Moving from chat-based prompting to lightweight scripting and automation.
Training Format
Hybrid: online and in-person workshops.
Hours
~6h (core modules)
Language
All training will be in English, with Portuguese and Spanish translations available.
Certificate
A certificate from EIT Urban Mobility. is awarded upon completion of the online course(s).
Who is this course for?
Who is AIM4Mobility addressed to?

Interested in moving from chat-based prompting to real automation?
COURSE OBJECTIVES
At the end of the course you'll be able to
What will the participants get from the course
Apply
a decision framework to determine whether a given mobility task is better handled by chat-based prompting or Python scripting.
Connect
to LLM APIs (e.g., OpenAI, Anthropic) to automate text-based tasks such as summarisation and classification.
Write and run
simple Python scripts for file and data manipulation in Google Colab, using AI coding assistants to generate, debug, and modify code.
Combine
Python scripting and AI API calls into short automation sequences that solve a practical mobility data task end-to-end.
Process
urban mobility datasets programmatically — reading, filtering, and summarising data using Python with AI assistance.
Build (optional capstone)
an AI-assisted automation script for a self-chosen mobility data task.
MOBILLITY METHODOLOGY
A two-part journey: learn online, then apply it in person.
MODULES
Course structure and modules
MODULE 1 – Why Script?
Focus: Chat vs. script — the conceptual foundation
This module establishes what scripting unlocks beyond chat-based interaction.
This module establishes what scripting unlocks beyond chat-based interaction.
Key Themes: A decision framework for choosing chat vs. script, and a hands-on side-by-side comparison on a real mobility task.
Outcome: Confidence in recognising which of your daily tasks are better solved by a short script than a chat prompt.
MODULE 2 – First Steps with Python
Focus: Foundational syntax, taught through mobility-themed example.
This module builds the basics of Python, from Colab setup onward.
Key Themes: Google Colab setup, variables and data types, string manipulation, conditionals, and your first AI-assisted coding exercise.
Outcome: Ability to read and adapt simple Python code with an AI assistant at your side.
MODULE 3 – Collections, Loops & Functions
Focus: The building blocks for batch processing
This module introduces the data structures and control patterns needed to process many records at once.
Key Themes: Lists, dictionaries, loops, and functions.
Outcome: Ability to write short scripts that repeat an action across a batch of data.
MODULE 4 – Libraries, Files & AI-Assisted Coding
Focus: The first real automation payoff
This module delivers the motivational anchor of the course: automating a batch file task you recognise from daily work.
Key Themes: External libraries, file input/output, batch file automation, and the formal AI-assisted coding workflow — understand, modify, run.
Outcome: A working batch file automation script, and a first real feel for what automation can do.
MODULE 5 – Processing Mobility Data
Focus: Python for real mobility datasets
This module applies Python to genuine mobility data.
Key Themes: Loading CSV data with pandas, filtering and summarising dataframes, and processing Eurostat transport statistics and fleet records.
Outcome: Ability to turn a raw mobility CSV into a clean, summarised dataset with AI-assisted code.
MODULE 6 – Connecting to AI APIs
Focus: Python talking to AI
This module connects your scripts to large language models directly.
Key Themes: What an API is, making LLM API calls, designing prompts for automation, processing structured responses, and building a batch text-processing script.
Outcome: A script that calls an LLM API to summarise or classify mobility-related text at scale.
MODULE 7 – End-to-End Automation
Focus: Bringing it all together
This module synthesises scripting and AI APIs into complete workflows.
This module synthesises scripting and AI APIs into complete workflows.
Key Themes: Two-step automation workflows, full end-to-end pipelines combining data and AI, and a guided walkthrough of a complete mobility automation.
Outcome: A complete, working automation pipeline that you built and understand end-to-end.
MODULE 8 – Capstone (optional)
Focus: Independent application
The Capstone is where the course's patterns meet a self-chosen, real mobility problem.
The Capstone is where the course's patterns meet a self-chosen, real mobility problem.
Key Themes: Scoping your own project and selecting relevant patterns, then adapting and combining course material into a self-directed automation.
Outcome: A working automation script for a mobility task of your choosing, demonstrating scripting, API integration, and data processing skills.
WORKSHOPS
Apply what you've learned online, in person.
MODULES
Brought to you by:
CERTIFICATE OF COMPLETION
Interested in learning how to use LLM and AI more effectively in urban mobility?
This project is supported by EIT Urban Mobility, an initiative of the European Institute of Innovation and Technology (EIT), a body of the European Union. EIT Urban Mobility acts to accelerate positive change on mobility to make urban spaces more liveable. Learn more: eiturbanmobility.eu







