One task, several models at once
Technique
From one thread, ask the agent to start helper agents on different models that work on the same task. T3 Code's delegate_task lets an agent start child agents on any provider or model and wait for their results. Each helper runs in its official tool on a subscription you already have.
Theo's current stance
In his demo, helpers on GPT-6-1, Muse, Gemini 4 and Sonnet 5-5 explored one codebase with nothing special configured. Gemini only needed one sign-in click in settings.
Try it
- Install Claude Code, Codex or others and sign in there; T3 Code uses those existing logins.
- In one thread, ask for delegates on several named models to explore the codebase.
- Ask them to find interesting things and easy wins.
First seen
delegate_task : an agent can start child agents on any provider or model and wait for their results. This is the way to use several harnesses together.
Every mention
6:33
here, and I'm going to say, "I want you to review this code base with four different models. Spin up a delegate for 6-1 soul high in Codex, Muse wonderful at x-high, Gemini 4 Argon and anti-gravity, and Sonnet 5-5 in Claude. Tell them all to explore the code base and find interesting things as well as
7:15
these are all using their official harness and the subscriptions that I have for them, and I didn't do anything special to configure them. Gemini's a little annoying you have to click a sign-in button in the settings, but the rest are just using the stuff that you already have installed on your computer.
delegate_task : an agent can start child agents on any provider or model and wait for their results. This is the way to use several harnesses together.
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.