Engineering & Product · Digital Employee #101
AI SRE On-Call Assistant
Reduce incident time
Reduce incident time. AI SRE On-Call Assistant works for your product and engineering team under a named human owner, with its cost and results shown in the Investment & ROI Ledger.
What it does
Mission: Reduce incident time.
AI SRE On-Call Assistant works for your product and engineering team. Typical work: alert correlation, runbook execution (read-only first), incident timeline. It works inside IT & Security — Security Center, IT & Security — DevHub.
How it works under supervision
A named human owner is accountable for its work. Every hire starts in shadow mode (A1): it proposes, a person acts, and agreement is scored. In probation (A2) its drafts go out only after one-click approval until the probation criteria are met.
What it may do on its own
Its autonomy ceiling after probation is A2: it prepares each action as a draft and a person approves it with one click. Nothing it prepares takes effect without a person.
What needs approval
Its risk ceiling is R2. Once autonomy is earned, it may carry out reversible changes visible to others, such as assigning, scheduling or drafting (others are notified), without a separate approval. Anything external or customer-facing, such as sending a message or publishing, goes to the Approvals Inbox. R4 Actions (payments, deletion, signing, payroll) always need a person.
Runbooks run read-only first.
Cost and return in the Investment & ROI Ledger
Rent, AI usage, pass-through costs such as messages, and your team's supervision time are recorded as investment. Results are tracked against its KPIs (MTTR, runbook coverage) and your previous process, shown as observed or assisted unless a reviewed experiment shows incremental return. Nothing is guaranteed.
Availability
This role is planned for wave W4, after Year 1, once the apps it uses are ready.
Skills & Actions
What it does
- Alert correlation
- Runbook execution (read-only first)
- Incident timeline
Tools
Apps it works in
- IT & Security — Security Center
- IT & Security — DevHub
It uses only the apps and modules your workspace subscribes to, with the permissions you grant.
Frequently asked questions
Does AI SRE On-Call Assistant work without human oversight?
No. It has a named human owner and starts in shadow mode, then probation with one-click approvals. After probation its autonomy ceiling is A2: it prepares each action as a draft and a person approves it with one click.
What does AI SRE On-Call Assistant need approval for?
Its risk ceiling is R2. Anything external or customer-facing, such as sending a message or publishing, goes to the Approvals Inbox. R4 Actions such as payments, deletion, signing and payroll always need a person.
How do I see what AI SRE On-Call Assistant costs and returns?
The Investment & ROI Ledger records its rent, AI usage, pass-through costs and your team's supervision time, and shows results against its KPIs compared with your previous process. Returns are labelled observed or assisted unless a reviewed experiment shows incremental value.
When will AI SRE On-Call Assistant be available?
It is planned for wave W4, after Year 1. One3 is built in waves, and a role is published only when all the apps it uses are ready.
Put the AI SRE On-Call Assistant on probation
Agree the goal, the budget and the approval rules. The Investment & ROI Ledger shows what it cost and what it returned.