/ blog

PostgresEDI July 2026 Meetup — Public Speaking, AI Compliance

Actual sunshine ☀️ in Edinburgh 😲 and a room full of Postgres people catching up over pizza: July was good to us. 🐘

Highlights from the PostgresEDI July 2026 meetup

Thursday, July 9th brought us to Paterson's Land at the University of Edinburgh, and to a wonderfully diverse pair of talks: one on finding your voice in the community, and one on building auditable AI systems on Postgres. Thanks to everyone who came along, to our two excellent speakers, to my co-organisers Jim Gardner and Denys Rybalchenko, and to pgEdge for kindly sponsoring the pizza and refreshments.

For those who couldn't make it, or for those who want to revisit the details, here is a recap of the talks with slides.

The Talks

Speaking and Community Involvement for the Introvert

Pat Wright (Redgate)

Pat Wright in front of his title slide Pat Wright, ready to talk about speaking

Pat, a PostgreSQL Advocate at Redgate, kicked off the evening by making the case that technical skills alone aren't enough: speaking and community involvement can set you apart in your career, even if you're an introvert. All it takes is passion for your topic and "20 seconds of courage".

Pat Wright presenting his abstract submission tips Pat sharing his tips for conference abstract submissions

He walked us through the whole journey with refreshingly practical advice: writing an abstract that gets accepted, rehearsing to an empty room before presenting to others, testing demos relentlessly (and having a backup), and learning to "pause the introvert" on the day. His parting challenge for everyone: meet three new people at your next event.

📊 View the slides: Speaking and Community Involvement for the Introvert (PDF)

One Engine, One Audit Trail: Traceable, SQL-First Retrieval for Compliance-Critical Systems

Martins Otun (Algonix AI)

Martins Otun presenting his title slide Martins Otun introducing SQL-first retrieval for compliance-critical AI

Taking the stage next, Martins, Founder & Principal AI Engineer at Algonix AI, showed us how to build AI retrieval systems for regulated industries using PostgreSQL and pgvector, where auditability and compliance aren't an afterthought but a core part of the architecture. His framing scenario: an AI approves a £3M loan, and six months later the regulator asks "why?". Which documents, which embedding model, which chunk, and can you reproduce it today? Most vector databases can't answer, because they optimise for relevance, and "relevance is not evidence".

Martins Otun explaining the consequences of splitting the stack The three consequences of splitting the stack

His answer: keep vectors, permissions, document versions, and the audit trail all inside Postgres. Every retrieval writes its audit record within the same transaction, row-level security enforces access, and any answer can be reconstructed months later. One engine, one audit trail.

The core argument: your vector store should not be separate from your system of record The core argument of the talk

📊 View the slides: One Engine, One Audit Trail: Traceable, SQL-First Retrieval for Compliance-Critical Systems (PDF)

The audience at the PostgresEDI July 2026 meetup Audience at the PostgresEDI July 2026 meetup

Once the questions for Martins wrapped up, we moved the conversation over to The Canons' Gait, where it carried on well into the evening.

Obligatory post-meetup photo Obligatory post-meetup photo

What's Next?

Our next meetup is on Thursday, August 13th.

Register here: 👇

We are always looking for speakers, and we are eager to hear your stories! If you have an idea for a talk, please drop me an email at vyruss000 (at) gmail.com.

Make sure you are following us for updates:

Thanks again to Pat and Martins for two excellent talks, and to the University of Edinburgh for hosting us. See you on August 13th! 🍕