Changelog
Stay up-to-date with the latest updates to Yutori's products.
Discover Feed and Yutori MCP
Discover Feed
Browse what other people are using Scouts for with the new Discover tab on Scouts. Find inspiration, subscribe to public Scouts, and see what's trending across the community!
Yutori MCP
You can now use the Yutori API directly from Claude Code, Codex, Cursor, ChatGPT, OpenClaw, etc. via our MCP server. Create and manage web monitoring, deep research, and browser automation tasks — powered by the Yutori API — all without leaving your IDE.
Improvements
- Feedback guidelines provided via email replies or chat are now inspectable and editable in the Scout edit modal.
One-off tasks, chat with your Scouts, n1 vs. Opus 4.6, etc.
One-off tasks
Not everything needs to be a recurring Scout. You can now run one-off tasks — same powerful agentic search and browsing capabilities, just without the recurrence. Great for quick research or when you need an answer once, or to look at a report before scheduling a Scout.
Try a one-off task on Scouts →
Chat with your Scouts
You can now ask questions directly to your Scouts about its findings. The agent has full context of all past reports, so you can dig deeper into anything your Scout has surfaced without having to search through updates manually.
n1 vs Opus 4.6
We benchmarked our latest n1 checkpoint against Claude Opus 4.6 on the Navi-Bench and Westworld browser-use benchmarks. Opus 4.6 matches n1 in accuracy, but n1 is 2.5x faster and 5.6x cheaper.
Try out n1 on the Yutori API →
Inline images in Scout reports
Developer platform
We've released a dedicated platform for developers building on our API — a simple dashboard to manage API keys, track usage, and monitor your API requests.
Improvements
- Scouts can now be renamed from the Scout page.
- You can now invite subscribers when creating new Scouts.
n1 API, Invite Subscribers to your Scouts, and more
n1 API
Today, we made n1 — our browser-use model — available as part of our API.
n1 is a computer-use model optimized for web tasks through extensive mid-training, supervised fine-tuning, and reinforcement learning on real websites, achieving state-of-the-art accuracy with the fastest per-step latency amongst computer-use models.
Read the blog for more details and benchmarks →
For a no-code way to try n1, we've also released a Chrome extension that wraps around n1.
Invite Subscribers to your Scouts
You can now invite your team or friends to subscribe to your Scout. Invitees receive reports at the same cadence as you. First of many steps towards making Scouts collaborative.
Improvements
- In-app notifications for new Scout reports and invites.
- Support for downloading task trajectories for Browsing API tasks.
- Significantly reduced wait times in first Scout runs.
Research API, Remix, and Findings beyond a day
Research API
The Research API is now available! Research API tasks let you conduct wide and deep research into anything on the web using 100+ MCP tools and web navigation agents, reaching parts of the web that a search API can't get to.
Think of it as a one-time Scout run; same agentic search capabilities but without the recurrence.
Remix Scouts
You can now Remix any existing Scout shared with you to create your own version of the Scout, personalized for your specific needs.
Findings beyond a day
The Findings view now lets you look at historical reports beyond just the current day. Just pick a date (or swipe!) to browse findings and see what your Scouts discovered over time.
Realtime agent livestream, Twitter bot, natural language feedback & improvements
Watch agents work in realtime
Creating a new Scout now lets you follow along with the underlying agents, tracing their actions and reasoning in realtime as they make progress on your query.
Twitter bot: @ScoutThisForMe
We just released an X bot for Scouts. Tag @ScoutThisForMe on X with anything you'd like to stay updated on, and it automatically creates a Scout that replies on the thread with updates.
Natural language feedback on the web app
You can now provide feedback directly on the web app using natural language. This feedback gets absorbed into guidelines for the Scout, making it simpler to personalize and improve the quality of updates over time.
Improvements
- Faster Scout page load times.
- Improved checkout flow with pre-populated email addresses.
The multi-agent architecture powering Scouts
An average Scout run invokes 76 agents across a wide variety of tools, and processes ~1M tokens, for just 35 cents per run — all in service of delivering timely, comprehensive coverage of information across the long tail of the web.
We published a deep dive into the engineering principles behind Scouts — the architectural decisions that make continuous monitoring practical, the pitfalls we encountered, and how we balanced quality with cost.
Scouts is now generally available
Today, we're making Scouts available to everyone.
With a simple query, Scouts lets you deploy a team of AI agents to monitor anything for you — for house hunting, early stages of travel planning, sourcing leads, discovering rare products, job search, staying on top of niche news / research / podcasts, discovering local events, etc.
The underlying agent architecture is incredibly powerful — subagents all the way down, powered by our own web navigation agent, and with access to way more tools than before.
This what the future of interfacing with the web looks like. Where you're not sitting there manually browsing and refreshing, buried in tabs, ads, noise, distractions, context switches.
Scouts run 24x7 in the background on the web. So you have the mental space to focus on what's most meaningful to you.
Private Scouts
Scouts can now be made private so only you can view them.
Public Scouts are accessible via public-but-unlisted URLs, and can be shared with others for them to subscribe to. In either case, only the creator can edit the Scout.
Introducing Navigator and our API
Today, we're releasing Navigator — a state-of-the-art web agent that autonomously navigates websites to complete everyday tasks — available via our API.
It achieves 78.7% on Online-Mind2Web and 83.4% on Navi-Bench, with per-step latency 2-3x faster than other computer-use models like Claude 4.5, Gemini 2.5, and Claude 4.0.
Navigator can handle a wide range of real-world web tasks — checking availability, comparing prices, filling out forms, making reservations, ordering food, completing purchases, etc.
The bitter lesson for web agents
The last 1 year of building web agents has taught us a new bitter lesson that we think not many others are internalizing yet.
Agents that perceive the web like humans — using screenshots of websites — navigate and generalize better than agents that rely on the HTML or DOM.
Support for replying to Scout emails to give feedback
You can now reply directly to any report email to provide feedback to your Scout. This feedback gets incorporated into the Scout's subsequent runs, making it better at finding exactly what you're looking for.