Quotient AI

Databricks launches data engineering copilot and acquires agent evaluation startup ift.tt/YuLKGBE

Quotient AI was founded in 2023 by the engineers who led quality improvement for GitHub Copilot. The company was acquired today by Databricks, the San Francisco-based data analytics software company that raised $1.8 billion in additional debt this January. bizjournals.com/boston/news/20…

The news is out: @QuotientAI is joining @databricks! I'm so excited to work with @julianeagu and @freddiev4 on inventing the future of AI evals for enterprises.

Here we go! very excited to work with all of the great people at Databricks and make the best agents for data work in the industry I’ve been extremely impressed with everyone we’ve met, and there’s been amazing work shipped just in the last week (KARL, OfficeQA Pro, Genie Code…).

Databricks is acquiring Quotient AI to strengthen the agent evaluation and reinforcement learning capabilities in Genie, Genie Code, and Agent Bricks so customers get more reliable AI agents in production. Databricks already provides powerful tools for evaluating and improving AI agents. With Quotient, we're strengthening these capabilities across our platform with a continuous evaluation and improvement layer that monitors agent behavior in production, catches issues like hallucinations and broken reasoning before users do, and uses those signals to continuously improve performance over time. We're excited to welcome the Quotient AI team to Databricks as we continue building the most reliable platform for developing, deploying, and improving agentic systems at scale! databricks.com/blog/databrick…

Quotient is joining @databricks! @freddiev4 and myself started @QuotientAI in 2023 with a dream and a hunch that the next era of AI will be unlocked by systems that can measure, evaluate, and improve AI in the real world. Over the past couple of years, we partnered with companies ranging from AI-first startups to Fortune 500 enterprises. They used Quotient to monitor AI systems in production, ensure their agents met strict enterprise policies, and reinforcement fine-tune agents to consistently achieve double-digit performance gains. We built it all at the bleeding edge, with a small team that started in Boston, Massachusetts. Joining Databricks gives us the scale and resources to take this much, much further. Very grateful to our team, investors, customers, and everyone who supported us along the way. We couldn’t be more excited for what’s next. Onwards!

Great talk last night by @julianeagu (@QuotientAI), @thejackobrien (Subconscious), and @petecheslock (Red Hat)! LLMs as we know it today must change to meet the capacity we expect of them. Specialized agents, changing their hardware architecture, or funneling proper context!!

@julianeagu @QuotientAI Everyone who registers gets the recording + notes: maven.com/p/0516fe/how-t…

An agent that works in testing can still fall apart in production, and all the failures happen in the tool calls you aren’t watching. Next Tuesday (Nov 25 @ 2pm ET), @julianeagu (@QuotientAI) is dropping by to walk through how to catch these before they hit production. In this session she’ll cover: - Spotting when agents call the wrong tools or pass bad parameters - Using limbic-tool-use to evaluate tool accuracy at scale - Real-time tracing with Quotient MCP to debug what’s actually happening Julia led data at GitHub Copilot. Now she’s Co‑founder & CEO of Quotient AI, building the monitoring layer for production agents. You won’t want to miss this. Link below to sign up.

Doing a course with @jxnlco on Nov 25th! We’ll walk you through how to detect silent failures in agent-tool interactions, debug tool usage, and scale reliability in production. If you’re working on AI agents and want to go beyond “makes sense” to “actually works at scale”, this one’s for you.

@julianeagu @QuotientAI Nov 25: maven.com/p/0516fe/how-t…

Two sessions closing out November on the real failure modes of production agents: silent tool-call errors and multi-turn deployment drift. Tuesday, Nov 25 @ 2pm ET: How to Catch Tool-Call Errors in AI Agents with @julianeagu (@QuotientAI) Most agent failures happen quietly. Wrong tool. Bad parameters. No warning. Julia breaks down how limbic-tool-use and Quotient MCP surface these errors in production and how to trace, evaluate, and fix tool-use accuracy at scale. Wednesday, Nov 26 @ 1pm ET: Shipping an Agent: Lessons from LangChain’s Own Deployment with @AnikaSomaia (@langchain) What it actually took to run LangChain’s Insights Agent in production. Multi-turn evals that catch regressions early, debugging memory and context drift, and building feedback loops that keep agents stable over time. If your agents are headed for production, you’ll want these patterns in your toolkit. Link below.

Join us next week for AI Builders Night an informal demo + networking night with some of Boston’s top AI builders and practitioners. 🍕🥂 Food + drink provided.

“Ship and ship sooner than you feel you're ready. You'll learn so much more from your agent being in production than you ever could in dev.” - @julianeagu, Quotient AI Julia shared why real-world deployment is your best teacher for AI agents.

can every AI agent get better, and better, and better.. automatically? humans learn from their environments, so why wouldn't agents? nurture is built in production shared a first glimpse of what's possible @lisbonai_

LisbonAI has just started Broadcast here x.com/i/broadcasts/1…

jet lagged and about to demo some never seen before alpha we *just* cooked

We obsess over structure. Every pattern we uncover in chaos unlocks new potential.

RT @julianeagu: AI products today are shipped on intuition, a sense of what feels right more than what’s been measured. Production is a w…

Qdrant just launched an in-depth course on mastering production-grade vector search, and we’re part of it! We teamed up to show how to analyze and debug AI systems using @QuotientAI + @qdrant_engine. Our session covers real-world AI monitoring workflows w/ hallucination detection and document relevance scoring.