Skip to content
InfratoApp
← Learn for your role

AI for data analysts

Use machine learning and AI assistants on your own data, and know when the answer does not match the numbers.

Begin with machine learning basics, move to working with data in Python and Fabric, and finish with building and checking models.

intermediate10 stepsabout 20 h 38 min of listed material

Foundations

What you need to know before you build.

  1. Infrato courseAI for Data Analysts56 min

    Start here: using an assistant for SQL and analysis, and checking every number before you share it.

  2. Infrato courseUse AI Safely at Work: Privacy and Data55 min

    Sort the data you handle into never, ask first and fine before you paste any of it.

  3. Google · Course
    Machine Learning Crash Course
    Price not listed

    Google’s course on machine learning basics.

  4. Microsoft · Course
    Machine Learning for Beginners
    beginnerFree

    A lesson-by-lesson machine learning course using Python.

Build

Make the thing.

  1. Microsoft Azure · Course
    Introduction to machine learning with Python and Azure Notebooks
    beginnerFree131 min

    Machine learning with Python in notebooks.

  2. Infrato courseCheck the Output: Evaluate What AI Gives You55 min

    Build a small repeatable test for an AI result you rely on, awkward cases included.

  3. Microsoft Azure · Course
    Prepare AI-ready analytics data in Microsoft Fabric
    intermediateFree233 min

    Preparing analytics data in Microsoft Fabric.

Extend

Check it, harden it, go further.

  1. Microsoft Azure · Course
    Create machine learning models
    intermediateFree379 min

    Building machine learning models.

  2. Microsoft Azure · Course
    Implement a data science and machine learning solution for AI in Microsoft Fabric
    beginnerFree329 min

    A data science and machine learning solution in Microsoft Fabric.

  3. Stanford University · Course
    CS229: Machine Learning
    Price not listed

    Stanford’s machine learning course, for the underlying methods.

Tools to try

Products from each vendor’s own site, listed by name and link only. We have not tested them, they are not endorsements, and we are not affiliated with the vendors. Prices and features change, so check the vendor’s page.

There are more by what you use them for: AI tools worth learning.

Agents and MCP servers for this role

An MCP server runs code with your accounts and can act in them. Read what each one can reach, and which credentials it asks for, before you connect it. These are picked from our directories by hand, not ranked, and are not endorsements.

MCP servers

  • postgres-mcp

    Read and write access to Postgres, with performance analysis.

    Reaches: postgres. No credentials listed.

  • mcp-server-mysql

    Read-only access to MySQL.

    Reaches: mysql. No credentials listed.

  • mcp-google-sheets

    Google Drive and Google Sheets from an assistant.

    Reaches: google, googledrive, googlesheets. Asks for: GOOGLE_APPLICATION_CREDENTIALS.

  • excel-mcp-server

    Excel file manipulation.

    Reaches: excel. Asks for: EXCEL_MCP_AUTH_TOKEN.

  • dbt-mcp

    A server for working with dbt.

    Reach not listed. No credentials listed.

  • tableau-mcp

    Tableau’s own MCP server.

    Reach not listed. No credentials listed.

  • mcp-clickhouse

    Connects ClickHouse to an assistant.

    Reaches: clickhouse, fastmcp. Asks for: CLICKHOUSE_CLIENT_CERT_KEY, CLICKHOUSE_MCP_AUTH_TOKEN, CLICKHOUSE_PASSWORD, CLIENT_CONFIG_OVERRIDES_KEY, FASTMCP_SERVER_AUTH_AZURE_CLIENT_SECRET.

Agent skills

Your project

Answer a question from a messy dataset

Take a dataset you are allowed to share. Ask an AI assistant for an analysis plan, run the analysis yourself, then list every place where the claims made by the assistant did not match the data.

The order and the notes are Infrato's own picks. The resources are made by their providers, open at their own sites, and can change; prices, levels and durations are the provider's. Infrato is not affiliated with the providers listed.