AI Agents - lesson 7 | HackIndia Skills

Key point

One review rule

Your repo must make the agent easy to inspect, easy to run, and hard to misuse. A reviewer should not search through random files to find the tool schemas, approval gates, call-result loop, limits, or script note.

What to ship

You are not shipping a perfect AI product. You are shipping evidence that you can build a safe tool-calling agent.

Current agent systems still follow the same core pattern: the model asks for a tool, the app or provider runs it, the result goes back, and the loop continues until a final answer. Your repo should make that pattern visible.

Your to-do

Repo checklist

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.

Create a small README that explains the use case, setup, run command, and safety choices.
Keep tool schemas in one clear file or folder, not hidden inside a long prompt.
Name the file that runs the call-result loop clearly, such as agent_loop.py or runner.ts.
Add one approval gate for a risky action, such as sending a message, writing to a database, or charging money.
Add hard limits, such as max turns, model calls, tool calls, or tool concurrency, based on your stack.
Write a short note that says when you would replace this agent with a plain script.

0 of 6 done

Example

README skeleton

Use this as your minimum README. Replace the placeholders with your project details. Keep it honest if some features are basic.

Project: Campus Reimbursement Helper

What it does
Helps a student prepare a reimbursement request from bill details. It can read structured input, calculate totals, draft a message, and ask before sending anything.

How to run
1. Install dependencies.
2. Add required environment variables.
3. Run the agent with a sample request.

Safety features
- Tool schemas are in: src/tools/
- Call-result loop is in: src/agent_loop.py
- Approval gate is used before: sending the final email
- Hard limits used: max turns and tool call budget
- Risky actions are not run without human approval

When I would replace this with a script
I would use a script if the steps are fixed: read a CSV, calculate totals, fill a template, and save a PDF. I use an agent only when the request needs judgement, such as asking follow-up questions or choosing which tool to call.

Common mistake

Common submission mistake

Do not submit only a chat UI. A chat screen does not prove that you built a tool-calling agent.

Also avoid a repo where all safety logic is described in the README but not present in code. The README should point to real files.

Tip

Use AI carefully

Ask an AI assistant to review your repo before submission. Give it the checklist and ask what is missing.

Then verify the answer yourself. AI may claim that a limit or approval gate exists when it only appears in comments.

Prompt to use:
Review this repo for a hackathon submission. Check whether it clearly shows:
1. tool schemas
2. a call-result loop
3. a human approval gate
4. hard limits
5. a note on when a script is better
Return missing items with file names. Do not guess.