[go: up one dir, main page]

Git

17 articles about git.

1.6M Git Events Show AI Code Needs More QA

·12 min read

When AI agents generate most of your code, your review process must scale to match. Analysis of 1.6 million git events reveals where QA breaks down - and how to fix it.

code-reviewqaai-codinggitdeveloper-workflow

12 Agents on the Same Branch: The Git Chaos Nobody Warned You About

·13 min read

Running 12 AI agents on the same git branch causes merge conflicts, file stomping, and broken builds. A deep technical guide to git worktrees, conflict detection, and task decomposition for parallel agent development.

gitmulti-agentmerge-conflictsgit-worktreeparallel-development

600 Decision Logs in 2 Months

·2 min read

Git commits are decision logs. With 129K commits from AI agents, every architectural choice, bug fix, and feature decision is recorded with full context and

gitdecision-logsdocumentationcommitsai-agents

Why Your Audit Store Cannot Be Inside the Process

·2 min read

Using git as an external append-only audit store for AI agents - why the thing being audited should never control the audit trail.

ai-securitygitaudit-trailagent-safetyappend-only

Git Was Built for Humans but AI Is Writing My Code Now

·2 min read

Why git's human-centric workflow breaks down with AI-generated commits and how intent-based rollback could fix the problem.

gitai-codingversion-controldeveloper-toolsautomation

How Do You Prevent JSON-Seppuku?

·2 min read

Agents that modify their own config files can corrupt themselves. Store config in git with auto-commits for instant rollback.

configurationgitrollbackagent-safetyjson

The Problem with Logs Written by the System They Audit

·3 min read

When your AI agent writes its own activity logs, those logs cannot be trusted for verification. Git as an external source of truth beats self-reporting

verificationgitloggingai-agentreliability

Your AI Agent's Memory Files Are Lying - Git Log Is the Only Truth

·2 min read

Agent memory files described completing a task that git log showed was never committed. Why you should never trust self-reported memory and always verify

gitmemoryverificationai-agentreliability

Coordinating Multiple AI Research Agents Through Git - A Practical Guide

·6 min read

Git worktrees give each AI research agent an isolated workspace, merge conflicts surface contradictory findings, and the commit log becomes a complete research audit trail. Here's how to set this up and when to use it.

multi-agentgitcoordinationresearch-agentscollaboration

Sandbox vs YOLO Mode for AI Coding Agents

·3 min read

Should you run AI coding agents in a sandbox or let them execute freely? YOLO mode with frequent git commits offers the best balance of speed and safety.

ai-codingsandboxyolo-modedeveloper-workflowgit

What Actually Happens When 12 Agents Work on the Same Branch

·2 min read

Real lessons from running a dozen AI coding agents on one git branch - terminal collisions, build conflicts, and why a terminal manager is essential.

parallel-agentsgitmulti-agentterminal-managementdeveloper-tools

YOLO Mode vs Explicit Approval - When to Let AI Agents Run Freely

·2 min read

When should you skip permissions for AI agents? The answer depends on reversibility. Git repos are safe to YOLO, but email and messaging need explicit

ai-agentpermissionsyolo-modegitdesktop-automation

Agent Orchestrators vs Parallel Sessions with Worktrees

·2 min read

Comparing agent orchestration patterns vs parallel sessions with git worktrees. Real isolation wins for coding tasks because each agent gets its own workspace.

agentsorchestrationworktreesparallelgitcoding

Should AI Agents Get Co-Author Credits on Git Commits?

·2 min read

When Co-Authored-By: Claude appears in every commit, the AI has more co-author credits than human teammates. The case for transparency in AI-assisted

ai-developmentgittransparencyco-authorclaude-codeethics

Adding Co-Authored-By Claude to Every Git Commit

·2 min read

Why putting Co-Authored-By: Claude in your CLAUDE.md for automatic commit attribution matters for AI transparency. When the AI has more credits than your

gitco-authorclaude-codetransparencyai-developmentbest-practices

The Consensus Illusion - When Multiple AI Agents Work on the Same Codebase

·3 min read

Five agents on the same branch with no isolation creates the illusion of a stable codebase. Why consensus fails and conflict resolution should be left to

multi-agentconsensusgitcodebaseparallel-developmentconflict-resolution

Receipts Outlive Memory - Why Git Blame Matters More Than Agent Memory

·2 min read

Agent memory fades, gets pruned, and can be wrong. Git blame is the ultimate receipt - every decision traced to an exact commit, an exact prompt, an exact

gitaccountabilityagent-memoryversion-controldeveloper-tools

Browse by Topic