Data Formulator
AI
data analysis agent
SHOW HN2025
38points
13comments
#1,472of 3,837 in 2025
Top 39%of 2025 by points
How HN took it
QuietFewer than 5 comments about the project
2 positive, 0 neutral or asking, 1 mixed, 1 critical, out of 4 comments about the project.
Docs: 0 for, 1 againstIdea: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Local install option is appealing
From 1 comment
Pretty cool. I like the local install option. I almost skipped this as more AI wrapper shovelware. Would benefit from putting "Microsoft" in the title.
xnx on HN
Well thought out features
From 1 comment
Very cool - a lot of well thought out stuff in there. One area for exploration is letting people turn natural language questions into non-LLM queries, UIs, & dashboards. In other…
cadamsdotcom on HN
Objections
Looks like AI wrapper shovelware at first glance
From 1 comment
Pretty cool. I like the local install option. I almost skipped this as more AI wrapper shovelware. Would benefit from putting "Microsoft" in the title.
xnx on HN
Database connector documentation was hard to find
From 1 comment
There are references to using connectors to connect to databases, but I can't find any documentation on how to actually do that.
jaxn on HN
Requests
Put Microsoft in the title
From 1 comment
Pretty cool. I like the local install option. I almost skipped this as more AI wrapper shovelware. Would benefit from putting "Microsoft" in the title.
xnx on HN
Support turning natural language questions into deterministic queries and dashboards
From 1 comment
Very cool - a lot of well thought out stuff in there. One area for exploration is letting people turn natural language questions into non-LLM queries, UIs, & dashboards. In other…
cadamsdotcom on HN
Questions
How to connect to databases
From 1 comment
There are references to using connectors to connect to databases, but I can't find any documentation on how to actually do that.
jaxn on HN
Alternatives named
Zenquery
From 1 comment
Lol... this is exactly what my product does: https://zenquery.app
freakynit on HN
Definite semantic layer approach
From 1 comment
This was too perfect of a setup, had to record a video[0] showing how we do this. Yes, you definitely need need for a codification layer. I think a semantic layer is the best way…
mritchie712 on HN