Denver devs, come stop by Mile High Demo Night on Nov 12th at ID345! Putting this on with @cipherstash, @supabase and @DreambaseAI. 3 live demos, food and drinks.
Building something? Come demo it 😎
4 days until @Supabase stops auto-exposing new public tables to the Data API.
If you're using supabase-js/ssr in your app, make sure you grant access and set up permissions correctly with RLS!
If your agent recommends anything like: "grant to anon, disable RLS"... please don't do it 😅
@supabase Make sure you're using Dreambase to stay on top of your Supabase health & observability with our free assessments & alerts:
https://t.co/5nCwnouHhu
Denver devs, come stop by Mile High Demo Night on Nov 12th at ID345! Putting this on with @cipherstash, @supabase and @DreambaseAI. 3 live demos, food and drinks.
Building something? Come demo it 😎
Your Agentic Data Team just got an upgrade 👾👾👾
- Smarter orchestration across data specialist agents
- Metrics as first-class citizens, no longer requiring dashboards
- Semantic Layer improvements for API and MCP connectors
Rolling out now!
⚡ Happy Friday! Fun milestone for @DreambaseAI this week: we crossed 1,000 workspaces.
With our new @Supabase partnership and our Observability release dropping next week, I have a feeling we'll double that before the end of the year.
What a time to be building! 📈
⚡ @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...
We moved our data agent onto @supabase Compute in the private alpha: 1.7x faster answers at 4.7x lower model cost. Hat tip to @laktek for the help!
Huge work from @dreambase_jc on the deep dive. Shoutout to the rest of the crew too: @alwaysunday@kyleledbetter@edmoralesb
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: https://t.co/P4X7z7DTUU
Holy sh*t, the new Supabase Compute is fast 💨 and you're gonna love it.
We ran some quick evals with early access (thanks @mattjohnstondev & @laktek) and the results are really promising.
💰 6.7x cheaper to run at ~$.05 per question (Woz's favorite) instead of our current $.36. That's roughly $500 for 10,000 questions vs the current $3,600.
With Compute, we're seeing 2.3x faster answers before we've started to optimize. And a bonus of 17x fewer tokens used. We like that.
@dreambase_jc is putting together a deeper dive early next week, and we'll be rolling it into @dreambaseAI right away. Anyone else tried it out yet?
T-minus 1 day until @Supabase Select ⚡
Here's a quick teaser for our Happy Hour invites, aka your cure for "Vibe Analytics" 😆
Find me or anyone on the @dreambaseAI Team and join us Friday night for a drink or three 🍻
Oh, and we built a fun lil' site too. See y'all sooooon!
🔗 https://t.co/l23buXY63K
👾 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!
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.