cevian
ceviantech.bsky.social
cevian
@ceviantech.bsky.social
Tech lead for pgai, pgvectorscale, and all other AI things @ Timescale.

Postgres rocks!
or try our brand-freaking-new free services:

```
curl -fsSL cli.tigerdata.com | sh
tiger auth login
tiger mcp install

```
October 22, 2025 at 5:49 PM
We're releasing it today. Works with Claude Desktop, Cursor, Windsurf, VS Code. Open source with a free hosted service.

www.tigerdata.com/blog/free-po...
How to Train Your Agent to Be a Postgres Expert | TigerData
Turn AI into a Postgres expert with our MCP server. Get 35 years of best practices, versioned docs, and prompt templates for production-ready schemas.
www.tigerdata.com
October 22, 2025 at 5:49 PM
Instead of thin API wrappers, we teach AI things like "Always index foreign key columns - Postgres won't do it for you" and "Use BIGINT GENERATED ALWAYS AS IDENTITY, not SERIAL."
October 22, 2025 at 5:49 PM
Last week @anthropic.com announced Skills - turning generalist LLMs into domain experts through structured knowledge. Different implementation, same philosophy. (Our approach might show how to implement Skills entirely through MCP 🤔)
October 22, 2025 at 5:49 PM
That's where our get_prompt_template MCP tool comes in. Ask "design a schema for IoT devices" in plain language. The AI automatically pulls in the right Postgres expertise. No slash commands, no template picking.
October 22, 2025 at 5:49 PM
The fix isn't obvious. I hate the copy-paste prompting I see in the wild. MCP prompt templates bother me too - why should users need slash commands? Isn't the AI supposed to figure this out?
October 22, 2025 at 5:49 PM
AI coding should make this better. Instead, it's making things worse. Every "AI-generated" schema has the same issues: wrong ID types, missing indexes, timezone nightmares. Infuriating.
October 22, 2025 at 5:49 PM
I've spent 10 years at Timescale (now TigerData) watching devs make the same database mistakes: forgetting to index foreign keys, case-sensitive email lookups, arbitrary VARCHAR limits. The pain of botched migrations and downtime is real.
October 22, 2025 at 5:49 PM
github.com
August 21, 2025 at 8:36 PM
They just access the database and expect it to have the context.

But most databases can’t explain themselves. And that’s the core problem.

So we built a semantic catalog on top of Postgres. It added context inside the database. SQL accuracy improved by 27%.
August 21, 2025 at 8:36 PM
China is over 2 million with "administrative detentions", as I specified in my post.
July 17, 2025 at 3:42 PM
Of course we also have a smaller prison population than China www.prisonstudies.org/country/china If you count "administrative detentions"
China | World Prison Brief
www.prisonstudies.org
July 17, 2025 at 2:47 PM
US prison population (biggest estimate, way more than actual): 2 million
world population: 8 billion
tell me how that's 5%?

Learn some math.
July 17, 2025 at 2:41 PM
That's because Stalin killed *millions* of people he sent to the Gulag. You point is so stupid, it's painful.
July 17, 2025 at 2:29 PM
Imagine not knowing Iran has a history of forcing gender reassignment on gay people
June 19, 2025 at 7:31 PM
Why can’t a gay man have a loving family you homophobe?
May 15, 2025 at 11:18 PM
He is in no way a nazi but you are foul for making the word nazi meaningless in an age where real Nazis are gaining power
May 15, 2025 at 11:07 PM
Best of all, my team is actively exploring this new direction. We think it’s the future. 🚀

#AI #PostgreSQL #DataIntegration #Innovation
May 1, 2025 at 3:14 PM