Introducing → Rubric Labs
We're an applied AI lab. We build ambitious AI products.
Our team has worked with leading-edge companies like Gumloop and Graphite to help bring practical AI applications to market.
We sat down to talk about our process.
What is polish? When we improve a feature, are we flexing intelligence or exercising sustained attention?
We tested whether a critique-improve loop closes the gap between "it works" and "it's good". Across our experiments, the answer is yes.
New post: rubriclabs.com/blog/autonomo…
@nvidia is joining us as a sponsor along with @redwood_ai , @RubricLabs and @rootlyhq !
a special thanks to all our sponsors for the week-long AI safety (control) hackathon, launching this Thursday both irl in Montreal and online
signups still open, details in thread!
Text the system. Get software. Test and repeat.
We recently ran an in-person experiment where users could text a number to get an OpenClaw instance, complete with a computer and a subdomain.
The system itself was managed by an OpenClaw, too.
Read more: rubriclabs.com/blog/openclaw…
New Post: Contract Engineering
AI agents ship broken software. Tests pass, the app deploys, and it’s still wrong.
We’ve been writing contracts: Requiring proof that every event fires in order for every use case.
Once all contracts are filled it ships. rubriclabs.com/blog/contract…
Big news: SpendHQ has acquired Sligo AI
We’re proud to have partnered with Sligo through an important part of the journey, and excited to see what the two teams build together.
Congratulations to everyone involved.
rubriclabs.com/blog/sligo-pr…
New post: Unblocking Agents
Agents are capable of building great software. What stops them: permissions, credentials, infrastructure, and identity.
We stood up a parallel org called Rubrot and gave agents admin permissions, hardware and credit cards. rubriclabs.com/blog/unblocki…
New post: Primitives over Pipelines
The AI systems most teams are shipping today were designed for dumber models. Now that frontier intelligence can follow instructions, reason, and self-correct the move is to give agents primitives and let them cook.
rubriclabs.com/blog/primitiv…
Working closely with Gumloop's design and engineering teams, we had a rare glimpse into how this Series A company stays nimble at scale.
We share in their instinct to ship fast.
Orgs are rich with systems. LLMs are naive.
Structured Outputs guarantee the shape of an LLM's output, letting them plug into existing infrastructure.
Where vibe-coding tools top out, structure is needed to keep scaling.
At Rubric, we're pushing structured outputs to their limit to generate full-stack apps in a fundamentally safer way.
Follow everything we do here:
github.com/rubriclab/
Introducing → Rubric Labs
We're an applied AI lab. We build ambitious AI products.
Our team has worked with leading-edge companies like Gumloop and Graphite to help bring practical AI applications to market.
We sat down to talk about our process.
The next generation of software is going to be flexible, personalized and powerful.
We’re building a lean team that can experiment while also having the persistence to get to production.
Read more about our process here: rubriclabs.com/blog/introduc…