Meet Anna. Your Principal Generalist & Team Lead.
Anna is the orchestrator of the CloudThinker Multi-Agent System. She routes work to the right specialist, coordinates parallel agent runs during incidents, owns the playbook from page to post-mortem, and signs the report that goes to your leadership team.
Leading use cases, customizable Skills
These are leading patterns customers run with Anna across operations — orchestration, runbooks, routing, post-mortems, SLOs, and on-call. They're starting points, not the limit — extend, replace, or add your own sub-skill with the Skills Framework.
/incident-orchestration
War Room Coordination
Spins up war rooms in Slack / Teams, pulls in the right specialist agents (SRE, Cloud, Kubernetes, Database), and keeps the incident channel synthesized in real time.
/runbook-execution
Playbook Library
Selects and executes from the 325+ pre-built runbook library — failover, scale, rotate, restart — and chains them with /create-task and approval gates.
/cross-team-routing
Specialist Routing
Reads the request, classifies the domain, and routes to Olivier, Alex, Kai, Tony, or all of them in parallel — with consolidated output for the requester.
/postmortem-author
Blameless Post-Mortems
Generates a blameless RCA with timeline, contributing factors, and action items — drafted directly into your wiki, Notion, or Confluence.
/sla-governance
SLO / SLI Reporting
Tracks SLO burn across every service, alerts on error-budget exhaustion, and generates monthly availability reports for leadership review.
/escalation-policy
On-Call & Paging
Configures and audits PagerDuty / Opsgenie / Rootly escalation paths, rotation health, and out-of-hours fairness across the on-call team.
From prompt to repeatable Command in three steps
Start with a prompt
Ask Anna in chat to coordinate an incident, run a routine, or generate a post-mortem. She executes a one-shot run inside Sandbox Isolation, calls the specialist agents she needs in parallel, and posts a synthesized status to your incident channel.
@anna please coordinate the incident on payment-service — pull in the SRE Agent, Database Agent, and Cloud Agent, and post a synthesized status in #incident-alpha every 5 minutes.
Persist as a Skill
Use /create-skill to capture the discovered surface, auth flow, Rules of Engagement, validation logic, and notification routing as a reusable Skill versioned in the Knowledge Base.
/create-skill orchestrate-payment-incident --from-thread #current --specialists sre,database,cloud --channel #incident-alpha --status-cadence 5m
Run anywhere as a Command
Invoke the saved Skill as a /-prefix Command from chat, webhook, or schedule. Re-runs are deterministic — same RoE, same surface, same CVE-mapped report.
/orchestrate-payment-incident
Safe by construction — from sandbox to audit
Anna inherits the same platform primitives that protect every CloudThinker agent. Every orchestrated run is sandboxed, every approval gate is enforced, every routed action is recorded — so incident response is fast without ever bypassing the controls your security and compliance teams expect.
Sandbox Isolation
Every run executes inside an ephemeral microVM with strict egress and a tamper-evident audit trail.
Guardrails Engine
Guard-in and guard-out policy enforcement on every model call — PII / PHI redaction and secret detection by default.
Rules of Engagement
Strict scope, method, and rate-limit constraints. Read-only proof-of-concept execution. No destructive operations.
Immutable audit
Every reasoning step, tool call, and finding is recorded — exportable to your SIEM and reviewable by compliance.
Compliance Certifications
We maintain the highest industry standards and regularly undergo rigorous third-party audits to ensure compliance.
Ready to let Anna run your operating rhythm?
Our operations team partners directly with your SRE, platform, and incident management leads — war-room playbook reviews, post-mortem templates, and SLO governance walkthroughs on request.
- Multi-agent orchestration
- Blameless post-mortems
- SLO governance + on-call audits