Static UX shell. No backend calls, integrations, agents, or side effects.
Open demo run
Run timeline

Agent run detail

Static operational timeline for future LangGraph stages, approval interrupts, retries, latency, token cost, and confidence.

Open ticket detail
Run timeline
Mock LangGraph node state with latency, cost, confidence, and approval wait markers.
Ticket normalized
Complete

Tenant, customer, severity, product area, request_id, and idempotency scope were attached to the run packet.

Latency
212 ms
Cost
$0.000
Confidence
100%
Classified as deploy regression
Complete

Matched Field API, production, P1 severity, and likely schema compatibility risk.

Latency
1.4 s
Cost
$0.012
Confidence
88%
Retrieved evidence
Complete

Selected a runbook, deployment changelog, service status snapshot, and one similar resolved ticket.

Latency
2.8 s
Cost
$0.006
Confidence
84%
Risk and action plan
running

Preparing a customer update plus a Jira escalation draft. External side effects are blocked until approval.

Latency
running
Cost
$0.014
Confidence
82%
Human approval interrupt
waiting

A reviewer must approve or edit the draft because the evidence includes a stale runbook and a customer-visible reply.

Latency
wait
Cost
$0.000
Confidence
requires reviewer
Idempotent tool execution
queued

The Jira draft and customer reply will use stable idempotency keys after approval.

Latency
n/a
Cost
$0.000
Confidence
blocked
Run state
The UI exposes the identifiers needed to reconstruct a run from database records and traces.
run_id
RUN-7781
thread_id
thread-fieldapi-northstar-1048
trace_id
trace-demo-3f82
workflow version
fieldops-demo-v0
state
waiting_for_approval
Trace handoff
Future LangSmith links should be persisted with run IDs and exposed here.
LangSmith trace placeholder
Mock trace ID trace-demo-3f82 is displayed without linking to a real external workspace.