It'd be nice if it also included the queries for each use case, and had a better understanding of sharding. As is, I gave it a bunch of requirements, it created some tables. Was it sufficient? No idea, it didn't say what the query was for each requirement. Would it scale? Again, no idea without the queries. (But actually, no, it wouldn't have scaled; some requirements were impossible without cross-shard scans).
Show HN: ChartDB Agent – Cursor for DB schema design
21–30 of 37 posts
Re: Show HN: ChartDB Agent – Cursor for DB schema design
#22"an open-source tool" --> https://github.com/chartdb/chartdb ( AGPL-3.0 license ) prompts: https://github.com/chartdb/chartdb/blob/c3c646bf7cbb1328f4b2...
These are all easily testable in Docker containers. There's a concerning lack of attention to detail here, or perhaps the prompt itself was also created using AI and it bakes in hallucinations from the get-go.
As for the AGPL: in ChartDB's previous Show HN (only 6 weeks ago), I asked how they were running an enhanced paid SaaS when they had so many external contributions prior to adopting a CLA, and I did not receive a response [1].
Re: Show HN: ChartDB Agent – Cursor for DB schema design
#23Re: Show HN: ChartDB Agent – Cursor for DB schema design
#24what makes this an "agent"
Re: Show HN: ChartDB Agent – Cursor for DB schema design
#25Re: Show HN: ChartDB Agent – Cursor for DB schema design
#26I can prompt an LLM to make a mermaid diagram and iterate on it. Why do I need "ChartDB"?
I'd gonna go one step further and argue that you don't even need mermaid for creating DB schemas.. direct chat works fairly well for reference.
Re: Show HN: ChartDB Agent – Cursor for DB schema design
#27It'd be nice if it also included the queries for each use case, and had a better understanding of sharding. As is, I gave it a bunch of requirements, it created some tables. Was it sufficient? No idea, it didn't say what the query was for each requirement. Would it scale? Again, no idea without the queries. (But actually, no, it wouldn't have scaled; some requirements were impossible without cross-shard scans).
99% of apps never need to shard data. Probably closer to 99.9% if they are single tenant.
Either way, working around sharding and scale seems like a place where a good AI could help provide recommendations and tradeoffs, so it's disappointing that the model doesn't seem to deal with it well. For basic relational schema design, I don't see much benefit of having AI.
Re: Show HN: ChartDB Agent – Cursor for DB schema design
#28Re: Show HN: ChartDB Agent – Cursor for DB schema design
#29"an open-source tool" --> https://github.com/chartdb/chartdb ( AGPL-3.0 license ) prompts: https://github.com/chartdb/chartdb/blob/c3c646bf7cbb1328f4b2...
At quick glance I already see several things in that prompt are completely incorrect. For example: MariaDB has natively supported sequences for quite some time; for decades all versions of MySQL/MariaDB support "bool" or "boolean" as an alias; the timestamp default value advice is wrong as any arbitrary expression can be used; etc. These are all easily testable in Docker containers. There's a concerning lack of atten…
I choose to believe that it's a brilliant feint. The author will run all these comments back into their LLM to generate fixes for all of these issues.