BEGINNER · 8 MODULES · 64 LESSONS

Agent Fundamentals and Tool Calling

Learn from scratch how an AI model goes from answering to acting: build an agent with tools, a decision loop, and error handling in Python.

For you if
You code in Python and want to know what really happens inside an AI agent.
By the end
You'll know how to define tools, build the agent loop, chain multi-step tasks, and recover when a tool fails.
You need
Basic Python installed on your computer. No API key or internet connection required.
  1. 01Qué es un agente8 LESSONS
    1. Module 1: What Is an Agent
    2. From Answering to Acting: What Is an Agent
    3. LLM+Prompt vs. Agent
    4. The Perceive: Decide, Act, Observe Loop
    5. When You Need an Agent (and When You Don't)
    6. The Anatomy of an Agent: Model + Tools + Loop + Goal
    7. The Agentic Ecosystem Landscape
    8. Mini-project: Map a Reservo Request to an Agent
  2. 02Tools And The Tool Contract8 LESSONS
    1. Module 2: Tools and the Tool Contract
    2. What Is a Tool
    3. The Tool Contract: name, description, input_schema
    4. Writing Descriptions: This Is How the Model Chooses
    5. What a Tool Returns to the Model
    6. Designing Scoped Tools
    7. Reservo's Tools, with Their Schema
    8. Mini-project: Declare and Run Reservo's Tools
  3. 03The Tool Calling Protocol8 LESSONS
    1. Module 3: The Tool-Calling Protocol
    2. How the Model Requests a Tool
    3. The Anatomy of the `tool_use` Block
    4. Parsing the Request and Dispatching
    5. Returning the Tool Result
    6. The Complete Round Trip
    7. Verifying the Shape Against the Documentation
    8. Mini-project: A Single-Tool Round Trip
  4. 04The Agent Loop8 LESSONS
    1. Module 4: The Agent Loop
    2. The Agent's While Loop: Request, Execute, Feed Back, Repeat
    3. Feeding Results Back: the tool_result and the History
    4. The Iteration Cap: Why Every Agent Loop Needs a Brake
    5. Multi-Step: Chaining Tools
    6. When Does the Agent Stop?
    7. Tracing a Full Multi-Step Run
    8. Mini-project: A Multi-Step Loop Runner
  5. 05Multi Tool Agents And Tool Selection8 LESSONS
    1. Module 5: Multi-tool agents and tool selection
    2. Giving the model several tools
    3. How the model chooses a tool
    4. Disambiguating similar tools
    5. Parallel tool calls
    6. The cost of too many tools
    7. Grounding answers in tool results
    8. Mini-project: a multi-tool Reservo agent
  6. 06State Memory And Context In The Loop8 LESSONS
    1. Module 6: State, memory, and context in the loop
    2. The conversation history accumulates
    3. Why the model needs the history
    4. The context window: what to keep
    5. Summarizing long tool results
    6. Passing state between steps
    7. Short-term memory vs. long-term memory
    8. Mini-project: a stateful Reservo agent
  7. 07Errors Retries And Robustness8 LESSONS
    1. Module 7: Errors, retries, and robustness
    2. When a tool fails
    3. Returning the error as a tool_result
    4. The model sees and corrects
    5. Validating the model's arguments
    6. Retries with a cap
    7. Timeouts and graceful degradation
    8. Mini-project: a robust Reservo agent
  8. 08Project A Reservo Agent With Tools8 LESSONS
    1. Module introduction: the capstone, the Reservo agent with tools
    2. The complete tool set, with its schemas
    3. The runner protocol and the loop
    4. Multi-tool selection and state
    5. Robustness in the capstone
    6. The end-to-end demo
    7. What your agent still needs
    8. Project: ship the Reservo agent
Reviews

What students say

These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.

No approved reviews yet.

Be the first to share your experience!

SEC. 06 · THE STUDIO

Why this studio exists

For decades, building software belonged to technical profiles with years of training, and getting a digital product into the real world took companies months or years. No-code and AI have narrowed that gap, but the knowledge is still held by a few.

Tech Benders exists to open that knowledge up, so business teams and non-technical teams can put their ideas into production with the right technical decisions behind them. AI does what you ask of it. Without a technical base, what it builds may not scale with your company’s ecosystem, and its costs can run away over time.

The team knows the pains of large organizations and the speed at which they have to move. It brings solution architecture, data engineering, product built end to end from back end to front end, and daily work with AI. Software that solves what you need in days, not months, with the cost of AI kept in check.

Founders

The studioRead about Tech Benders →

Write to ushi@techbenders.io

Made with Wislab