AI Agents - lesson 1 | HackIndia Skills

Key point

The core idea

A model does not directly send UPI, edit your database, or call an API. It emits a structured tool request, then your app or the provider executes that tool and sends the result back.

Tools are how an agent acts. Without tools, the model can only answer from text it already has.

What counts as a tool

A tool can fetch data, run code, call an external API, use a computer, or call another agent. Current SDKs group tools in different ways, such as hosted tools, built-in execution tools, function tools, and agents-as-tools.

For this track, start simple. A function tool is enough: you wrap a local function with a JSON schema so the model knows its name, description, inputs, and expected output.

Example

Tiny mental model

Imagine a campus event helper. A student asks, “What events are open today?” The model should not guess. It should call a tool that reads your events data.

The tool call is not the final answer. It is a request for your program to do work.

User: What events are open today?

Model returns a tool request:
{
  "tool": "list_open_events",
  "arguments": {
    "date": "2026-09-21"
  }
}

Your app runs list_open_events(date).

Tool result:
{
  "events": ["AI project clinic", "Web dev sprint"]
}

Model returns final answer:
Today you can join AI project clinic or Web dev sprint.

Your to-do

The basic loop

Do each one yourself, then tap it to tick it off. The ticks are only a checklist for you: they are not marked or scored.

Send the user request and available tool list to the model.
Let the model decide whether to answer or request a tool.
Execute the requested tool outside the model, in your app or by the provider.
Send the tool result back to the model.
Repeat until the model returns a final answer.

0 of 5 done

Common mistake

Common wrong idea

Beginners often think the model “uses the API” by itself. Usually it does not. The model selects a tool and provides arguments. Your code is responsible for execution, errors, permissions, and logging.

Older tutorials may show tools only as function calling. That is incomplete now. Function tools are still useful, but modern agent platforms also include hosted tools, built-in execution tools, MCP tools, and agents-as-tools.

Tip

Name actions clearly

Tool names should sound like safe functions, not vague wishes. Use get_fee_status instead of handle_student. Use create_invoice_draft instead of do_payment.

A clear name and description help the model choose the right tool. They also help your reviewer understand your public repo quickly.