AI Agents UI
The AI Agents section is where you see what Tantilium Cloud Runner's AI is doing: the always-on reactive pipeline, and the reasoning agents you (or the platform) launch to investigate problems. To learn how the agents themselves work, see AI Agents.
Agent overview (/agents)
A status card for each service in the reactive pipeline, updated continuously from its health endpoint.
The observability agent collects telemetry snapshots, the analysis agent detects anomalies and makes decisions, and the action agent carries out approved remediations. The feedback agent measures whether those actions helped, and the recommendation agent turns insights into recommendations.
Below the cards, a flow diagram shows how events move between them, following the same closed loop described in Reactive AI Pipeline.
Each agent's page
Every pipeline agent has its own page with its latest output:
| Page | Shows |
|---|---|
/agents/observability | Recent telemetry snapshots per cluster. |
/agents/analysis | Analysis results: anomalies, risk scores and decisions. |
/agents/actions | Actions taken, their reasons and outcomes. |
/agents/feedback | Feedback signals and how thresholds have adapted per cluster. |
/agents/recommendations | Recommendations, by priority and category. |
Agent runs (/agents/runs)
An agent run is one session of a reasoning agent working on a goal. The runs list shows each run's agent type, cluster, prompt, status (with a spinner while running), duration, trigger (manual or automatic) and start time.
Start a run
-
Select New Run.
-
Choose an agent type.
Use the SRE Orchestrator for open-ended investigation across everything. For a narrower question, pick the specialist: the Security Auditor reviews security posture, findings and RBAC; the Cost Optimizer looks at spend, waste and right-sizing; the Incident Responder triages and resolves an active incident; the App Advisor reviews one application against best practices; the Load Test Analyst interprets performance and load-test results; and NodeOps covers node pools, capacity and consolidation.
-
Choose the cluster.
-
Describe what you want in the prompt. Be specific about the symptom and the time frame.
-
Select Start Run. The run opens immediately so you can watch it work.
The same thing through the API:
POST /api/agents/runtime/api/v1/runs
Content-Type: application/json
{
"agent_type": "sre_orchestrator",
"cluster_id": "prod-us-east",
"prompt": "Investigate why memory usage has been climbing for the last 2 hours"
}
Runs also start automatically: when the analysis agent's risk score for a cluster exceeds 70, an SRE Orchestrator run is launched with the analysis as context.
Watching a run (/agents/runs/{id})
The run view streams the agent's work live.
Left, the reasoning trace:
- Thinking (purple, collapsible): the agent's reasoning between steps.
- Tool calls (blue): each tool the agent calls, with its input.
- Tool results (green): the result and how long it took.
- Tool errors (red): calls that failed, and how the agent recovered.
Right, the output: the agent's findings and recommendations, streamed as they're written.
If your connection drops, the view reconnects automatically and catches up. The run itself carries on on the server regardless, and its full history is saved.
How streaming works
The page subscribes to a Server-Sent Events stream:
GET /api/agents/runtime/api/v1/runs/{id}/stream
Content-Type: text/event-stream
Each event is a JSON object:
{ "type": "thinking", "run_id": "abc-123", "payload": "Let me start by checking..." }
{ "type": "tool_call", "run_id": "abc-123", "payload": { "tool": "get_cluster_health", "input": "{}" } }
{ "type": "tool_result", "run_id": "abc-123", "payload": { "tool": "get_cluster_health", "duration_ms": 143 } }
{ "type": "text", "run_id": "abc-123", "payload": "The cluster health score is 72/100..." }
{ "type": "done", "run_id": "abc-123", "payload": null }
The stream ends with done (or error). Use the same endpoint to build your own integrations, for example posting run results to a chat channel.
Next steps
- Your first AI investigation: a guided walkthrough.
- Agent runtime: agents, tools and models in depth.