Agent Runs

Inspect agent runs by task, status, duration, tool calls, retries, and failure point so debugging stays tied to the actual execution trace. The screen connects Runs and Traces so platform and engineering teams can find the “New run” action while checking runs 24h and success.

Use this reference when you need to design this workflow inside an existing product. The example includes practical records such as Research agent · 97% and Support agent · 95%, rather than an empty visual shell.

Agent Runs
Use this template in Figr

Template facts

Screen

Analytics

Primary action

New run

Pattern

Analytics

State

Default, loading, empty, error, permission, success

Design system

Adaptable product UI theme

What this screen helps users do

Platform and engineering teams need a clear “New run” action without losing sight of runs 24h, success and the affected records. Keep the decision and its outcome clear before moving to the next task.

Key elements

  • Primary action: New run is clearly available where the task happens.
  • Main view: Runs keeps the starting point obvious.
  • Connected view: Traces supplies nearby context.
  • Metric: Runs 24h is visible with a meaningful value.
  • Another signal: Success helps people judge what to do next.
  • Representative record: Research agent · 97% makes the example specific.
  • Second record: Support agent · 95% shows the pattern works beyond one item.

States worth designing

  • No data for the chosen period; show what people can do instead of leaving a blank panel.
  • Loading runs without changing the layout unexpectedly.
  • Partial or delayed metrics; explain the problem and preserve work.
  • Permission denied for traces; clarify who can continue.
  • Success after choosing New run; confirm the result and the next step.
  • Network or data refresh failure; offer a retry without losing context.

Where this screen sits in the flow

Runs → Traces → New run → Review outcome

Patterns used

Analytics, Runs, Traces, Tools, accessible states, contextual actions

Why these choices work

Make time ranges, filters and metric units clear. Show the data behind each trend so readers can test what changed.

In this design, people should be able to compare Research agent · 97% with Support agent · 95%. Make runs 24h clear, then use success to explain whether the next step needs attention.

Before handing this to a designer or engineer, check keyboard focus, error copy, permissions and what happens after they choose the “New run” action. The happy path alone is not enough.

Related UI examples: AI Evaluation, AI Usage & Cost, Prompt Library.

Start from this in Figr

Design a agent runs screen for our existing software product. Use our real design-system tokens, components and product language. Show Runs and Traces, include believable records such as Research agent · 97%, and make new run easy to find. Map loading, empty, failure, permission and success states before you create editable high-fidelity screens.

Open Figr