Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.lumiqtrace.com/llms.txt

Use this file to discover all available pages before exploring further.

Open LumiqPilot anywhere: Press ⌘J on Mac or Ctrl+J on Windows/Linux from any page in the dashboard.
LumiqPilot is the AI copilot built into LumiqTrace. Open it with ⌘J (Mac) or Ctrl+J (Windows/Linux) from anywhere in the dashboard. Instead of navigating menus, you describe what you want in plain language — LumiqPilot interprets your intent, shows you exactly what action it plans to take, asks for confirmation on anything consequential, then executes it and reports back.
LumiqPilot is available on the Team and Scale plans. On Free and Pro, the ⌘J shortcut is visible but opens an upgrade prompt.

​
Opening LumiqPilot

You can open LumiqPilot three ways:
  • Press ⌘J / Ctrl+J anywhere in the dashboard
  • Click the Pilot item in the left sidebar
  • Click Ask Pilot in any anomaly or alert notification banner
The Pilot panel slides in from the right side of the screen. Previous conversations in the same project are preserved across sessions.

​
What LumiqPilot can do

LumiqPilot has direct write access to the following resources in your project. It reads context from your live metrics, trace data, and configuration before suggesting or taking action.

Alert management

Create, modify, snooze, or delete alert rules. “Silence the error-rate alert for the next 2 hours” or “Create a new alert if p99 latency exceeds 5 seconds.”

Guardrail management

Enable, disable, or update guardrail policies. “Disable the toxicity guardrail on the demo project” or “Add a new guardrail that blocks requests about competitors.”

Prompt management

Create new prompt versions, update labels, and roll back to previous versions. “Roll back the support-reply prompt to the previous production version.”

SDK config

Push real-time configuration changes to running SDK instances. “Switch all GPT-4o calls to GPT-4o-mini” or “Set the sample rate to 10% for one hour.”

Cost analysis

Explain cost spikes, surface top-spending models, and generate optimization recommendations on demand.

Incident investigation

Correlate anomalies, trace errors, and configuration changes into a coherent timeline with a plain-English explanation.

​
Safety gates

LumiqPilot applies two levels of safety before executing any write action: Role check. Members with the Member role cannot trigger any write action. Admins can execute most actions. Owners have unrestricted access. If your role is insufficient, Pilot explains what permission is needed and who to contact. Confirmation for high-risk actions. For destructive or broadly impactful operations — deleting an alert rule, disabling guardrails, changing model routing, setting disable_tracing: true — Pilot presents a confirmation card before executing. The card shows exactly what will change and gives you a Confirm or Cancel button. Pilot never takes a high-risk action without explicit confirmation.
Actions confirmed in LumiqPilot take effect immediately. There is no undo button — but every action is logged in the audit trail (see below), and most changes can be reversed by asking Pilot to undo them.

​
Example conversations

The following examples show the kinds of requests LumiqPilot handles well:
You: Why did my costs spike this morning?Pilot: I can see a 340% cost increase between 9:00 AM and 10:30 AM today. The spike is concentrated in the gpt-4o model — 847 requests were made in that window compared to your 7-day average of 210. The largest trace was from session sess_abc123, which made 14 sequential GPT-4o calls with an average of 3,200 input tokens each. That session alone cost $0.47. The spike correlates with a deployment at 8:52 AM — it looks like a new feature is making more LLM calls than expected.You: Create an alert if hourly GPT-4o cost exceeds $5.Pilot: I’ll create an alert rule with metric cost_usd, condition >, threshold 5.00, window 60 minutes, model filter gpt-4o. Does that look right?You: YesPilot: Alert rule “GPT-4o hourly cost > $5” created. It will be evaluated in the next 5-minute cycle.
You: GPT-4o is down. Switch all calls to GPT-4o-mini immediately.Pilot: I’ll push an SDK config rule to redirect all gpt-4o calls to gpt-4o-mini across all running instances. This is a high-risk operation — it affects all active API key holders for this project. Confirm?You: ConfirmPilot: Config rule applied (version 12). Running SDK instances will pick up the change within the next flush cycle (~2 seconds). I’ll create a reminder to remove this rule — how long should the override stay active?You: 1 hourPilot: Done. I’ve set the rule to expire in 60 minutes. You’ll receive a notification when it’s removed.
You: The support-reply prompt is producing bad responses. Roll it back to the last stable version.Pilot: The current production version of support-reply is v8 (deployed 2 hours ago). The previous production version was v7. I’ll move the production label from v8 back to v7. Confirm?You: YesPilot: Label updated. support-reply version 7 is now live on production. Version 8 still exists in staging if you want to review and fix it.

​
Audit log

Every action LumiqPilot takes is written to the audit log with full attribution. To review the log, go to Settings → Audit Log. Each entry shows:
  • The timestamp of the action
  • The user who triggered it
  • The action type (e.g., alert.create, sdk_config.update, prompt.label_update)
  • The before and after state (for updates)
  • Whether the action required and received confirmation
The audit log is exportable as CSV from the Scale plan. Use it to meet compliance requirements or to give engineering managers a review of what changed and when.

​
Self-tracing

LumiqPilot traces its own AI calls through LumiqTrace. You can see Pilot’s model calls in your traces view under the lumiqpilot agent tag. This means Pilot’s own token usage and latency count against your event quota — but it also means you have full transparency into how Pilot is using AI to serve your requests.

​
Notifications from Pilot

LumiqPilot can proactively surface information without you asking. When an anomaly is detected or a new cost optimization opportunity is found, a notification badge appears on the Pilot icon in the sidebar. Open Pilot to see the full context and take action.