All use cases
ON-CALL HEALTH

Stop waking up for routine pages

60-80% of overnight pages are routine patterns the on-call could fix with a runbook, but still wake a human up to run.

"When a routine alert fires at night, I want it resolved by an agent inside our policy, so I only get woken for the things that actually need me."

The problem

On-call burden is the single biggest driver of senior SRE attrition, and the painful truth is that most pages are routine. The pod that needs a restart, the cache that needs a flush, the queue that needs a drain. Each is a 30-second action a human could do in their sleep, except they can't, because they have to wake up first, get to a laptop, and navigate four tools to do it. The cumulative damage is measured in attrition.

How Nova solves it

Nova's policy envelope decides which pages need a human and which don't. Routine patterns close themselves; novel ones still page.

  1. Policy envelope, written once

    You define what Nova can do without approval (scale this deployment up to N replicas, restart this pod, flush this cache, rotate this key) and what requires a human (anything affecting customer data, anything with blast radius > 1 service).

  2. Trust scores per agent action

    Agents earn autonomy by track record. An action with 500 successful runs and zero rollbacks gets a trust score of 99 and operates without approval. An action with mixed history requires a human.

  3. Always-loud escalation for the unfamiliar

    When the symptom doesn't match a known pattern, or the trust score is below threshold, Nova pages the on-call with full context, the alert, the correlated signals, the candidate runbooks, and the recommended action.

Teams running Nova in agent-first mode report 60-80% of overnight pages closing without a human page at all. The remaining 20-40% land in someone's pager with the diagnosis already done.

Try this on your stack

Get Started Free, cancel anytime. Or book a 30-minute walkthrough with a founder.