What is your technique of getting the job done with AI agents?
by•
I believe the key way where AI assistants really become a big help from now on depends on how many tasks you can delegate to them in parallel.
When I get down to development work, I usually have eight windows open, and occasionally when the administrative tasks start pouring in I have thirty-plus running.
You see, AI is very swift and with advances in every AI model, it's possible to entrust an AI with longer tasks. Consequently, if I only had one session open, I'd be the one waiting on the agent. Several at once is different. The agents are the ones waiting for our decision while the work continues and I believe that is how we get far more results done.
What is your technique of getting the job done with AI agents?
14 views
Replies
I usually break the work into smaller independent tasks and let agents handle them in parallel while I review the results and make key decisions so I can keep moving without waiting on every step
@shivam_kushwaha16 Same here. Independent is the key word for me. When two sessions touch the same files they start stepping on each other, so I try to split the work so each one has its own corner.
@hisashispace Exactly, splitting tasks by file ownership is a smart way to avoid conflicts when agents work in parallel Have you tried using separate Git branches for agents that need to modify the same files
@shivam_kushwaha16 Yeah, for the bigger jobs each one gets its own git worktree and its own branch, made by a small script. That way nothing half done lands in main.
One catch we ran into: our worktrees share node_modules with the main checkout. Running a full npm install inside one broke the link to a local package, and the build failed. It took about an hour to track down. Now we only install the one package we need when we're in a worktree.