reviewing a Small Coding Agent
Sprocket Lets an Agent Buy Parts
Claude MIDI Twister Shows Agent State- Ski Runs Voice Coding Locally
- skill-language-server Refactors Agent Skills
Yamlet Makes Agent Specs Smaller
agent-manager Puts AI Agents in tmux
codex-security Tests the Repo Boundary
Dn Turns Issues Into Agent Plans
Telnyx Kimi K3, Is It Fast Enough to Use?
verified-3d-mesh-intersection Verifies 3D CSG
verified-3d-mesh-intersection Verifies 3D Mesh CSG
claude-code 2.1.218 Backgrounds /code-review
Decispher Adds Grok CLI Support
FeyNoBg Opens a Background Removal Library
FeyNoBg Removes Backgrounds in Public
FeyNoBg Ships Background Removal Library
Boffin Adds Per-Edit Agent Guardrails
Claude Code 2.1.218 Backgrounds Reviews
coding-agent-skill-library Serves Skills via MCP
Termic Runs CLI Coding Agents
Argus Manages VS Code Worktree Agents
claude-code 2.1.219 Surfaces MCP Failures
Cursor Router Powers Auto Mode
AgentCost Tracks Local Agent Spend
Claude Code 2.1.219 Adds Opus 5- Show HN: WhipDesk Controls Dev Machines From Phones
Echo Claims Fable-Level Results for Less
Echo Tests Cheaper Open-Weight Routing
OneCLI Keeps Secrets Out of Agents
Bento Puts Slides in One HTML File
Review Habits for AI-Generated Code
serve-avd Streams Android Emulators to Browsers
Yorishiro Gives Coding Agents a Body
claude-code 2.1.216 Loosens Sandboxes
Claudexor Routes Coding-Agent Quotas
CodeAlmanac Writes Wikis From Agent Chats- joydex Turns a Flight Throttle Into Codex Controls
Ask HN: Shipping Apps Without Seeing Code
Claude Code 2.1.215 Makes Reviews Explicit
claw-coder Runs an Autonomous Local Agent
claw-coder Runs Coding Agents Locally
claw-coder Takes Autonomous Coding Local
Cursor and Codex Hit by Sandbox Escapes
OpenAI Cuts Codex Context Window
PocketVeto Is a Bluetooth Agent Remote
Agent-talk Gives Coding Agents a Backchannel
claude-code 2.1.212 Splits Forks and Subtasks
Hermes Agent Runs Kimi K3 in a Sandbox
Claude Code 2.1.212 Tames Background Sessions
Codex Micro Makes Agent Control Physical
Brainless: Claude Code-Style Shadcn Components
deja-vu Shares Agent Memory Over SSH
Codex Encrypts Sub-Agent Prompts
Juggler Turns Coding Agents Into a Workbench
Microsoft’s Claude Code and Copilot CLI Study
claude-meseeks Adds Meeseeks Waiting Alerts
clawk Puts Coding Agents in VMs
Evaluate Prompt Quality in Claude Code and Codex
Sanbox Gives AI Agents MicroVM Sandboxes
Terence Tao Builds Apps With Coding Agents
Why Claude Code Sends 33k Tokens First
claude-code 2.1.205 Fixes Workflow Edges
searxng-ai-kit Turns SearXNG into an MCP Server
9lives Heals Playwright Tests Safely
Abralo Puts Claude Agents in One Window
local-motion Runs Cursor Agents Locally
claude-code 2.1.206 Smooths Repo Friction
Databricks Tests Agents on Millions of Lines- Kastra Enforces Policies for Cursor Agents
Ask HN: What Agent Sandboxes Are Missing
Claude Code 2.1.205 Hardens Agent State
Moo Versions Machines for Agent Branches
Moo Versions the Whole Machine
ultralytics-mcp Connects YOLO to Cursor- claude-code 2.1.202 Tunes Dynamic Workflows
Local MCP Connects Mac Apps to Agents
Rowboat vs Claude Desktop for AI Work
Rowboat vs Claude Desktop: Local Work Surfaces
Claude Code 2.1.202 Adds Workflow Controls
Code Cleanliness Changes Coding Agent Footprints
Whyline: Company Memory for Cursor
Ask HN: Banned From Claude Code
TikZ Editor Makes LaTeX Figures Less Painful
Ask HN’s LLM Coding Flow Debate
Dan Luu on Agentic Coding: Keep the Loop Bounded
open-knowledge vs Obsidian and Notion
Scopewalker MCP Measures Code Complexity
Manufact YC S25 Turns MCP Servers into Hosted Apps
OpenAI Codex Sensitive Files Issue
Router Picks Models Inside Cursor
Claude Code Rollout Drill
Claude Workflow Training for Teams
Codex Agent Rules for Real Repos
Codex Team Rollouts for Real Repos
Cursor Guardrails for Real Teams
Cursor Shared Workflows for Teams
Bound Claude Code Agent Teams
Codex CLI MCP Setup
Cursor Rules vs AGENTS.md, a Team Playbook that Scales
Safer Codex Rollouts for Teams
Train Safer AI Coding Habits
Adopt Claude Code as a Team
Codex Remote in Real Repos
Safe AI Coding Team Rollouts
Teach AI Coding With Guardrails
Train Teams on Coding Agents Safely
Use Cursor Agents With Guardrails
A Practical AI Review Workflow
A Team Rubric for Cursor Skills
Codex Remote for GitHub Workflows
Review Rules for AI Coding Agents
Run a Claude Code Team Workshop
A Safer Agent Review Convention- Codex Review Guardrails That Stick
Learn Claude Code as a Team
Roll Out Cursor Team Training- Run Codex as an Engineering Team
Give Coding Agents Team Rules
Govern Coding Agents as a Team in Cursor
Orchestrate Coding Agents Safely
Train Cursor Agents as a Team
Wire Codex to MCP Safely
Choose Code Review Agents by Receipts
Claude Code Hook Conventions
Cursor Agents Need Team Conventions
Pick Code Review Agents Safely
Run Review Agents With Receipts- Train Your Team on Codex Remote
AGENTS.md for Codex Teams
Compare AI Coding Agents Safely
Compare Coding Agents for Teams
Compare Coding Agents With Guardrails
MCP Setup for Claude Teams- Use Cursor Rules as Team Rails
Accept Claude Skills Like Code
Bounded Benchmarks for Coding Agents
Review Code With Codex CLI
Team Boundaries for Coding Agents
Train Your Team on Cursor 3.9
Verify Coding Agents in Isolation
A Cursor MCP integration checklist
Check Codex MCP access before a task
Govern Autonomous Codex Workflows
Govern Autonomous Coding Agents
Govern Codex Agents With Workflows
Guardrails for Autonomous Coding Agents
How Autonomous Coding Agents Ship Safely
How Coding Agents Stay Inside Bounds
Let Coding Agents Work Safely
Make Coding Agents Follow a Workflow
Rules for Autonomous Coding Agents
Subagent conventions for Claude Code teams
A Team Operating Model for Claude Code
Agentic Coding for Mixed-Skill Teams
Codex 26.616 Workflow Check
Codex Conventions for Mixed-Skill Teams
Codex Workflow After App 26.616
Cursor 3.8 Code Review with Subagents and Skills
Govern Coding Agents by Skill
Make Cursor Reviews Leave a Trail
Skill Gates for AI Coding Teams
Skill Rubrics for Coding Agents
Team Conventions for Claude Code
AI Code Review Needs a Receipt
Code Review Agents Need Receipts
Codex AGENTS.md Team Rules
Cursor Automation Team Conventions
Pick the Review Workflow First
Practical Rules for Claude Code Teams
A Safer Codex Review Loop
A Team Claude Code Review Workflow
AI Coding ROI With Guardrails
Cursor Rules for Team Automations
Governed AI Coding at Team Scale
ROI Guardrails for Coding Agents
Add MCP to Codex Safely
Cursor MCP for Team Workflows
Team AI Coding Training Plan
Train Coding Agents Safely
Claude Code or Copilot for Teams
Cursor Review Workflows With Subagents
Install Codex CLI for Teams
A practical context budget for Codex CLI
Claude Code conventions for an engineering team
code review tools Need Receipts
Cursor Agents Team Checklist
AI Code Review Workflow for Teams
Codex Code Review for CLI Teams- Cursor Skills and Team Rules for Large Codebases
How to enable agent teams in Claude Code
Cursor MCP Support and How to Add a Server Safely
Hands-On Claude Code Workshops for UK Development Teams
Cursor Skills for Team Workflows
Shared agent workflows for review risk reduction- Cursor Agent Review Loop
Cursor Rules for Team Workflows
AI code review habits- AI coding training and compliance regulations: a working model
AI coding training requirements for DevOps teams on Codex CLI- What is MCP in Cursor IDE? The answer for Codex CLI teams
Codex Windows review loop
Cursor 3.6 auto-review and rules
Safer Agents for Legacy Code
Codex Windows update: MCP and mobile use
Agent Code Review Without Drift
Codex CLI 0.135.0 workflow
Cursor in Jira: tighter scope, cleaner handoffs
Codex CLI boundaries
Cursor Jira review workflow- Onsite or Virtual AI Coding Training
- Codex CLI review receipts
Cursor in Jira, with clear handoffs- Training agents without chaos
Agentic coding guardrails
Claude Code Hooks, PreToolUse, and MCP Permissions
Codex CLI workflows for reviewable diffs- Cursor Jira workflows without chaos
Claude Code MCP team conventions- Codex CLI Goal Mode, Appshots, and the Real Workflow
Claude Code team skills and conventions
Codex CLI review loops
Cursor Automations in the Agents Window
Claude Code team conventions
Codex CLI, GitHub, and MCP
Cursor Automations Across Multiple Repos, Without Drift
Claude Code hooks for teams
Codex CLI 0.132.0, AGENTS.md and MCP Official Docs
Cursor Jira handoffs without drift
Govern AI Coding Before It Drifts
Claude Code review receipts
Cursor Composer 2.5 team guide
Agentic Coding Breaks At The Handoff
Claude Code 2.1.139 team conventions
Codex governance: four contracts that hold in review
Best practices for agentic coding in real environments
CLAUDE_CODE_STOP_HOOK_BLOCK_CAP in Claude Code 2.1.143
Codex mobile CLI: runs that survive review
Claude Code 2.1.142 team conventions
Codex mobile CLI docs your team can read anywhere
Codex workflows for mobile handoffs
Cursor 3.4 cloud agents
Cursor Bugbot effort levels as review policy
How to Set Up Agentic Coding Workflows and Guardrails
Codex workflows: governance that lives in the repo
Cursor Cloud Agent Setup and the Environment Contract
Codex auto review: setup, strengths, and limits
Cursor subagents and skills for teams
Fast mode is not the default: when fast models earn it
AI coding agents workflow guardrails for browser control
Claude Code 2.1.136: team convention fixes
Is Codex CLI Giving MCP Too Much Reach?
AI agent guardrails that hold
Claude Code 2.1.138: team conventions check
Codex workflows for Chrome and the CLI
Agentic workflows from PR to merge
Claude Code 2.1.137 fixes Windows activation
Cursor subagents and skills for teams
OpenAI Codex CLI AGENTS.md Official Docs, Explained
Composer 2 for Cursor teams
Claude Code 2.1.132 team conventions
Cursor 3.3 context for subagents and skills
Claude Code 2.1.129 team conventions
Codex CLI Workspace Tools for Reviewable MCP Connectors
Cursor 3 subagents and skills
Claude Code 2.1.128 team conventions
Cursor team controls for admins- AI agent guardrails: why every harness needs them
Claude Code conventions for shared repos
Cursor Canvases for team workflows
Claude Code 2.1.121: MCP guardrails
Cursor Security Review beta
Claude Code 2.1.122 team conventions- Codex 5.5: pin the model before you swap it
Cursor team marketplace: rules with named owners
Claude Code 2.1.126: MCP, hooks, skills
Codex CLI /goal Command and AGENTS.md Workflow- Cursor Subagents, the Official Docs and the Missing Contract
Cursor 3.2: subagents, worktrees, multi-root
Agent boundaries for teams running coding agents- How to clean up agent-written code
Morning signal review: an AI code review checklist
Headless SaaS for agents: APIs before dashboards
Agent drift: how to read coding agent output
Local first: why local checks before CI win for agents
MCP for team workflows: scopes, owners, receipts
Specs for coding agents that hold up in review
Stop adding a regression test for every bug
An agent-friendly codebase beats a clever prompt
An AI coding workflow that holds up under audit
Lead sourcing with agents that survives review
Narrow skills for coding agents beat broad ones
Evaluating AI coding tools that hold up- MCP for UI components: boundaries before the demo
Fast evals for better coding agent decisions- Keep parallel coding agents from colliding
Specs and tests: the stable stack for AI coding
Stop using CSS selectors in E2E tests
A better bug-finding prompt for coding agents
Agentic team workflows that survive review
AI coding tools that keep working after rollout
Cursor Composer layers in agentic coding- Headless agent runs in CI need receipts
Long-running agent loops you can still review
Coding agent loops for messy code
AI coding tools that last past the demo- AI coding team workflow beats prompt tuning
Markdown files for coding agents: the real interface
Browser checks for coding agents that reviewers can replay
Keep the AI coding stack current and agents bounded
Reviewing AI generated code defensively
Coding Agent Browser Automation Needs an Owner
AI coding wrappers that hold up under review
Subagent prompts: why every fork needs its own brief
AI coding tool rollout without surprise rework
Reliable AI coding workflows under pressure- AI coding workflow patterns that survive review
Async subagents that speed up AI coding workflows
How returning Markdown from docs shapes agentic coding
Cursor .mdc vs CLAUDE.md vs AGENTS.md- Playwright MCP: faster agent loops with receipts
What to do when AI coding tools regress
Running multi-agent teams without losing the review trail
Cursor 2.4 subagents and skills for engineering teams
Put research into practice
Work with Rogier and Vasilis on the tools and codebase your team uses. Onsite, offsite, or remote.