The alpha, twice a week
That was 3 min.
Get the best new moments in your inbox every Wednesday and Saturday. It's free.
Check your inbox
We sent a link to your address. Click it to finish signing up. Not there in a minute? Look in spam.
or
Lightcone · 3 min · Oct 30, 2026
Supabase makes errors actionable for coding agents
Supabase rewrites error messages to tell agents how to recover and where to find help.
In this episode
Full episode- 9:55AI makes a personal database useful to everyonePro pick 7 min
- 32:18Agent memory turns into a retrieval problemPro pick 6 min
- 19:55Supabase moved from dashboards to code as agents arrived3 min
- 23:31Supabase wants to win startups on day one and scale with them3 min
- 29:42Supabase makes errors actionable for coding agents3 min
- 17:53Supabase lets engineers choose their AI tools2 min
- 43:21Small SaaS teams can make fundraising optional2 min
- 45:25Supabase uses dogfooding and team capacity to adapt3 min
“inside the error messages, you are literally telling them how to fix this error”
Takeaways
- Error messages can explain how an agent can fix a problem.
- Improve error guidance around your product’s common use cases.
- Evaluate models and invest in testing where agents struggle.
About this segment
Supabase rewrites error messages to tell agents how to recover and where to find help. It also evaluates models on specific use cases, shifting engineering effort toward testing.
Paul Copplestone is cofounder and CEO of Supabase.
Garry Tan, Host · President & CEO, Y Combinator
Co-founded Posterous and Initialized Capital, an early Coinbase backer.
Harj Taggar, Host · Managing partner, Y Combinator
Co-founded Auctomatic with the Collison brothers and later Triplebyte.
Diana Hu, Host · Managing partner, Y Combinator
CTO of Escher Reality; after Niantic bought it, ran AR for Pokémon GO.
Jared Friedman, Host · Managing partner, Y Combinator
Co-founded Scribd, which YC funded in 2006; has advised 20+ YC unicorns.
From “Why Everyone Is About To Have Their Own Database”, Oct 30, 2026. Watch the full episode
Thanks. We'll look at and fix what's off.
Transcript
Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.
- 29:46
things that you've been doing that like really make agents like you better like error messages is you know you know what was that key insight and like are there a bunch of other things that you're doing that kind of obvious on the one hand on the other hand like nobody's doing yet yeah so like the error messages yeah i was at a dev tungst in a fast night and i was surprised that this wasn't so obvious but we really dug into our error messages so that you can take a use case like oh i want to build an application and generally like developer tung error messages at like 500 something basic and you just know there's a problem.
- 30:23
But now you actually want the agents to like remedy themselves. So inside the error messages, you are literally telling them how to fix this error or to go and read some docs to fix the error. So a lot of it is just picking your use case and just trying to do these loops on improving your own error messages so that you can one-shot basically anything that you want. Yeah, that makes sense. basically you know if you're being used by an agent the agent will encounter an error message in the past a human would have to go google that and do a bunch of stuff but here you can just say oh like you're just you know out of inodes so you should probably go do this yeah because there's like two stages to winning the agents the first is being picked by the model and then the second is like if they get stuck you don't want them to switch away so guaranteed they'll get stuck
- 31:15
at some point you just want to give them the tools to to remedy so it's not actually that complicated they're smart enough now that they can figure out a lot of stuff but you do have to re-engineer a lot of what previously was just for humans and developers for agents do you test your project your product for agents like do you have agents like try to use super base and then like report all the places where they had trouble yeah yeah yeah all the different models we've got an evals website where we see which models are building the best and we've got our own eval suite internally we eval as well which ones are best just with postgres so that's interesting for the industry and build skills around it so that they can adopt them and actually develop with postgres so yeah it's a lot of testing and in fact pretty much now a lot of our engineering effort is going into
- 32:06
like testing specific use cases rather than the building we want to think through how people are