every company has a shared drive nobody can find anything in we built a doc library that files itself and answers questions with the exact page + citation it's called jevbox. built on extend parse + jev. and it's open source. a few ways to use it: - contract library for procurement and ops - due diligence dataroom for VCs - policy and compliance reference for HR - clean context for your agents MCP included with authz built in (think google drive permissions) self-host it or one-click deploy to render, instructions are in the repo. link in the comments!
10
5
32
3,180
file system & chat bot 📂
1
8
285
dots keeps leaving me on read
1
4
171
Is me buying a LAB putter off Temu a microcosm of AI spend slowly routing to Chinese models?
3
174
Andrew Luo retweeted
Today we're shipping Parse Auto-Router: it picks Light or Performance Parse for every page in a document, so you don't have to. Clean pages go to Light, hard pages go to Performance. Set engine to parse_auto to try it today.
Article

Introducing: Auto-Router for Parsing

Parse Auto-Router evaluates each page in a document and routes it through Light Parse or Performance Parse based on page-level signals. This gives teams one configuration for mixed-complexity

5
3
20
10,912
Edit fills PDF forms programmatically, with or without embedded fields. We've improved detection on low-quality scans and skewed pages, made field labels more consistent, and redesigned filling to better handle corrupt files, revisions, and signatures. The new form detection model is fine-tuned from the layout model behind Parse. Great to see our AI/ML team's work compound across products! @ameyaajoshi @joon_kim96
Our Edit API got a major upgrade with a new forms model delivering: > better field detection, labeling, and filling > improved corrupt PDF handing > verifiable signatures that survive revisions check it out and try it on your docs!
Article

Introducing Edit with Improved PDF Form Detection and Filling

TLDR: Edit helps AI/ML teams automate PDF form filling by reducing manual field mapping, improving form field detection accuracy on low-quality scans and skewed pages, and improving handling of

4
4
17
1,096
i was thinking more
I know we all thinking the same thing
Made with AI
6
317
added a PDF editor to Extend UI annotation, signing, forms & redaction, built on embedpdf also a paper inspired color picker :) extend.ai/ui/docs/components…
2
1
14
1,060
benchmarks 📊
2
10
535
maybe just me but noticing coding agents have been patching libraries more frequently fable found a bug with older versions of next js swc and regex code, components would render fine locally but not in production builds
179
Andrew Luo retweeted
today, we're shipping Extend Templates: 50+ document types, ready to go. every template comes with the pipeline, processor settings, schema, sample document, and expected output already figured out. until now, teams rebuilt all of that every time, based on vibes and whatever expertise was locked in someone's head. point your coding agent at one, import it into your Extend account, or fork it on GitHub. browse the library and find your document type!
just shipped @ExtendHQ Templates with @andrewlu0!!! 50+ pre-built doc processing pipelines + a smart search library. We noticed AI teams ran into similar challenges, like the 12-page EOB w/ nested tables, or the bad receipt scan. Now they can solve them with Extend in <1 minute. — every page is agent-readable, so you can point Claude Code or Codex at one and the template ships itself — import into your Extend account in <10s — fork it, or grab the client code in TS / Python / Java / Go Check it out! It's live now at extend.ai/templates
1
4
13
1,471
Andrew Luo retweeted
our workflows product has executed 100,000,000+ runs, and companies like Opendoor, Zillow, and Mercury use it to run their document pipelines. today, we're shipping Workflows v2. very few document problems are a single step. the most common thing teams build is a chain: split → extraction → validation → routing (→ sometimes a human in the loop). most teams end up writing orchestration code, retry logic, and state management to build this flow. workflows exist so you don't have to rebuild that infrastructure every time. what's new in v2: - a GitHub app for CI/CD: review, test, and deploy workflow changes like any other production code - multi-file extraction: treat a packet as one unit of work instead of a pile of disconnected calls - validations: catch bad output at the step where it happens, not three systems downstream - routing logic: branch on extracted fields, confidence, or your own business rules - agents: describe what you want in natural language, and agents can manage the exact same workflows as code
6
6
36
6,017
Onboarding flow 🪶
4
2
14
1,002
Kimi K3 reverse engineered the MTA's API and now i can check the optimal train line to take to work every day gpt 5.6 users could never
1
23
1,544
Added a React PowerPoint viewer to Extend UI Supports most of the charts our Excel viewer does, still testing the support for different shapes/fonts extend.ai/ui/docs/components…
1
1
17
3,370
aint no way 🤯
Made with AI
1
1
56
8,885
steering it the right way is the magic prompt
The people getting great UI results with AI aren’t using a secret model or a magic prompt. They know what a great interface looks like, and they know how to steer AI towards it. Work that used to take a week takes a day, and the quality bar doesn’t drop, it goes up, because you spend your time on the things that matter. At the end of the day, people that use AI best are the ones that were excellent before LLMs as well. The ones that got the fundamentals right, went that extra mile, and cared about the thing they were working on.
11
1,398
It's a great component and soon will be powering a refreshed chat experience @ExtendHQ
If you want to add a navigation trail to your own chat app, the new MessageScroller component has the hooks you need out of the box. Look for: const { currentAnchorId, visibleMessageIds } = useMessageScrollerVisibility()
1
10
807