assistant-ui Tools

SkillMedia

This skill is a guide for registering tools and building their interfaces in assistant-ui chat apps. Once added, your AI can help you set up custom tool displays, render tool call results in the conversation, and add confirmation prompts so a person approves actions before they run.

Available today. Use it from your connected AI after setup.

No other account needed.

Add the skill, then ask your AI to register a tool or build a confirmation prompt in your assistant-ui app. It can guide you through rendering tool calls and adding approval steps as you build.

Then ask your AI: use the assistant-ui Tools skill

What your AI can do with it

Register LLM tools in an assistant-ui chat app
Render tool calls so their results appear in the conversation
Build custom interfaces for how tools look and behave in chat
Add confirmation prompts that ask a person to approve an action
Set up approval steps where a human reviews a tool call before it runs

What this skill tells your AI

The instructions your AI receives, as published by compozy/compozy in .agents/skills/assistant-ui/assistant-ui-tools/SKILL.md and read by ahel’s review.

Always consult assistant-ui.com/llms.txt for latest API.

Tools let LLMs trigger actions with custom UI rendering.

References

./references/make-tool.md -- makeAssistantTool/useAssistantTool
./references/tool-ui.md -- makeAssistantToolUI rendering
./references/human-in-loop.md -- Confirmation patterns

Tool Types

Where does the tool execute?
├─ Backend (LLM calls API) → AI SDK tool()
│  └─ Want custom UI? → makeAssistantToolUI
└─ Frontend (browser-only) → makeAssistantTool
   └─ Want custom UI? → makeAssistantToolUI

Backend Tool with UI

// Backend (app/api/chat/route.ts)
import { tool, stepCountIs } from "ai";
import { z } from "zod";

const tools = {
  get_weather: tool({
    description: "Get weather for a city",
    inputSchema: z.object({ city: z.string() }),
    execute: async ({ city }) => ({ temp: 22, city }),
  }),
};

const result = streamText({
  model: openai("gpt-4o"),
  messages,
  tools,
  stopWhen: stepCountIs(5),
});

// Frontend
import { makeAssistantToolUI } from "@assistant-ui/react";

const WeatherToolUI = makeAssistantToolUI({
  toolName: "get_weather",
  render: ({ args, result, status }) => {
    if (status === "running") return <div>Loading weather...</div>;
    return <div>{result?.city}: {result?.temp}°C</div>;
  },
});

// Register in app
<AssistantRuntimeProvider runtime={runtime}>
  <WeatherToolUI />
  <Thread />
</AssistantRuntimeProvider>

Frontend-Only Tool

import { makeAssistantTool } from "@assistant-ui/react";
import { z } from "zod";

const CopyTool = makeAssistantTool({
  toolName: "copy_to_clipboard",
  parameters: z.object({ text: z.string() }),
  execute: async ({ text }) => {
    await navigator.clipboard.writeText(text);
    return { success: true };
  },
});

<AssistantRuntimeProvider runtime={runtime}>
  <CopyTool />
  <Thread />
</AssistantRuntimeProvider>

API Reference

// makeAssistantToolUI props
interface ToolUIProps {
  toolCallId: string;
  toolName: string;
  args: Record<string, unknown>;
  argsText: string;
  result?: unknown;
  status: "running" | "complete" | "incomplete" | "requires-action";
  submitResult: (result: unknown) => void;  // For interactive tools
}

Human-in-the-Loop

const DeleteToolUI = makeAssistantToolUI({
  toolName: "delete_file",
  render: ({ args, status, submitResult }) => {
    if (status === "requires-action") {
      return (
        <div>
          <p>Delete {args.path}?</p>
          <button onClick={() => submitResult({ confirmed: true })}>Confirm</button>
          <button onClick={() => submitResult({ confirmed: false })}>Cancel</button>
        </div>
      );
    }
    return <div>File deleted</div>;
  },
});