TechTips by Moh

Mentorship Courses Blog Tips Projects Contact

← All articles

Tool calling in Python: the task agent, file by file

Read a Python tool-calling agent file by file, from the API call to main.py. Then watch a saved chat store tomorrow as a date three years ago.

Five clay file folders, the middle one open with a teal glow and a wrench, under Tool Calling, File by File.

Nov 03, 2026

Mohammad Mahdi Mohajer

Mohammad Mahdi Mohajer

In this article

01What you will be able to read when this post ends
02The only file that talks to the model
03The file the tools will read and write
04Each tool is a schema and a function
4.1get_todays_date
4.2create_task
4.3filter_tasks_by_text
4.4filter_tasks_by_due_date
4.5filter_tasks_by_status
4.6update_task and delete_task
4.7by_name and definitions
05The loop that joins the call, the file, and the tools
06main.py is how you run it
07The saved chat, including the date it got wrong
08Find what breaks, then fix it

In this article

Keep reading

More from the blog.

A user sits at a laptop with a loading ring while a CPU chip, a GPU card, a RAM stick, and a glowing I/O path sit nearby.

I/O, CPU, GPU, or memory bound?

Your processor graph looks calm and customers still wait. Name what the slow job is bound by: a reply from outside, the processor, the graphics card, or the memory.

A clay code tablet whose rows light teal one by one toward a speech bubble, under A RAG Chatbot, Line by Line.

A RAG chatbot, line by line in Python

Walk a small RAG chatbot in Python in the order it runs: four methods once, four on every question. Then three live runs, and the three gaps they leave.

Eight stacked clay bars like lines of code; the seventh glows teal as chat bubbles drop into it, beside RAG in 8 Lines.

RAG in 8 lines, and where memory goes

The eight stages of a basic RAG chatbot, one line of code each. Why the closest chunks are not the answer, and the one line that changes to give it memory.