A 27B model trained with reinforcement learning to find the root cause of production incidents.
Read the technical reportResolveAI Labs · 18 November 2026
Pass rate is the share of runs in which LLM judges score the causal chain at least 0.8 against a reference chain, a threshold we calibrated with on-call engineers.
“ResolveAI’s SRE-1 model shows what a domain-specific model can deliver for production. The fact that ResolveAI has managed to produce this model is a testament to the team’s deep modeling and RL talent. We are proud to have supported ResolveAI as the first design partner for Snowflake Cortex Training, which they used to build SRE-1”
Vivek Raghunathan
SVP of Engineering at Snowflake
“AI in production has to deliver more than promising results in a demo. It needs to be accurate, dependable, and economically viable at scale. Domain-specific models like ResolveAI’s SRE-1 represent an important step toward making AI a meaningful part of how we detect, investigate, and resolve incidents. At Zscaler, where we protect the world’s largest enterprises, including more than 50% of the Fortune 500, we see significant opportunity to work with ResolveAI to improve reliability for our customers.”
Misha Kuperman
Chief Reliability Officer & GM, Zscaler
SRE-1 investigates in your environment, working backwards from an alert or issue to find the root cause. It searches through hundreds of tools and integrations to produce a cited causal chain, explaining all steps from the root cause to what triggered the alert.
Thousands of codebases, petabytes of telemetry, hundreds of tool calls per investigation.
Most alerts get no postmortem, and some incidents have several root causes, or none known.
Telemetry ages out within weeks, so incidents worth evaluating are rare and short-lived.
By evaluation time, the fix is recorded in commits, tickets and chat that the model could read.