Home
Companies
SID

SID

Connect Google, Notion & Email Data to LLMs

We make it easy for developers to connect customer data to their LLM apps. Instead of spending months on integrations and retrieval pipelines, Reworkd's AgentGPT added our button in an afternoon and let thousands of people connect their Notion, email and Drive instantly. Every single AI company is building data retrieval. Currently, they're doing this from scratch – we don't think they should have to. Just like OpenAI made working with LLMs as simple as an API call, SID makes it easy for every AI company to access data the same way.

SID
Founded:2023
Team Size:4
Location:San Francisco

Active Founders

Maximilian-David Rumpf

Max is the CEO of SID.ai. Previously, he was a researcher at ETH Zürich, where he worked on AI accelerator design with the professor who developed Google's TPU architecture. In early 2023, he developed MultiGPT, the first multi-agent AI that garnered thousands of users and ~500 Github stars in a single week. Max was awarded a German national excellence scholarship, awarded to 0.5% of German students.

Maximilian-David Rumpf
Maximilian-David Rumpf
SID

Lukas Ruflair

Lukas Ruflair is co-founder and CIO at SID.ai. He studied Computer Science at ETH Zurich, loves hacking and previously built one of the first multi-agent AI simulations, racking up millions of views on Twitter.

Lukas Ruflair
Lukas Ruflair
SID

Lotte Seifert

Lotte is determined to let people use their data for their own good. She holds a degree in CS from ETH Zürich and a degree in Economics from the University of St. Gallen. In early 2023, she developed MultiGPT, the first multi-agent AI that garnered thousands of clones and ~500 Github stars in a single week. Previously, Lotte worked at Europe’s first AI venture studio Merantix and organized the continent's largest student-run startup conference with guests such as Matt Cohler & Esther Wojcicki.

Lotte Seifert
Lotte Seifert
SID

Company Launches

tl;dr

We allow you to connect your LLM apps to your customer's data in an afternoon using a single button and an "AI-friendly" API.

Ask: Please introduce us to companies building AI apps or considering adding AI to their product. We can save most teams months in engineering & MLOps.

❗Test the API with your own data: We have a free live demo at demo.sid.ai

Problem: Data x AI takes months & DIY is the only option

Today, companies like Jasper spend months building integrations with their customer's salesforce, email, and docs. Previously, we made consumer AI apps (that went viral on Twitter) and found we spent 70% of our time doing data integrations instead of improving our product.

Why is it taking Jasper months?

There are two challenges, and developers tend to underestimate both. You must ingest the data (e.g., call Google's API) and interpret the data (i.e., go from chunks to insights).

Ingesting is a lot of grunt work: The APIs change, and a lot of infra is needed to keep information up-to-date – and deprecate the old. This is finicky and maintenance-heavy. And don't get us started on applying for Google Drive API keys: That can take months and costs ~$30k.

Interpretation is what's tricky. A naive embed + vector DB sounds compellingly easy but rarely works well for production-sized datasets. (If it does work for you, please reach out!) Despite what "Big Vector DB" is telling you, there is a lot of engineering and NLP that's needed: Recognize entities, model relationships, give it temporal awareness, filter the fluff, handle multimodal data, augment data with questions and summaries – I could go on. You must choose (& deploy) a language model for each of these tasks. And have you considered that the data distribution for Powerpoints is slightly but perniciously different than PDFs? Go directly to jail; do not pass "go."

Oh, and have you thought about compliance?

Solution: Integrate all your customer's data in an afternoon with SID

SID makes it easy for developers to connect LLM apps to their customer's data. We offer developers a button that lets people link their data and lets devs query our API to ask questions about that person or their company. That's it.

We take care of the ingestion, interpretation, and storage of the entire customer data stack – so devs don't need to think about vector DBs, maintaining infrastructure, or Google's API oddities. We self-host all LLMs used for analysis to ensure privacy – critical for customers. We've already served over a million API calls and average <200ms response times.

We've lived through the pain and built SID so future devs don't have to. We're starting with the most popular integrations and are adding new ones fast – at no extra cost to our customers. Please reach out if there's anything specific you need.

🇨🇭PS: We're Swiss, so we know how to keep your information secret.

The Team

We love being the odd ones: Lotte can fly a plane but can't drive a car, Georgijs still swears by Vim and built his own compiler at MIT, Lukas goes from idea to product faster than anyone the author knows, and Max is a researcher at heart who won't stop digging until he finds the truth – or people stop talking to him.

Asks: Please introduce us to AI teams!

  • If you know someone building AI apps or planning to add AI to their company, please refer us (m@sid.ai)! We save most customers months in engineering time.
  • Try out our demo with your own Google Drive and Notion at demo.sid.ai – if you find something cool, email or tweet at us.
  • Support our launches on Twitter and follow the team (linked above)
  • Star our repo on Github