Let CloudThinker agents investigate and execute pre-approved runbooks within your policies. Start with every action reviewed, then increase autonomy only when the evidence earns your trust.
Every CloudThinker deployment starts in Manual. You control the graduation — one approved Runbook at a time.
The agent proposes. You decide.
All write operations pause for human approval. Agents freely perform reads — querying metrics, searching logs, mapping dependencies — but every pod restart, scale event, or config change requires a thumbs-up.
New customers, regulated environments, building initial trust
Pre-approved actions run. Everything else escalates.
If you've defined it in a Runbook or Agent Policy — the agent executes without interruption. Novel scenarios escalate to humans. Trust grows with every Runbook you author.
Established teams with Runbook coverage, recommended for production
Agents decide and act. Only hard limits escalate.
Full decision-making authority. Agents assess risk, choose actions, and execute — scaling, restarting, rolling back. The only exceptions are hard-coded safety guardrails that cannot be overridden.
Mature environments, non-production, speed-critical incident response
The Action Classifier sits between every agent decision and CloudSkill execution. It evaluates every proposal before anything touches your infrastructure.
The agent submits an ActionProposal with full context — target resource, operation type, parameters, and justification for the action.
Four layers run in sequence: Mode Check, Pre-Approval (Runbook / Agent Policy), LLM Risk Assessment, and Hard Safety Guardrails.
One of three outcomes in under 200ms. AUTO_APPROVE executes immediately. ESCALATE queues for human review. BLOCK_REDIRECT instructs the agent to reformulate.
After execution, the agent validates the outcome identically regardless of how the action was approved — confirming resolution or detecting unexpected side effects.
Deterministic read/write lookup against current mode.
Runbook match and Agent Policy lookup.
LLM evaluates reversibility, blast radius, environment, and history.
Non-overridable limits enforced in every mode.
Possible verdicts
CloudThinker classifies every CloudSkill operation into one of four risk tiers. How each tier is handled depends on the current operating mode — giving you fine-grained control over what agents can do.
| Risk Tier | Manual | Auto | Autonomous |
|---|---|---|---|
LOW Reads, status checks, metric queries | ✅ Auto-approve | ✅ Auto-approve | ✅ Auto-approve |
MEDIUM Scaling, pod restarts, non-prod writes | 👤 Escalate | ✅ If pre-approved | ✅ Auto-approve |
HIGH Rollbacks, security changes, migrations | 👤 Escalate | ✅ If pre-approved | ✅ Auto-approve |
CRITICAL Delete prod, IAM admin, VPC, cross-account | 👤 Escalate | 👤 Always escalate | 🔒 Hard guardrail |
Default action classification
Every Auto Mode deployment runs within a layered defense model. Hard guardrails, circuit breakers, prompt injection detection, and complete audit trails — every action is governed, regardless of mode.
These limits are enforced in every mode and cannot be overridden by any customer configuration. They are the absolute floor of safety.
Auto Mode automatically falls back to Manual when issues are detected. The circuit opens fast, closes carefully, and notifies your team via Slack on every trigger.
Recovery: circuit auto-closes after 1 hour with no further issues. Admins can close manually. All events notify via Slack.
External data — logs, API responses, webhooks — is treated as untrusted. The classifier traces the causal chain and flags suspicious instruction patterns before any action executes.
Every action — auto-approved or human-approved — generates an identical immutable audit entry. The trail includes the classifier reasoning, pre-approval source, and Kai's validation result.
Auto Mode is built on top of the full CloudThinker platform — every capability integrates with the Action Classifier, AgentGraph, and the three-layer autonomy framework.
Pre-approve step-by-step procedures. Any Runbook covered by an Agent Policy runs end-to-end in Auto mode without interruption.
Define governance rules that feed the Action Classifier in real time. Update a policy and it takes effect immediately.
Classifier uses live topology data — resource dependencies, environment tags, compliance scope — to enrich every risk decision.
Every human approval in Auto mode is a Runbook candidate. Over time, coverage grows based on your actual operational patterns.
Watch every action as it happens — mode, verdict, classifier reasoning, and pre-approval source visible on a live dashboard.
Measure mean time to resolution across modes. See the business impact of each Runbook you add and each trust level you unlock.
Visualize which incident types have pre-approved Runbooks and which are gaps — guiding where to build trust next.
Key metrics
Auto-Approve Rate
% of actions auto-approved vs. escalated
Classifier Latency p99
Time to produce a verdict
False Negative Rate
Auto-approved actions causing issues
Mean Time to Resolution
End-to-end incident resolution
Circuit Breaker Triggers
Activations per week
Runbook Coverage
% of incidents with pre-approved Runbooks
The CloudThinker difference
| Traditional Automation | CloudThinker Auto Mode |
|---|---|
| Binary on/off per workflow | 3-mode trust journey: Manual → Auto → Autonomous |
| Static playbooks, manual execution | Runbooks + Agent Policies — trust built over time |
| Alert context only | Full topology via AgentGraph — blast radius, dependencies |
| Human is the safety layer | 3-layer classifier + circuit breakers + cross-keeper consultation |
| Action logs only | Full reasoning trace with pre-approval source and classifier explanation |
| No learning — same approvals forever | Approval patterns → Runbook candidates → growing auto-approve coverage |
Start in Manual. Define your first Runbook. Watch your team sleep through the next 2AM incident.