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 Agent SDK is now available.
Define agents as code, with prompts in Markdown and tools in TypeScript. Deploy them on our hosted infrastructure, or run them on your own.
Built-in evals let you measure every change and make your agents better over time.
1000% agree w/ Claire here, CC Projects is software factory for the rest of us.
Our team's merged PRs and releases have gone thru the roof.
Proves that UX still matters (maybe more than ever).
Plot twist: I’ve moved 80% of my personal coding over to claude code + opus-5.5
why?
- cc projects is goated
- I can’t press “steer” anymore in codex
- code is good?
- less front end slop
but tbh: opus 5.5 creative abilities was the gateway drug to taking back my coding work
👀 we’ve been quietly working on something new for Supabase teams: day one observability.
@supabase native. One click set up. Easy for your team to reach for, and even easier for your agents 🤖
Tell us what you’re building for early access👇
MCP analytics is the new web analytics.
We made ours public, and built a leaderboard of the most popular models, harnesses, tools, and more we see at PostHog.
Here's what it shows:
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!
⚡ @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...
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…
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!
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
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.
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.