What should I attend at MLOps World? We had bem read every talk
We're at MLOps World in Austin next week. We used bem to index all 65 talks and workshops, so you can match them to what you care about, or to your LinkedIn profile.
Antonio Bustamante
Blog
Notes from the bem team.
Engineering notes, product updates, and research on applied AI from the bem team.
2026
- Bem Labs
We read the fine print of the AI agents I actually use
dots, Muse, Instinct, Grok Bot and Perplexity's Teammates get your email, your calendar and sometimes your card. We used bem to map their terms into a graph: who pays when the agent gets it wrong, who can see your stuff, what it won't forget, and who can buy your data. Plus 10 gotchas. Every line links to the clause.
- Bem Labs
We read Anthropic’s S‑1 the way Wall Street will
Anthropic filed its S-1 this morning. We pointed bem at all 420 pages and the exhibits: classify, split, extract, enrich, evaluate, shape, send, join, render and parse, plus an ontology, a knowledge graph, and a chatbot on the File System API. Every output is here.
How to automate certificate of insurance verification for a large fleet
A working COI verification pipeline on the bem V3 API. Real ACORD 25 certificates in; limit checks, expiration flags, and a live carrier knowledge graph out. About three seconds per certificate, with a trace you can audit.
Sovereign AI starts in your review queue
Everyone selling "sovereign AI" is selling residency or GPUs. Ownership is a loop: your people correct, your model learns, and you keep the asset.
How to turn a PDF into structured JSON without writing a parser
A hands-on guide. Go from a raw invoice PDF to validated, schema-shaped JSON in a single bem API call, with a full trace you can audit. Real request, real response, no parser required.
How to homogenize vendor datasheets into one internal spec
Every supplier sends a different format. Extract each onto your internal schema and render them all into one template. Shown on two real vendor epoxy datasheets from 3M and Henkel Loctite.
How to turn a shipping document into a clean confirmation
Extract the details from the document you received, reconcile against your records with Enrich, and render a standardized confirmation. Shown on a real public bill of lading.
How to abstract a contract with bem Render
Extract the terms from a dense agreement, render a clean source-attributed summary, and keep every value traceable. Grounded in DigitalOcean's real credit-agreement amendment.
Render: verified documents from unstructured data
Every document generator assumes you already have clean data. Render is the one connected to the part that gets it. We ran it on DigitalOcean's real credit-agreement amendment: bem read the 33-page filing, generated a verified facility summary, and flagged a malformed figure in the filing instead of silently correcting it. New in bem today.
- Engineering
Reverse-engineering Claude's CLI with Kimi K3 and Ghidra
Fable would never. Kimi K3 breezed through it.
Danny DeVito is mentioned 4 times in Jersey Mike's S-1
We ran the whole S-1 through bem, built a knowledge graph, and counted. The sandwiches check out too: 3,300 locations, $4.3B systemwide sales, a 45%-plus Adjusted EBITDA margin, and the Predecessor/Successor accounting from Blackstone's buyout.
- Engineering
Docket: turning a Supreme Court opinion into a legal-AI app
The Supreme Court’s birthright-citizenship ruling runs 194 pages: a majority, two concurrences, and three dissents. We turned it into Docket, an open-source legal-research app, to show what you can build on bem. The full opinion, an interactive knowledge graph, and an agent that answers with citations while reading only what it needs.
Agentic File System Access
A knowledge graph and cross-document memory for your documents, built right out of the box. The best of semantic search and a real filesystem for your agents, with no vector store to maintain.
How to parse Bending Spoons' F-1 in seconds
bem turns the whole prospectus into a knowledge graph you can traverse.
- Engineering
Launching Data Join: Many Documents, One Record
The first n-way matcher for unstructured documents. Match many files into one record, with full lineage on every field.
We used bem to analyze SpaceX's 308-page S-1 filing
How to use bem to analyze an S-1 filing: from PDF to orbital GPUs.
The last freight document pipeline you'll build.
Extract, Parse, Enrich, Classify, Send. One workflow that handles every document a logistics operator touches in a day.
Product Launch: bem Integrations
Native connectors for Google Drive, Dropbox, SharePoint, Box, and S3. Available in every account today.
- Engineering
Launching Bounding Boxes: Show Your Users Exactly Where Their Data Came From
Every extracted field now includes the exact page coordinates of its source. Build provenance into your product with one flag.
- Bem Labs
Why AI CRMs Still Make You Work
Real ambient systems don't ask. They observe and act.
- Whitepaper
The Two Paths of Document Intelligence
RAG and agent-native document access are diverging. This guide covers both, then demonstrates each on a 456-page NFL contract with working code.
- Updates
V3: The Foundation for Verified AI
Today we’re shipping the biggest release in Bem’s history: a redesigned API, first-party SDKs in four languages, a Terraform provider, an MCP server for agent integration, and a CLI. Six releases, one principle — deterministic outcomes from probabilistic systems.
- Perspectives
How to Govern Unstructured Data
Your governance stack only covers structured data. Here is how to close the gap.
- Guides
Why Do Finance and Accounting Teams Trust Bem?
It's been a busy quarter. We've been onboarding and working with more and more teams handling extremely sensitive data. We're excited to tell you more about it.
- Updates
The AI Industry Is About to Bifurcate. Here's Our Bet
Models like Claude Mythos will coexist with small, specialized ones. They serve fundamentally different purposes. We're building for the side that keeps regulated industries running.
- Engineering
How to Validate AI Document Extraction Accuracy in Production
Confidence scores, dual-model evaluation, and the correction loop that makes extraction reliable at scale
Laziness Is Destroying the Software Industry
Seven infrastructure failures in seven days. This is what happens when speed is the only metric.
- Perspectives
MCPs, CLIs, and APIs Are All Just the Same
Programmatic access to resources has always been non-negotiable. So why is the industry losing its mind?
- Perspectives
Why is bem not an agent?
Because our customers don't need one, and agents aren't ready *yet* for day-to-day critical business operations.
- Perspectives
Code Never Mattered.
No, Perplexity did not kill Bloomberg. No, Claude Code didn’t kill ServiceNow. Codex didn’t kill Salesforce.
- Features
Introducing Forge: Drop your data. Deploy.
Forge closes the gap between data extraction and a running operation. Drop your data. Deploy.
- Updates
Deep Roots, Global Reach: Welcoming BuenTrip Ventures
We are proud to welcome BuenTrip Ventures as a strategic investor. A partnership rooted in shared values, deep ties to LatAm, and a commitment to building the deterministic infrastructure that powers the future of AI.
- Engineering
Why we built Private Link (and why you should use it)
Zero public exposure. Fully managed infrastructure. Why Private Link is the no-brainer architecture for enterprise AI.
Introducing Video support: Computer Vision as infrastructure
Full video and image understanding, now as infrastructure
How to build a Retail AI Agent with the bem API
Create an agent with bem that can detect products in planograms, CCTV, social media posts, e-commerce, and more
- Perspectives
Why Your ERP is Lying to You (And How to Fix It)
Stop wasting 80% of your payroll on data entry and start generating real-time intelligence.
- Guides
How to parse invoices accurately with bem
Invoices can be gnarly. Here's a production-ready, enterprise workflow to extract their data accurately (and enrich it with your source of truth).
2025
- Engineering
Building AI That Doesn't Break in Production
bem is an event-driven, function-based AI platform. That's uncommon, but so is AI in critical production environments.
- Features
- Features
- Perspectives
- Guides
- Perspectives
- Perspectives
- Perspectives
- Features
- Features
- Features
- Features
- Features
- Guides
- Posts
Introducing Function Review: From Black Box to Glass Box for Production AI
Measure, manage, and guarantee the performance of AI primitives in production. Now it's possible to build AI systems for unstructured data that you can trust.
- Features
- Customer Stories
- Updates
- Updates
- Customer Stories
Ply revolutionizes RFQ management with bem's AI-powered automation
Ply revolutionizes RFQ management with bem's AI-powered automation
- Perspectives
- Perspectives
- Perspectives
- Guides
- Perspectives
- Perspectives
- Perspectives
- Perspectives
- Perspectives
- Engineering
- Perspectives
- Features
- Perspectives
- Customer Stories
- Features
- Perspectives
- Features
- Perspectives
- Perspectives
- Podcasts/Video
- Posts
Order.co achieves seamless procurement automation with bem's AI-powered data transformation
Order.co achieves seamless procurement automation with bee's AI-powered data transformation
- Posts
Loop automates data transformation at scale for new clients with bem
Loop automates data transformation at scale for new clients with bem
- Podcasts/Video
Hard Software Episode 12: Infrastructure Evolutions with Maxim Fateev, Co-Founder + CTO @ Temporal
In this episode, Antonio sits down with Maxim to cover all things AI innovation, infrastructure hot takes, and Maxim's journey prior to Temporal.
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
- Podcasts/Video
2024
- Podcasts/Video