#002 AI Powered Data Transformation, Combining gen & trad AI, Semantic Validation

7 snips

Apr 12, 2024

Antonio Bustamante, a serial entrepreneur, talks about building bem.ai, a data tool for AI and software. Topics include challenges of integrating semi-structured data, using LLMs in data transformation, reliability of data infrastructure, and interoperability layers for systems.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ANECDOTE

Price Sheets Broken By Pumpkin Decorations

Antonio recounts parsing farm price sheets that broke whenever customers added holiday decorations or changed formatting.
He said they even asked users to stop adding pumpkins because formatting changes broke parsing.

INSIGHT

LLMs Are Part, Not The Whole

Antonio says LLMs are only ~30% of the solution and must be combined with validation and infrastructure.
He emphasizes building fault-tolerant systems that keep LLM strengths and discard their weaknesses.

INSIGHT

Preserve Geometry For LLM Inputs

Antonio stresses feeding LLMs documents that preserve geometry and semantic co-location, not just raw OCR text.
He argues LLMs need structured context (tables, spatial cues) to interpret complex documents accurately.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Today’s guest is Antonio Bustamante, a serial entrepreneur who previously built Kite and Silo and is now working to fix bad data. He is building bem, the data tool to transform any data into the schema your AI and software needs.

bem.ai is a data tool that focuses on transforming any data into the schema needed for AI and software. It acts as a system's interoperability layer, allowing systems that couldn't communicate before to exchange information. Learn what place LLMs play in data transformation, how to build reliable data infrastructure and more.

"Surprisingly, the hardest was semi-structured data. That is data that should be structured, but is unreliable, undocumented, hard to work with."

"We were spending close to four or five million dollars a year just in integrations, which is no small budget for a company that size. So I was pretty much determined to fix this problem once and for all."

"bem focuses on being the system's interoperability layer."

"We basically take in anything you send us, we transform it exactly into your internal data schema so that you don't have to parse, process, transform anything of that sort."

"LLMs are a 30% of it... A lot of it is very, very like thorough validation layers, great infrastructure, just ensuring reliability and connection to our user systems.”

"You can use a million token context window and feed an entire document to an LLM. I can guarantee you if you don't, semantically chunk it out before you're not going to get the right results.”

"We're obsessed with time to value... Our milestone is basically five minute onboarding max, and then you're ready to go."

Antonio Bustamante

bem.ai

Nicolay Gerold:

Semi-structured data, Data integrations, Large language models (LLMs), Data transformation, Schema interoperability, Fault tolerance, Validation layers, System reliability, Schema evolution, Enterprise software, Data pipelines.

Chapters

00:00 The Problem of Integrations

05:58 Building Fault Tolerant Systems

13:51 Versioning and Semantic Validation

27:33 BEM in the Data Ecosystem

34:40 Future Plans and Onboarding