Agent trail

Agent trail is a Agents block from Orvain UI, built for React and Vue with a matching Figma frame.

Best for

A small live card for one agent while you do something else

Anatomy

Agent, app and status · what it is doing now · a short trail of what it did · allow or decline when it stops for an OK · stop

MCPConnect the MCP server
Fix the checkout crashOrvain agent · web-app
2 of 5 done
  1. 8s
    1. Found 3 tickets about the crash
      3 tickets
    2. All of them on Safari 17
      #4821
  2. 34s
    1. Opened a checkout with an empty cart
      test mode
    2. The page threw on submit
      500
  3. Patching the checkout formVS Code · editing cart.ts
    0:09
    1. Found the empty-cart case
      cart.ts:142
    2. Added a guard and 2 tests
      4s
  4. Writing the release note
    1. Added it under Fixed
      v3.2.1
    2. Linked the 3 tickets
      3 links
  5. Opening a pull requestAsks you first

In the Orvain Library

Get Agent trail for your product

The block’s code in React and Vue, its frame in the Figma file, and the Orvain MCP so your AI tools build with it. Part of every Library plan, alongside every other block.

  • React
  • Vue
  • Figma frame
  • Orvain MCP

About this block

Part of Agents

What’s inside

05parts

The pieces it is built from. Keep them all, or drop the ones your product doesn’t need.

  1. Agent, app and status
  2. What it is doing now
  3. A short trail of what it did
  4. Allow or decline when it stopsfor an OK
  5. Stop

Responsive behaviour

420 px

Drawn at this width and never stretched past it. Below it, controls, text and spacing step down from the box the block sits in, not the window.

1440pxDesktop · 12 columns

When to use it

Where Agents earns its place

Reach for Agents

  • An agent that acts in other people's apps, where some of its actions need a yes before they happen.
  • Several agents or several attempts running at once, where someone has to see which is stuck and which is done.
  • Runs long enough that people leave and come back, and need to catch up on what happened and what waits on them.
  • Spend or time that has to be explained afterwards, step by step, against a budget.

Reach for something else

  • A single question and a single answer. An assistant thread from the AI Chat family is the right surface, with its research shown inline.
  • A background job with no decisions in it, such as a nightly export. A progress bar and a notification say all there is to say.
  • A fixed automation people design ahead of time. Build it on the Workflow canvas, where the steps are drawn before they run rather than chosen as it goes.

Accessibility

06to keep

What the block ships with. Hold on to these as you make it yours.

  • Named controlsEvery icon-only button keeps a text label, so a screen reader can say what it does.
  • Keyboard firstEvery control is reachable with Tab, and its focus ring stays visible.
  • More than colourA state never rides on colour alone; a mark or a word goes with it.
  • Contrast holdsRetheme freely, but keep text at or above the contrast it ships with.
  • Calm motionFor visitors who ask for reduced motion, things simply appear.
  • Room to hitTargets stay at least 24px, with space between neighbours.

Notes for AI

1 line

Is all your assistant needs. With the Orvain MCP connected, it builds the block from your own tokens and components.

Add the Orvain “Agent trail” block to this page: agent, app and status, what it is doing now, a short trail of what it did, allow or decline when it stops for an OK, stop.

Works in
Connect the MCP

Questions about Agent trail.

What is the Agent trail block?

Agent trail is a Agents block from Orvain UI, built for React and Vue with a matching Figma frame. Best for a small live card for one agent while you do something else.

What is the Agent trail block made of?

Is the Agent trail block responsive?

Is the Agent trail block accessible?

How do I add the Agent trail block to my project?

When should I not use a Agents block?

More Agents blocks

All Agents

Agent monitor

Watching one agent run, and giving it the OK when it asks

Agent plan

Reading what an agent will do before it starts, and watching it work through the plan

Agent checkpoints

Going back to an earlier point in a run and trying again from there

Agent findings

Reviewing what an agent found, and fixing or dismissing each item

Agent fleet

Keeping track of many agents at once and answering the ones that ask

Agent graph

Seeing which agents hand work to which, and through which apps

Agent cursors

Editing a document alongside agents and taking or leaving what they change

Agent lanes

Comparing what several agents did over the same stretch of time

Agent queue

Watching a queue of agent jobs work through a pool of workers

Agent recap

Catching up on what agents did overnight

Trace waterfall

Finding where a run spent its time across models, tools and calls

Cost waterfall

Seeing where a run's money went, step by step, against a budget

Agent inbox

One place to answer everything agents are waiting on

Approval gates

Getting a run signed off by the people who have to say yes before it goes on

Autonomy dial

Deciding how much an agent may do on its own, app by app

Agent steering

Changing what a running agent does without stopping it

Parallel attempts

Letting several models try the same task and keeping the best one

The Orvain Dispatch

Premium components, free in your inbox.

Join the Orvain Dispatch and get production-ready components, free to keep: React and Vue code plus the Figma frame, yours to ship.

Just components, never spam. You can unsubscribe anytime.