Create better prompts for o1

30 of january of 2025

Let's see how to do prompt engineering with o1 using an example.

Goal

I want a list of the best medium-length hiking trails less than two hours from Madrid.

Return Format

Each trail should offer a unique and exciting adventure and be relatively unknown.

For each route, return the name of the route as you would find it on AllTrails, and then provide the starting address of the route, the ending address of the route, the distance, the driving time, the duration of the route, and what makes it a unique and exciting adventure.

Return the top 3.

Warnings

Make sure the trail name is correct, that the trail actually exists, and that the time is accurate.

Context

For context: my family and I go on a lot of hikes! We've done practically all the local hikes around Madrid. We definitely want to get out of the city. We recently hiked up Mount Guadarrama, from the bottom of the stairs to the viewpoint overlooking the lake.
It was very long, and this weekend we'd like to do something different. We love delicious food. One thing I loved about the Guadarrama hike was that it ended with a celebration (getting to the city for breakfast!).

Continue reading

MCP Elicitation: Implementing Elicitation in Servers with FastMCP and Python

Learn how to implement elicitation in MCP (Model Context Protocol) servers with FastMCP. Complete step-by-step tutorial to create an intelligent travel booking agent that requests user information interactively. Includes server and client code, virtual environment setup with uv, and practical elicitation examples for real-time user data collection.

MCP Durability: Server and Client with Persistence for Long-Running Tasks

Learn to build durable MCP server and client for long-running tasks with persistence. Complete Model Context Protocol tutorial featuring SQLite data persistence, background task management, and real-time monitoring. Implement data migration, batch processing, and ML model training that survive server restarts. Python code examples using FastMCP, resources, tools, and durability patterns for enterprise applications.

Resumable MCP: How to Build Servers and Clients with Automatic Checkpoints

Learn to build resumable MCP servers and clients with automatic checkpoint capabilities. Complete tutorial on implementing task interruption handling, state persistence, and recovery for long-running processes in Model Control Protocol. Includes practical code with FastMCP, persistent session management, and real-world examples for processes that can be interrupted and resumed from where they left off.

Last posts -->

Have you seen these projects?

Horeca chatbot

Naviground

Subtify

View all projects -->

Do you want to apply AI in your project? Contact me!

Do you want to improve with these tips?

Memory profiler

See the memory usage of a script

DataLoader with pin_memory and num_workers

Increase DataLoader performance with pin_memory and num_workers

py-smi

Python library to get GPU data like `nvidia-smi`

Last tips -->

Use this locally

Hugging Face spaces allow us to run models with very simple demos, but what if the demo breaks? Or if the user deletes it? That's why I've created docker containers with some interesting spaces, to be able to use them locally, whatever happens. In fact, if you click on any project view button, it may take you to a space that doesn't work.