Show HN: Acolyte – Query your data warehouse in plain English | Hacker News Reader

Show HN: Acolyte – Query your data warehouse in plain English

acolytehq.com

6 pointsmjirv9 comments

Hi all,

I've spent the past 4 years working as a data analyst and analytics engineer. One of the biggest pain points for analysts is that, even with tools like Looker and Tableau, they still spend a ton of time answering fairly simple questions from less-technical users instead of doing high-value analytics.

Often as a data analyst I've felt like a computer translating requests from English into SQL. That got me wondering - could an actual computer do it instead?

For a while, I thought the answer was "no" (or at least not in the near future). But then OpenAI's Codex[0] was released. I started using GitHub Copilot[1] every day while writing SQL in Visual Studio, and it felt like magic. The autocomplete was getting my code right a lot of the time, even for complex SQL queries.

So I decided I'd give this a go. I've built a demo using the Codex API and dbt Labs's "Jaffle Shop" example database, which will be familiar to many in the Analytics Engineering community. It's a simple database, but the results are promising. The demo app gets a lot of queries right, and it does so without any database-specific logic.

The only input needed is a schema.yml file describing the tables and columns (which any dbt project would have) and 2 or 3 example queries, so I am hoping to open up testing to more data warehouses and users in the near future.

I hope you enjoy using the demo. If you have any feedback, ideas, or would like to test it out on your own data warehouse, my email is in my bio!

[0] https://openai.com/blog/openai-codex/ [1] https://copilot.github.com/

Tried the demo - it seems it doesn't recognize names (values) yet, for example "howard sum amount" leads to simply 'SELECT sum(amount) FROM orders'.

Our SeekTable has similar function where values could be matched too -- but instead of SQL result is a report configuration: https://www.seektable.com/help/search-driven-analytics

Interesting that on practice this function is rarely used by end-users, and because of this we didn't evolve this function.

Ah yeah that’s a good example of something it can’t do well. Right now you have to give more context, e.g. “How many orders were placed by someone named Howard?” works for me.

Thanks for sharing about Seektable. Neat that you’ve already built out a search function, and even aside from that it looks like a really interesting tool.

great job. it works seamlessly. I like the fact that you show the underlying sql so that we know if it is wrong and edit it if needed. Some other tools just don't show you how the magic is made and you cannot be 100% certain if data result is correct

Thanks, I really appreciate that feedback!

For those having trouble with the URL, you can also use http://acolytehq.com

How do you expect this to impact the job market for software engineers or database administrators?

Interesting question. If this succeeded beyond my wildest dreams I’d expect the main impact to be on data analysts and freeing up their time to be spent on more in-depth projects rather than one-off requests.

In general I suspect AI tools like Codex will have a large impact on other technical roles like SWEs and DBAs, but I won’t try to predict exactly what that will look like.

I see the jaffle shop example has made it's way out of DBT ;)

Reply on news.ycombinator.com