Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

Foundations of Agentic Tool Use in Python

via CodeSignal

Go to class Write review

Overview

Master the practical building blocks of agentic systems in Python. Covering Factors 1, 3, 4, 8, and 9, you’ll prompt for structured outputs, define and validate tool schemas, own the context window, and run explicit loops that you control. You’ll also compact execution errors back into context for self-correction, turning natural language requests into reliable tool executions.

Syllabus

  • Unit 1: Prompting for Structured Output
    • Making Your First API Call
    • Crafting Prompts for Structured Output
    • Parsing JSON from City Guide
    • Iterating Through Structured Task Lists
    • Handling JSON Parsing Errors Gracefully
  • Unit 2: Defining a Tool Schema and Requiring Tool Use
    • Migrating to Native Tool Calling
    • Enforcing Tool Use with Required Parameter
    • Extracting Structured Tool Call Arguments
    • Expanding Tool Schemas for Richer Outputs
    • Routing Logic for Multiple Tool Calls
  • Unit 3: Executing Tool Calls and Managing Context
    • Defining Schemas and Making Tool Calls
    • Executing Functions from Tool Calls
    • Recording Tool Calls in Context History
    • Closing the Loop with Final Answers
    • Handling Multiple Tool Calls in Parallel
  • Unit 4: Controlling Loops of Agentic Tool-Use
    • Building the Agent Loop Foundation
    • Connecting Your Agent to the LLM
    • Closing the Action-Feedback Loop
    • Reporting Agent Results and Safety Checks
    • Testing Loop Robustness with Complex Tasks

Reviews

Start your review of Foundations of Agentic Tool Use in Python

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.