Research
Practical research on AI coding, agent workflows, and software delivery. Methods, evidence, and lessons for teams working in existing codebases.
Articles
164 articlesNo articles match your search.
Claude Code 2.1.327 Protects MCP Config
Codex CLI 0.170.0 Fixes MCP and Sandbox
Cursor Progress Log Hook Events
Devin Adds Security Findings CSV
GitHub Copilot Fusion Scores 71.2% on Terminal-Bench
Claude Code 2.1.326 Adds Startup Warnings
Multiple Cursor Agents for One Task
Product Managers and Codex Pull Requests
Claude Code 2.1.323 Adds Code Mode
Claude Code 2.1.325 Tightens Permission Prompts
Codex CLI 0.168.0 Improves TUI Workflows
Codex CLI 0.169.0 Adds Workspace Tabs
Cursor Agent Usage Limits for Teams
Set Boundaries for Context7 in Claude Code
Use Cursor Skills in Team Repos
Claude Code Security Review Receipts
Claude Code Workflow for Teams
Codex CLI Code Review Receipts
OpenAI Codex CLI GitHub Workflow
AI Coding Workflow for Teams
Using Cursor Skills Marketplace Safely
Set Up Claude Code Agent Teams
Claude Code Hooks for Team Rules
OpenAI Codex CLI Early Review Notes
Train Teams on Cursor Subagents
Claude Code GitHub MCP Permissions
Connect Codex CLI with MCP
Add MCP Servers to Claude Code
Run Claude Code Agent Teams Safely
Measure AI Coding ROI on Teams
Choose a Code Review Model
Compare AI Coding Tools by Workflow
Review UI Changes with Playwright MCP in Claude Code
Use Cursor Rules in Team Repos
AI coding training for engineering, product and design
Data boundaries and human approvals for AI coding agents
From AI experiments to a team workflow
How Autonomous Coding Agents Write Code
How to review AI-generated code
ROI of AI coding tools
Shared standards for Claude Code, Cursor and Codex
Skill Rubrics for AI Coding Teams
Claude Code and GitHub Copilot for Teams
Choose an AI Code Review Workflow
Install Codex CLI for Team Workflows
Use Figma MCP in Claude Code
AI Code Assistant Training Plan
Run Codex Agents With Team Guardrails
Train Teams on MCP Integrations
Use Figma MCP in Cursor Safely
Codex CLI Tool for Team Workflows
AI coding maturity: five levels and where your team stands
Evaluate AI Coding Agents as a Team
Claude Code Skills for Team Workflows
Using Cursor MCP Servers Safely
AI Code Review With Receipts
Claude Code Review Workflow
AI Software Development Teams Can Trust
Cursor Agent Conventions for Teams
Cursor AI for Team Workflows
Governing ChatGPT dots agents: permissions and a first pilot
MCP Events and unattended agents: guardrails before rollout
Vetting ChatGPT plugins before your team installs them
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
Jev: probabilistic decisions for agent harnesses
From AI-generated code to a reviewable change
How to measure an AI workflow before scaling it
17K Runs of Claude, Codex, and Cursor
Sensez Catches Agent Code Smells
Skills MCP Searches Thousands of Agent Skills
Simon Willison on Breaking Claude Code Auto Mode
Z Brings Minimal Agentic Coding to Terminals
Speko Launches Voice AI Router
Cursor Cloud Agents Start Faster With Builds
Remarc: contextual feedback for coding agents
Codex vs Claude Code, What Teams Running Both Actually Say
Maximizing Claude Code Sessions
Claude Code 2.1.229 Stabilizes Remote Control
Ante Ships Offline Coding in One Binary
claude-code-meter Tracks Claude Code Usage Pace
MicroCodex: Reviewing a Small Coding Agent
Ski Runs Voice Coding Locally
agent-manager Puts AI Agents in tmux
Telnyx Kimi K3, Is It Fast Enough to Use?
Boffin Adds Per-Edit Agent Guardrails
AgentCost Tracks Local Agent Spend
Claude Code 2.1.219 Adds Opus 5
OneCLI Keeps Secrets Out of Agents
Bento Puts Slides in One HTML File
Test a Quota Router Before Adding Cursor
Claude Code 2.1.215 Makes Reviews Explicit
Agent-talk Gives Coding Agents a Backchannel
deja-vu Shares Agent Memory Over SSH
Juggler Turns Coding Agents Into a Workbench
Terence Tao Builds Apps With Coding Agents
searxng-ai-kit Turns SearXNG into an MCP Server
Kastra Enforces Policies for Cursor Agents
Claude Code 2.1.205 Hardens Agent State
TikZ Editor Makes LaTeX Figures Less Painful
Teach AI Coding With Guardrails
Train Teams on Coding Agents Safely
Govern Coding Agents as a Team in Cursor
Check Codex MCP access before a task
Subagent conventions for Claude Code teams
Cursor 3.8 Code Review with Subagents and Skills
Cursor Review Workflows With Subagents
Claude Code conventions for an engineering team
Cursor Skills and Team Rules for Large Codebases
Cursor Jira review workflow
Codex CLI Goal Mode, Appshots, and the Real Workflow
Codex CLI 0.132.0, AGENTS.md and MCP Official Docs
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 docs your team can read anywhere
Cursor Cloud Agent Setup and the Environment Contract
Codex auto review: setup, strengths, and limits
Fast mode is not the default: when fast models earn it
AI coding agents workflow guardrails for browser control
Is Codex CLI Giving MCP Too Much Reach?
AI agent guardrails that hold
Codex workflows for Chrome and the CLI
Agentic workflows from PR to merge
OpenAI Codex CLI AGENTS.md Official Docs, Explained
Codex 5.5: pin the model before you swap it
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
Agent boundaries for teams running coding agents
How to clean up agent-written code
Coding Agent Browser Automation Needs an Owner
AI coding wrappers that hold up under review
How returning Markdown from docs shapes agentic coding
Cursor .mdc vs CLAUDE.md vs AGENTS.md
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.