Tool usage

As explained in Build AI-Enhanced Web Apps

Tool calling is a technique in which an AI model emits a structured request for an external tool or function, receives the execution result, and incorporates it into its response.

Tool calling lets a model request external information or actions when a prompt needs real-time or specialized data. The application executes the request and returns its result for the model to use in its response. section 4.4 section 4.4.1

Figure 4.14 The process of tool calling in an AI-powered application using the Vercel AI SDK. This shows how a user action initiates a prompt, which is formatted by the SDK and sent to the AI provider. The AI model may request a tool call, which is then executed by the SDK. The tool’s response is fed back to the AI model through the SDK, and finally, the result is used to update the UI for the user.

Follow the request from the user through the model and SDK, then back to the model and the interface. Tool execution stays under application control. section 4.4.1

Weather lookup

A model can request weather data for a region, receive the result, and incorporate it into an answer. An alternative is to insert fetched weather data directly into a prompt; this works best with a consistent prompt format and offers less flexibility. section 4.4 section 4.4.1

How Build AI-Enhanced Web Apps covers it

How deep it goes

Traces the structured-request and execution cycle through the application server and SDK, including a less-flexible prompt-injection alternative.

Examples

Demonstrates weather retrieval and tool-call messages, with booking systems, e-commerce, and automation agents as use cases.

What it assumes

Builds on familiarity with structured data generation and content streaming.

What you can do after

Apply tool calling with the Vercel AI SDK by defining custom tools, registering them, and handling their responses.

How it connects

Connects tool calling with external APIs, database queries, local functions, structured data generation, and the Vercel AI SDK.

liveBookmanning.com

Read Build AI-Enhanced Web Apps on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Build an AI Agent (From Scratch)A tool call is a model-generated specification requesting invocation of a particular external tool with particular arguments.
• 

  liveBookmanning.com
  AI Agents and ApplicationsA tool call is a structured model response that requests invocation of a named tool with supplied arguments.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionTool use is an AI system capability in which the system invokes external software, services, or functions to perform actions or obtain information.
• 

  liveBookmanning.com
  AI for Everyday ITFunction calling is a language-model capability that enables a model to request invocation of defined software functions or external services by producing structured arguments.
• 

  liveBookmanning.com
  Reinforcement Learning from Human FeedbackTool use is a model capability in which generated interactions invoke external tools or services to perform tasks.
• 

  liveBookmanning.com
  Build Python Web Apps with StreamlitTool use is the capability of an AI system to invoke external software functions or services while solving a task.
• 

  liveBookmanning.com
  Investing for ProgrammersA tool use pattern is an agent architecture in which an agent delegates tasks to external tools, libraries, or APIs and integrates their results.
• 

  liveBookmanning.com
  Spring AI in ActionA tool call is a model-generated request for an application to invoke an external callable capability.
• 

  liveBookmanning.com
  Building Reliable AI SystemsAn AI capability in which a model invokes external tools to obtain information or perform actions.
• 

  liveBookmanning.com
  Authorization in ActionA tool invocation is a request by an agent or software system to execute an operation provided by an external tool.
• 

  liveBookmanning.com
  AI Agents in Action, Second EditionA tool call is a structured request from an AI system to invoke a tool and obtain its result.
• 

  liveBookmanning.com
  AI Agents in ActionFunction calling is an LLM interface capability that produces a structured request to invoke a named function with extracted arguments.

Compare how 13 books explain tool usage →

Related concepts

• OpenAI APIuses · The OpenAI API is a programming interface that allows software applications to send requests to OpenAI models and services and receive responses.
• command-line interfacecontrasts with · A command-line interface is a text-based interface through which users or programs interact with software or a computer by entering commands and receiving output.
• reliable agentused by · An AI agent that performs tool use and multi-step workflows while taking safe actions.
• tool descriptionuses · A tool description is a structured specification of a callable tool's purpose, capabilities, and invocation interface, including its expected inputs.
• control looppart of · A control loop is a repeated process that observes a system’s state, compares it with a desired state, and uses feedback to guide corrective action.
• AI agentused by · An AI agent is a computational system that uses artificial intelligence to interpret information, select actions, and pursue goals through interaction with an environment.

This explainer was generated by Manning's knowledge graph from the text of Build AI-Enhanced Web Apps. The section links point to the parts of the book it draws on.