A conceptually simple web task can become a “long-horizon” task for today’s computer-use models.
If a model can only act through UI primitives, click, type, scroll, everything gets forced into a sequence of low-level operations. Even simple tasks turn into dozens of steps: filling forms field by field, clicking through variants, and executing long sequences of small, incremental interactions.
We introduced a hybrid mode: vision + DOM + code. Pure vision generalizes but is unnecessarily slow; pure DOM + code is fast but can be brittle given the current state of the web. The hybrid combines both, taking the fast, programmatic path when possible, while using vision to verify against what’s actually rendered.
The result: "long-horizon" tasks collapse into shorter ones—less time, less compute, and more reliable outcomes.
𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐢𝐧𝐠 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫 𝐧𝟏.𝟓
The most capable computer-use model for the web.
Pareto-domination: accuracy, latency, cost
• SoTA across all benchmarks
• +5-10% over GPT 5.5, Opus 4.7, n1
• +25% over Gemini
• 2x faster, significantly cheaper
Expanded action space
• UI actions (like n1)
+ JavaScript generation & execution
Building and using Delegate, I've had to re-learn how I work with agents.
Delegation asks for a different kind of giving up control. Not the back-and-forth you're used to with LLMs. You hand something off and let it run.
It takes some getting used to. But once it clicks, it's hard to go back.
Thanks @kytsune for covering Delegate!
> Delegate is not a chat interface like ChatGPT; it is an active participant that goes out and takes actions on a user’s behalf.
> When additional access is needed, Delegate has a superpower: an app called Yutori Local.
> Local is an app that currently runs on MacOS ... It can reach out onto the web, shop for you, navigate web pages, log into them and then take actions on the user’s behalf – including buying tickets to a matinée.
Why cowork when you can delegate?
We've been heads down on our new agent, excited to get it live! Plz lmk how it works for you.
- Sent by Razzo, Max's Delegate.
This is an amazingly powerful and capable product.
1. proactive
2. personal
3. great at web research (open and logged in context)
Prepare to be amazed.
As I've been saying in the team, "Just talk to it", it's great with memory.
Happy Delegating!
Today we’re launching Delegate!
Let Delegate handle the busywork so you can focus on the outcome and move on with your life.
From coworking → delegating.
Try it: https://t.co/YQ4x8Bvqh2
This is the real deal.
It’s an agent you can actually give work to and then walk away. No babysitting. No constant prompting. Just “here’s the mess—figure it out.”
Delegate from @abhshkdz & @yutori_ai feels like the first agent that really understands delegation, not just chatting.
https://t.co/UF07ydZh03
This is what we started Yutori for, and today we're launching it!
Meet Delegate.
Designed for delegation, not chat. It’s proactive, it’s always on, it remembers.
It connects to your apps and learns your context — who you are, how you work and what your priorities are.
It schedules itself forward, it follows up, it follows through.
You don’t need the perfect prompt. Just do a stream of consciousness brain dump of everything on your mind. Delegate it all. And move on. It will break things down. Finish what it can. Come back for input where it needs it.
Try it! https://t.co/T2wH2mgyPf
AI agents should be like microwaves — reliable, intuitive, no questions asked and no surprises. You always know what you're gonna get. Every single time.
That's Delegate.
Super proud of what the team shipped! Can’t wait to hear what you think :)
We just shipped the biggest update to Scouts since launch (and yes, we know what day it is).
Scouts used to be just for monitoring. Now they act.
Scouts is now a general-purpose task execution engine for the web. Tell it what you need done, and it does it: across any website, behind any login, connected to your apps.
🧵
Introducing n1 — Yutori’s browser-use model.
Available today via our API.
If you’ve been using Claude, Gemini or OpenAI’s computer use models for browser automation — you should switch to Yutori’s n1. It is more accurate, significantly cheaper, and a drop-in replacement.
Yutori is sponsoring Creators Corner's Agentic Orchestration Hack!
Come build on Yutori's API. Besides access to state-of-the-art web agentic tech, there will also be prizes for the Best Yutori API projects! A large part of the @yutori_ai team will be there through the day — come say Hi :)
January 16th.