AI Usage & Cost

Track AI usage by model, feature, team, request type, and budget so product quality and cost stay in the same operating view. The screen connects Overview and Models so platform and engineering teams can find the “Set budget” action while checking requests and tokens.

Use this reference when you need to design this workflow inside an existing product. The example includes practical records such as Reasoning models · 46% and Fast models · 31%, rather than an empty visual shell.

AI Usage & Cost
Use this template in Figr

Template facts

Screen

Analytics

Primary action

Set budget

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 “Set budget” action without losing sight of requests, tokens and the affected records. Keep the decision and its outcome clear before moving to the next task.

Key elements

  • Primary action: Set budget is clearly available where the task happens.
  • Main view: Overview keeps the starting point obvious.
  • Connected view: Models supplies nearby context.
  • Metric: Requests is visible with a meaningful value.
  • Another signal: Tokens helps people judge what to do next.
  • Representative record: Reasoning models · 46% makes the example specific.
  • Second record: Fast models · 31% 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 overview without changing the layout unexpectedly.
  • Partial or delayed metrics; explain the problem and preserve work.
  • Permission denied for models; clarify who can continue.
  • Success after choosing Set budget; 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

Overview → Models → Set budget → Review outcome

Patterns used

Analytics, Overview, Models, Features, 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 Reasoning models · 46% with Fast models · 31%. Make requests clear, then use tokens 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 “Set budget” action. The happy path alone is not enough.

Related UI examples: Agent Runs, AI Evaluation, Prompt Library.

Start from this in Figr

Design a ai usage & cost screen for our existing software product. Use our real design-system tokens, components and product language. Show Overview and Models, include believable records such as Reasoning models · 46%, and make set budget easy to find. Map loading, empty, failure, permission and success states before you create editable high-fidelity screens.

Open Figr