Human in the loop (HITL) example in tutorials/fundamentals

[MohTahsin]

Adding a human in the loop example in tutorials/fundamentals. Going over multiple ways to interrupt the Strands Agent loops for human approval before executing a tool.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[github-actions]

Latest scan for commit: 464cdbc | Updated: 2026-02-23 17:29:05 UTC

✅ Security Scan Report (PR Files Only)

Scanned Files

• 01-tutorials/01-fundamentals/10-human-in-the-loop/README.md
• 01-tutorials/01-fundamentals/10-human-in-the-loop/images/pattern-1.png
• 01-tutorials/01-fundamentals/10-human-in-the-loop/images/pattern-2.png
• 01-tutorials/01-fundamentals/10-human-in-the-loop/requirements.txt
• 01-tutorials/01-fundamentals/10-human-in-the-loop/strands_hitl.ipynb
• 01-tutorials/01-fundamentals/README.md
• 01-tutorials/README.md

---

Security Scan Results

Critical	High	Medium	Low	Info
0	0	0	0	0

Threshold: High

No security issues detected in your changes. Great job!

This scan only covers files changed in this PR.

[manoj-selvakumar5]

hi @MohTahsin - thank you for the updates! I think we are pretty close. Could you please address the following points and I think we will be good to merge?

• the README says Claude Sonnet 4 but the Agents are using Haiku in the notebook
• json and os are imported but never used. Please remove them.
• Drop Pattern 1 diagram — Pattern 1 ("Standard Tool Execution") that shows normal agent behavior with no interrupt gives an impression that it is another HITL pattern. Including it alongside the two actual interrupt patterns makes it look like 3 HITL strategies when there are really 2. I'd suggest removing Pattern 1 from both the README and the notebook intro. If a baseline reference is needed, a single sentence is enough: "Without interrupts, tools execute immediately and return results to the agent." Please rename the other two patterns as 1 and 2.