Context is king
Raw LLM logs are useless without user intent, sentiment or behavior insights.
About Kubit
Building the Future of Agent Analytics
Developing AI agents is incredibly hard. Debugging them shouldn't be.
Kubit Agent Analytics was born out of a shared frustration: while building our AI Analyst features, we were tired of drowning in raw JSON just to figure out why an agent failed. Standard observability tools told us what broke (latency, token limits, system errors), but they couldn't tell us why the user was frustrated. To get the full picture, we had to manually stitch together clickstream data, prompt versions, and raw logs across six different tabs. It was a context-switching nightmare. So, we fixed it.
Our mission
Our mission is to turn unpredictable generative AI into measurable, optimizable products. We map user intent directly to LLM reasoning chains and pipe that context straight into your coding agent via MCP. Leveraging our deep roots in product analytics and a uniquely flexible warehouse-native architecture, we are building the future of Agent Analytics.
Our Philosophy
Action over observation
Finding an error isn’t enough; you need the complete analytical insights and the tooling to take action.
Solve it where you build it
Kubit feeds exact user intent and behavioral context straight into Claude Code or Cursor via MCP, allowing your coding agents to deploy auto-fixes and optimize performance without you ever switching tabs.
Backed by investors who share our vision
Insight Partners
Shasta
TSVC
Join the Kubit Team
We are a team of AI builders, data engineers, and product specialists who have built data platforms at enterprise scale. We are well-funded, moving fast, and looking for people who want to define the future of Agent Analytics. If you are obsessed with developer tools, LLM observability, and ending the era of tab-switching, we want to talk to you.
Open positions
Senior AI Engineer (MCP & IDE Integrations)
- The Role: You will own the core developer experience, building and scaling our native integrations with Claude Code, Cursor, and emerging coding agents via the Model Context Protocol (MCP).
- Stack: TypeScript, Python, LLM frameworks, IDE Extension APIs.
Data Engineer
- The Role: You will build the high-throughput pipelines that ingest, process, and stitch together massive volumes of OpenTelemetry (OTel) traces and clickstream events with zero sampling.
- Stack: Snowflake/Snowpipe, ClickHouse, OpenTelemetry, Kinesis.
Developer Advocate
- The Role: You will be the voice of Kubit to the AI engineering community. You’ll build demo apps (like our AI shopping agent), write technical deep-dives on LLM observability, and share best practices to help developers optimize their agents.
- Stack: Strong communication, active in the AI/DevTools community, experience with Langfuse/LangSmith/Arize/OTel is a plus.
How to Apply
Don't see your exact role but know you belong here?
We are always looking for exceptional talent.
Email us your resume, GitHub profile, or a brief note about what you are currently building.
Contact us
Join the conversation
We love hearing from the engineers building the next generation of AI agents. Whether you need help debugging a trace, want to discuss a custom Enterprise deployment, or just want to talk shop about LLM observability, here is how to reach us
Technical support
Email us at support@kubit.ai, in-app chat or just ask your coding agent to ping us directly using the /kubit:support command.
Sales and enterprise
Reach out to sales@kubit.ai to discuss warehouse-native deployments, custom MSAs, and volume pricing.
Careers
Want to help us build the future of Agent Analytics? Send your GitHub profile and resume to careers@kubit.ai.
Discord
Join our community of AI product engineers to ask questions, share your agent builds, and chat directly with the Kubit core team.
GitHub
Check out our open-source Claude Code and Cursor plugins, MCP skills, OTel SDKs, and demo apps at github.com/kubit-ai