Cover art for Resolve AI's SRE-1 model finds root causes of production alerts

Resolve AI's SRE-1 model finds root causes of production alerts

AI agents close 70% of alerts without engineers.

By ·

Nov 19, 2026

7 cards · 1m 10s · tap to begin

From · · · 1m 10s

Resolve AI's SRE-1 model finds root causes of production alerts

AI agents close 70% of alerts without engineers.

In brief

AI agents close 70% of alerts without engineers. Resolve AI's SRE-1 model identifies root causes of production issues, cutting alert resolution time by tenfold with 95% accuracy. Originally reported by SiliconANGLE.

Resolve AI launches SRE-1 model

Resolve AI Inc. has launched SRE-1, a 27 billion-parameter model trained to find root causes of production alerts.

SRE-1 improves incident resolution

SRE-1 increased pass rate from 6.9% to 38.8% on 49 live production cases, solving twice as many incidents as coding agents.

Primary On-call service

Primary On-call uses AI agents to investigate alerts, close issues, or escalate to engineers with 80% of alerts handled without escalation.

Salesforce uses Primary On-call

Salesforce reported 70% of CRM Analytics team alerts closed by AI without waking engineers during testing.

SRE-1 achieves 95% accuracy

SRE-1 solves production alerts with 95% root-cause accuracy and tenfold improvement in mean time to resolution.

Resolve AI's funding

Resolve AI raised over $190 million including a $40 million Series A extension valued at $1.5 billion.

Primary On-call shadow mode

Shadow mode records AI actions for teams hesitant to hand over pagers directly.

At a glance

Resolve AI's SRE-1 model identifies root causes of production issues, cutting alert resolution time by tenfold with 95% accuracy.

Read the original on SiliconANGLE

Read the TL;DR — this story on one card.

How we make summaries

React

Sign in to react and comment.

Comments (0)

Life is short. Keep it sweet. Respect others' opinions and be kind!

    Recommended next

    More decks on resolve ai and related topics.