Text To SQL
topic on 4 shows · 4 statements across 4 episodes
the Knowledge Project 
Latent Space 
the Official SaaStr Podcast 
the MAD Podcast
4 statements about Text To SQL, every show
Tavakoli: Text-to-SQL fails in BI without deep semantic data understanding
“I think the hard part for the standalone BI tools was they historically really had no semantic understanding of the data, right?
You didn't extract of a data warehouse.
They stood there.
And when they tried to add talk to data, it was mainly just, let me conve…”
Frankle: Text-to-SQL is one of the most impactful LLM use cases for enterprise
“Like it's, you know, text to SQL is still, or like having a model be able to make SQL calls in the backend is actually like one of the single most useful things for my customers. It sounds really boring. Models are really good at it and it moves the needle day…”
Incumbents will dominate text-to-SQL, making it a bad startup problem
“The bigger companies, like Databricks or Snowflake might build these tools and offer it on their sequel editor or, like, some kind of, like, you know, assistant And that could probably solve the problem. It's not a great problem for a startup to work on.”
Text-to-SQL is table stakes and largely better than traditional dashboards
“Now the whole text to SQL has become, you know, table stakes. I mean, you can interrogate, you know you know, Salesforce data on Snowflake, you know, what just text to SQL. And it's really nice by the way. I mean, hell, it's all a lot better than using dashboa…”