
Pinned Tweet
Introducing Expand Fetch, a new way to scrape and crawl the web.
Your agent has never seen the web. No wonder it gets basic questions wrong.
Traditional Markdown APIs lose critical details. So we trained two System one models to change that:
Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts.
X-Ray, a JSON model that uncovers the hidden data behind every page.
Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw.
Three products. One API.
On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%.
Available today at $1 per 1,000 fetches.
Try it at expand.ai
It's rare to see so much original thought in a platform. Julius is ahead of the whole field. Highly recommend checking it ou!
excited to announce that @thecompanyai is part of @ycombinator F26!
we're building multi-agent orchestration modeled on how a real company works. fleets of agents get org charts, shared memory, and everything else required to run a company end-to-end, 24/7.
thanks @koomen & @maxkolysh for the support!
check it out @ thecompany.company
Introducing Expand Search 🔍 Pareto frontier search for your agent.
Two weeks ago we launched Expand Fetch. But which pages should your agent fetch?
We need search. And existing providers are either too expensive or low quality.
Expand Search costs $1.50 per 1,000 searches, with the highest average answer accuracy across the five public benchmarks in our evaluation.
Sign up in the next 24 hours and get 50,000 free credits.
We tested across five public benchmarks: WebCode, SimpleQA Verified, FRAMES, SEAL-Hard and AA-Omniscience Public.
Expand had the highest composite score, with accuracy comparable to Exa Auto and Brave LLM Context at less than a third of their price.
1
4
373
We're on a mission to make the web programmable. Fetch and Search are our first steps.
Give your agent this prompt to get started: "Set up expand.ai/start.md"
1
6
250
Oh noo I just made a 30 min dictation with ChatGPT and it can’t upload it. Heelp cc @mxstbr
285
Tim Suchanek retweeted
Effect 4.1 has been released!
New crypto modules, HttpApi improvements, and lots of other great additions and fixes.
Read more here: effect.website/blog/releases…
Enjoy!
@EffectTS_
1/ Excited to announce our new company Particle
This is our first step in a series of models focused on developers.
With particle-1, we focused on token efficiency and managed to keep parity in performance while using ~45% fewer tokens.
Live now: particle.ai
I can't believe now many agent products still don't let you write an immediate follow up question.
2
3
296
Sometimes, the answer is already on the page. You just need a better way to get to it.
That’s what @timsuchanek is tackling with @getexpandai’s Fetch, which captures web data that traditional extraction can miss, from tables and icons to hidden JSON.
Every line links back to its source, helping agents work with more complete, reliable context.
Because sometimes, better answers start with better inputs.
hubs.ly/Q04Cnp6z0
Dots is an incredible product. I just activated it and already got 3 notifications about things I would otherwise have missed: an accountant email with deadline, an important vendor change and an upstream PR that was stuck
4
413
This is huge! Humanlayer is one of the most thought through pieces of software. Very exciting!
10
1,031
Tim Suchanek retweeted
At @promptingco, we are now the first platform to track how your products show up across Muse, Grok Bot, and Instinct, all in one place.
AI agents are becoming the new front door to shopping. Consumers aren't just asking agents what to buy anymore. They're letting agents buy it for them.
See which of your products get recommended, which sources agents cite, and where competitors are winning. Know what it takes to get picked.
DM me and I'll show you how your brand stacks up against competitors.














