Loading video...

Video Failed to Load

Go Home

Recipe for insane development speed: Git worktrees + AI agents = parallel coding superpowers While one agent fixes issue #361, another tackles #305, and a third investigates that user bug report—all without conflicts. This changes everything.

45,195 views • 1 year ago •via X (Twitter)

11 Comments

Kieran Klaassen's profile picture
Kieran Klaassen1 year ago

See my scripts

Alexander Mia's profile picture
Alexander Mia1 year ago

INTRODUCING: Agentic Security - LLM Security Scanner! 🔍 🔑 Features: Scans for prompt injections, jailbreaking & more. Provides detailed reports & options to customize attack rules. 🔗access the GitHub Link ↓

Iggy's profile picture
Iggy1 year ago

I made for precisely this!

Courtland Allen's profile picture
Courtland Allen1 year ago

I've been doing this but realizing that working in parallel, isn't that helpful on a regular basis. Like by the time I set up a new work tree, install dependencies, and describe my task to the AI, the AI is already done with what it was doing in the first work tree

Kieran Klaassen's profile picture
Kieran Klaassen1 year ago

with ruby all of that ios cached so no overhead

Peter Steinberger's profile picture
Peter Steinberger1 year ago

I experimented with worktree, claude works better with separate clones. I use 6 for my project.

Kieran Klaassen's profile picture
Kieran Klaassen1 year ago

how is that different than a worktree? a worktree is just a copy of the files too right?

andrii's profile picture
andrii1 year ago

great, and then who merges all this mess to main resolving all the inter-dependencies, conflicts and regressions?

Kieran Klaassen's profile picture
Kieran Klaassen1 year ago

with good research before its really good

Freddie Vargus's profile picture
Freddie Vargus1 year ago

you should check out

Kieran Klaassen's profile picture
Kieran Klaassen1 year ago

Cool will do! Thanks

Related Videos

Claude Code made developers 10x faster. Git worktrees just broke the speed limit again. Teams are now running 4–8 AI agents in parallel — each in its own branch — working at the same time. Not sequential. Not one prompt at a time. Parallel AI engineering. Here’s the shift: Old workflow: Prompt → wait → review → fix → repeat New workflow: Agent 1 → builds feature Agent 2 → writes tests Agent 3 → reviews security Agent 4 → refactors architecture Agent 5 → updates docs All running simultaneously. This is called compound engineering. You’re not using AI as a tool anymore — you’re managing a team of agents. Git worktrees make this possible: Each agent gets: • its own branch • its own workspace • its own context • its own task No conflicts. No overwriting. No chaos. Just parallel progress. The result? Claude makes you 10x faster. Parallel agents multiply that again. 10x → 30x → 50x productivity. Senior engineers are already doing this: brainstorm agent planning agent implementation agent review agent testing agent It’s basically CI/CD for thinking. And the weirdest part: This actually slows each step down but speeds the entire system up. More planning More reviewing More parallel execution = higher quality + faster delivery. We’re moving from: "prompt engineering" to: "agent orchestration" The new skill isn’t coding. It’s managing AI workers. The best engineers won’t write more code — they’ll run more agents. Bookmark this. Parallel AI development is the next meta

Nainsi Dwivedi

33,137 views • 1 month ago