Pinned Tweet
We're all seeing the benefits of a software factory for agents, but what about data?
There are huge gains in providing agents a data factory with the same types of quality loops and processes to refine raw data into usable business metrics and knowledge.
The bar was really raised at @Supabase Select '26, can't wait until next year.
⚡ @Supabase Select was a freaking blast! The whole @DreambaseAI team came out for the first Partner Day to feed our agents straight from the product team.
A few additional favorite moments in no particular order...
Kyle Ledbetter retweeted
The @DreambaseAI team tested their AI agent pipeline on Supabase Compute and saw faster and cheaper results!
Read the full story here: dreambase.com/blog/running-o…
The new @supabase Compute is awesome. We moved our @DreambaseAI data agent onto it during the private alpha, and answers came back 1.7x faster at 4.7x lower model cost.
Full write-up: dreambase.com/blog/running-o…
Killer upgrade for supabase dev in your software factory
Declarative schemas in the Supabase CLI have a new diff engine. The migrations it generates now cover RLS policy changes, grants, views, and partitions.
Learn more ↓
supabase.com/blog/declarativ…
Claude Dashboards and Claude Motion rock.
We gave it access to our product analytics via a single MCP and Claude built this fun interactive infographic storybook for our team.
All you need is a reliable agentic data platform and this thing can cook.
Also really fun to see @nateparrott demoing these features after following his journey from Arc->Anthropic.
💀 Dashboards are dead!
🏥 Long live Dashboards!
Return of the King
Absolutely huge day today—Bootstrap 6 Alpha 1 has arrived! Refreshed design, updated docs, new components, new Sass/CSS approach, more modern frontend stack, updated tooling. getbootstrap.com
Don't tell anyone, but we hacked the fancy @supabase Select badges and loaded our own Dreambase Invaders game 🤫👾
Saw some incredible new features being announced at @supabase Select today! ✨✨
Proud to have the @DreambaseAI team at the @supabase Partners day to kick off Supabase Select 💪⚡️
We're testing the Data Factory with users now and really excited about how it visualizes the data refinement process.
Seeing your data sources joined into dataset cubes ready for agents to query with DuckDB, and refined into business KPIs and metrics is quite empowering.
Dots are fun! Glad we were on top of this trend and created our Dreambase data "bytes" mascot 👾
Dots are here!
A new way to use AI that works 24/7 for you; get more of your time and attention back to work at a higher level.
openai.com/index/introducing…
Gotta feed them agents! 👾👾👾
So stoked to share more at Supabase Select on Friday.
👾 FEED YOUR AGENTS!
Agents operate at S-tier when fed a balanced diet of data. Feed them raw data only and you'll bloat their context window, upset their tummies, and give them brain fog.
🤔 "Is this really accurate or does it just sound right?"
We refine and enrich your data to cut the bloat and anchor your agents in data you can trust.
The whole team is in SF this week and we'll be sharing a lot more at @Supabase Select. Who else is going to be there? 👋
Loving the breadcrumbs of the new brand and can't wait to show the full thing!
The speed of structured decision making models like Jev is radically improving performance and economics both inside and outside our product.
Exponential speed boosts and savings.
Everyone's building features with Jev. For @dreambaseAI we pointed it at our own dev process instead.
Result: every PR checked against our written architecture standards. One hour on our two biggest PRs: 427 requests, 26 cents, 1.3 s median per report.
