AgentMark supports extending prompts with custom tools (like API calls or calculations) and creating agents that can make multiple LLM calls to solve complex tasks.

​
Tools

Tools are custom functions that your prompts can use to interact with external systems or perform specific operations.

​
1. Create and Register Tools

First, create and register your tools with the adapter tool registry:

import { VercelAIToolRegistry, createAgentMarkClient } from "@agentmark/vercel-ai-v4-adapter";

// Create your tool function
const checkWeather = async (input: { location: string, date?: string }) => {
  // Your weather checking logic here
  const weather = await weatherAPI.get(input.location, input.date);
  return { temperature: weather.temp, conditions: weather.conditions };
};

// create tool registry
const toolRegistry = new VercelAIToolRegistry();

// Register the tool
toolRegistry.register("check_weather", checkWeather);

// create agentmark client
const agentmarkClient = createAgentMarkClient({
  toolRegistry,
});

​
2. Define Tool Schema in Prompt

Then use the tool in your prompt:

---
name: weather-advisor
text_config:
  model_name: gpt-4
  tools:
    check_weather:
      description: Get current weather for a location
      parameters:
        type: object
        properties:
          location:
            type: string
            description: City or location name
          date:
            type: string
            description: Date to check (YYYY-MM-DD)
        required: ["location"]
---

<System>
You are a travel advisor that can check weather conditions. Use the weather tool to provide accurate forecasts.
</System>

<User>What's the weather like in Paris today?</User>

​
Agents

Agents can make multiple LLM calls and use tools to solve complex tasks.

​
1. Register Multiple Tools

import { VercelAIToolRegistry, createAgentMarkClient } from "@agentmark/vercel-ai-v4-adapter";

// create tool registry
const toolRegistry = new VercelAIToolRegistry();

// Register all your tools
toolRegistry.register("search_flights", searchFlights);
toolRegistry.register("check_weather", checkWeather);

// create agentmark client
const agentmarkClient = createAgentMarkClient({
  toolRegistry,
});

​
2. Create Multi-Step Agent

Enable agent capabilities by setting max_calls in your prompt:

---
name: travel-planner
text_config:
  model_name: gpt-4
  max_calls: 3  # Allow multiple LLM calls
  tools:
    search_flights:
      description: Search available flights
      parameters:
        type: object
        properties:
          from:
            type: string
          to:
            type: string
          date:
            type: string
        required: ["from", "to"]
    check_weather:
      description: Check weather forecast
      parameters:
        type: object
        properties:
          location:
            type: string
        required: ["location"]
---

<System>
You are a travel planner that can:
1. Search for flights
2. Check destination weather
3. Make travel recommendations
</System>

<User>Help me plan a trip from NYC to Miami next week.</User>

​
3. Run the Agent

import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";
import { createAgentMarkClient, VercelAIToolRegistry } from "@agentmark/vercel-ai-v4-adapter";  
import { FileLoader } from "@agentmark/agentmark-core";

// create tool registry
const toolRegistry = new VercelAIToolRegistry();

const prompt = await agentmarkClient.loadTextPrompt("travel-planner.prompt.mdx");

const vercelInput = prompt.format({
  props: {
    // your props here
  }
});

const result = await generateText(vercelInput);

​
Learn More

For detailed information about implementing tools, creating agents, and best practices, see the AgentMark Tools and Agents Documentation.

Key features include:

  • Custom tool creation
  • Multiple tool support
  • Multi-step agent workflows
  • Error handling
  • Parameter validation

Have Questions?

We’re here to help! Choose the best way to reach us: