Tool result

As explained in The Art of AI Product Development

Tool output is the data returned by an external tool after it processes an agent's request.

A tool result is the output returned after an agent selects and calls an external tool. API results may be verbose JSON, so parsing can reduce noise before the language model uses them. section 9.1.4

Practical handling options include:

• Apply custom logic to retain only fields relevant to the task. section 9.1.4
• Use a dynamic algorithm to identify the most helpful fields for the current situation. section 9.1.4

Verbose API response

An API may return a large JSON response. Trimming it to the relevant information gives the language model less noise to process. section 9.1.4

Figure 9.7 The agent’s process for using a tool

Shows the agent’s process for selecting, calling, and receiving results from a tool. section 9.1.4

How The Art of AI Product Development covers it

How deep it goes

Explains verbose JSON trimming and relevant-field selection without specifying a particular parsing algorithm.

Examples

Uses verbose API JSON and selecting or trimming relevant fields as examples.

What it assumes

Assumes tool selection and calling already produce an output that requires parsing.

What you can do after

Apply it via custom logic or dynamic selection to reduce irrelevant tool-output information.

How it connects

Connects tool results to language models, APIs, tool selection, and agent systems.

liveBookmanning.com

Read The Art of AI Product Development on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Build an AI Agent (From Scratch)A tool result is the output produced by an external tool after processing an invocation and its arguments, including whether execution succeeded or failed.

Compare how 2 books explain tool result →

Related concepts

• tool usageproduced by · Tool use is an AI system's invocation of external software functions, services, or other capabilities to obtain information or perform actions.
• code executionproduced by · Code execution is the process of running program instructions or computational operations in a computing environment.
• contextpart of · Context is the surrounding information, state, or circumstances that condition how an entity, event, or task is interpreted or how a system behaves.
• memoryproduces · Memory is a storage resource or mechanism that retains data or computational state for access during computation or later use.

This explainer was generated by Manning's knowledge graph from the text of The Art of AI Product Development. The section links point to the parts of the book it draws on.