This feels even more relevant now with everyone using Instinct to shop online
Was just a bit too early
Thinking about the upcoming era when every store has an embedded AI sales agent, but every customer has a personal AI assistant that crawls stores for them to find deals.
I like to imagine the agents will just have brief chat before getting down to business.
1
15
456
Eli retweeted
how it started vs. how it's going
@opendoor chose Extend to power document processing for its title and escrow operations
10s of millions of pages, 300k+ homeowners, and we're just getting started
If you are a great engineer and have experience with AI document processing and OCR, please send me a DM - especially if you are in or are willing to relocate to Miami.
12
34
201
44,221
Our customers so often ask us how to recreate the document oriented UIs in our Studio, and we've never had a good answer for them until now
Excited to finally open source some of our work here so anyone can make beautiful experiences for their document agents
@andrewlu0 crushed it on this, go check it out!
Introducing Extend UI — open-source components for document agents
- 14 components & examples for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more
- fully customizable
- MIT licensed
when we started, we tried every file viewer and document component library we could find
unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for @ExtendHQ
it was only ever meant to be internal, but enough customers kept asking for it that we decided to give it back to the community
it's useful for building agents, user-facing document flows, or internal tools
we use and maintain it for Extend ourselves, so it'll keep getting better over time (and it's battle tested on millions of pages running through our system every day)
it also works with design system agents like @magicpatterns for faster exploration and prototyping
available today on the @shadcn component registry! some examples in 🧵
15
2,380
Long array extraction is a core capability we have invested a lot of time in even since the early days at Extend. It's a very challenging problem that is far from just a model problem, you need a purpose built harness that enables foundation models to reliably extract 1,000s of data points over hundred to get the most out of any top model.
Our MAX mode for extraction does exactly that through a combination of things like:
- Dynamic chunking of large documents based on table sizes/density and schema complexity, with semantic preservation as much as possible
- Multiple passes through the full document to make sure all split context is persisted across the extraction over a long document
- Heavy usage of smaller models used to detect and fix mechanical issues around a variety of page and section boundary conditions
All this together brings us closer to the end goal of *perfect* extraction over any sized document and schema complexity. The most exciting part though is this is using a system we built and launched months ago, we're now working on a v2 that will take it to another level of complexity handling, stay tuned 👀
we created a new, open source eval (LongArray-Extract) for one of the hardest problems in document processing: how to extract every row out of long documents
some highlights:
- Extend's array extraction is SOTA (99.2%)
- 3x faster than the next closest competitor (5 min vs 14 min)
it's based on examples we've seen in production:
> bank statements with 2,000+ transactions
> clinical adverse-event listings with 1,000+ events
> legal filings with hundreds of numbered factual paragraphs
if you've ever built a document pipeline on hundred page docs with thousands of listings, you know exactly how quickly things break
we open sourced the benchmark + dataset so teams can inspect the docs, run the harness, and compare results directly
1
2
12
852
Few understand this, but there is no better time to reflect on how to improve your document ingestion pipelines than on your morning commute in nyc
why are there AI ads on the nyc subway now... how do i get out of this bubble
designed by @AirfoilStudio ????
3
1
17
1,351
There are many things I love about our new site, but my favorite is the animation all the way at the bottom for those interested enough to scroll to the end
proud to share Extend's updated brand and website! we spent 100s of hours on it, and obsessed over every single detail
multiple full redesigns thrown out, fonts swapped and swapped again, every animation tweaked until it felt right...we even locked ourselves in a room and white-boarded every single word on the page until it resonated
why? prospects would see a demo and say something like "this is not what I expected based on your site", and they were 100% correct
our product has changed so much in the past year, that we wouldn't even recognize the old version (new APIs, capabilities, entirely new categories of problems we now solve). Our old site didn't reflect any of that.
we’re proud of how this turned out, and we hope it conveys the level of craft our team obsesses over in everything we ship
check out the new site below and please share feedback!
1
12
848
Eli retweeted
One takeaway that stuck with me from my session with Eli Badgio at @ExtendHQ: Document processing isn’t a prompt problem, it’s a pipeline problem.
Getting to 99%+ accuracy means optimizing every step end to end, not just writing better prompts.
Notes from the session below.
1
1
19
5,759
This was super fun to build, and even more fun to use
Introducing Composer — the first AI Agent for document processing.
Get to production-grade accuracy, autonomously in minutes.
In our early beta, some teams hit 99% accuracy on complex document tasks in under 10 minutes.
Composer is an agent built to optimize schemas the same way a human would (but way faster).
Instead of tuning prompts by hand, you point Composer at your eval set inside Extend.
Composer will:
- analyze where your schema falls short
- propose targeted improvements
- run multiple experiments in parallel
- surface diffs, accuracy gains, and traces behind each change
With this launch, Extend is the only product on the market that helps you reach production-grade accuracy this fast.
Composer is live for all Extend customers today! Try it out at the link in comments below.
2
8
566
Eli retweeted
Document automation isn't just about replacing humans with AI.
The real skill is knowing when to fully automate and when to keep humans in the loop.
Billions of documents processed daily means billions in savings or costly errors depending on your approach.
if you want to learn more check out our talk with @ExtendHQ happening tomorrow
maven.com/p/da0487/startups-…
3
4
35
7,337
Eli retweeted
going on TBPN in 20 min to talk all things Extend + our recent series A round, make sure to tune in!
Morning. Here are our guest call-ins today:
– @realsohamparekh (Soham Parekh)
– @crmiller1 (Author of Chip War)
– @aginnt (Hydra Host)
– @bridge__harris (Founders Fund)
– @pryceandstuff (Open Ledger)
– @jacobrintamaki (Beautiful AI Art)
– @auren (SafeGraph)
– @mehran__jalali (Looking for Lost Civilizations)
– @kushalbyatnal (Extend)
– @avlok (AngelList)
See you all on the stream.
1
1
13
2,348
Looking forward to this chat! Make sure to tune in July 9th
Excited to share my upcoming Lightning Lesson with @ExtendHQ on document automation that scales from startups to F500!
We'll cover:
• When to fully automate vs. augment human workflows (and why it matters)
• Building robust validation systems that catch errors BEFORE they happen
• Scaling document solutions across different industries and company sizes
After 6+ years building search systems and advising dozens of startups on RAG, I've seen the same patterns emerge repeatedly. Document automation isn't just about OCR anymore - it's about creating intelligent systems that know when to be confident and when to ask for help.
Join us July 9th to learn frameworks that could save your company millions in processing costs while preventing costly errors.
1
6
1,856
Today we announced raising $17M to build the world's first truly end-to-end automated document processing cloud.
This year has been a whirlwind, but we’re only getting started.
We’re already live with fortune 500s and cutting edge AI teams, powering some of the most critical ingestion flows in every industry, but there is so much to do to finally unlock the world’s most critical unstructured data.
Don’t take our word for it though, we just opened up access to the product so you can go try it out now.
4
1
26
918