Home
Companies
Dataherald

Dataherald

Embed NL-to-SQL into your Product 📈

Dataherald enables you to embed Natural Language to SQL (“NL-to-SQL” or "Text-to-SQL") into your product. The NL-to-SQL API, built with an LLM, allows your users to conduct no-code data analytics, pull reports, get answers to data questions, and conduct complex data queries using just natural language.

Dataherald
Founded:2020
Team Size:10
Location:Los Angeles, CA

Active Founders

Anuj Saigal

Prior to Dataherald, I led Revenue Ops at Nauto, an AI company focused on the transportation industry. I also held roles in cleantech and finance: GM at EVgo (EV fast charging), SunEdison, the Dept of Energy, and JPMorgan.

Anuj Saigal
Anuj Saigal
Dataherald

Amir Zohrenejad

CTO/Co-Founder of Dataherald. Prior to Dataherald, Amir worked as a PM at Microsoft, founded a mobile messaging startup and led his family business. He studied EECS and Applied Mathematics at UC Berkeley.

Amir Zohrenejad
Amir Zohrenejad
Dataherald

Company Launches

TL;DR

Dataherald enables you to embed Natural Language to SQL (“NL-to-SQL”) into your product. The NL-to-SQL API, built with an LLM (such as GPT), allows users to conduct no-code data analytics, pull reports, and conduct complex data queries using just natural language.

Hi, we’re Amir and Anuj from Dataherald. There have been countless game-changing applications of AI, but one area that has remained uncharted is NL-to-SQL. But fear not - we’re changing that. We’ve built a cutting-edge NL-to-SQL engine, meticulously crafted to be the fastest and most accurate in the market, delivering an unmatched developer experience!

The Problem

Developers struggle to build NL-to-SQL into products because LLMs do not work out-of-the-box. LLMs do not:

  1. Utilize metadata and business definitions since they are not already stored in the relational database
  2. Conduct complex SQL queries, such as self joins, multiple sub-queries, or rarer operations like windowing, partitioning, lags, temporal calculations, etc.
  3. Create NL-to-SQL training dataset(s) for fine-tuned models
  4. Assess the accuracy of AI-generated SQL

The Solution

Dataherald’s API solves these challenges by allowing developers to:

  • Add business context from various sources (data dictionaries, DBT, Confluence docs, Google docs, etc.)

  • Identify relevant data tables
  • Fine-tune NL-to-SQL LLMs (including GPT-4!) specific to their data
  • Assess confidence levels in AI-generated SQL

All this happens with a few simple API calls.

Dataherald’s NL-to-SQL API unlocks data access wherever needed:

  1. Enabling Complex Data Queries in SaaS Apps: For example a large payroll software company uses Dataherald to embed NL-to-SQL into their front end so that users can ask questions like “How much did I spend on full stack engineers in our European offices in Q2 2023 and how is that trending?”
  2. Democratizing Data Insights: Companies integrate our API into Slack, enabling self-serve data requests, and freeing up valuable time for data analysts.
  3. Automate Customer Support with Chatbots: Customer support teams dealing with data-heavy queries leverage Dataherald in chatbots, automating inquiries regarding user data.

The ASK

  • Start using today - send me an email anuj@dataherald.com to get your API key and start using it today!
  • Share - tell your colleagues and friends about Dataherald
  • YC Companies - skip the wait list and claim the YC deal
  • Open-source engine is available on Github

Other Company Launches

🚀 Dataherald - Query your structured database in natural language

Enable anyone to get answers to ad hoc data questions in seconds – no SQL needed
Read Launch ›