Always free. For everyone.
AI Automation · Course outline

From a repeated task to a tested AI workflow.

20 modules and 60 lessons in 4 stages. Every lesson has real Python practice that runs in your browser and a short quiz. The course is free and open to everyone. For students, builders, and small teams. Start with basic Python variables, dictionaries, lists, functions, and loops. Use the Python course foundations if these are new to you. No AI or automation experience is assumed.

Start the first lesson
20 modules60 lessons20 guided practicals6 projects37 lesson hours
Before you begin: prerequisites, tools, and learning plan

For students, builders, and small teams. Start with basic Python variables, dictionaries, lists, functions, and loops. Use the Python course foundations if these are new to you. No AI or automation experience is assumed.

Each module has two lessons and one guided practical. Run a worked example, implement a function, pass input and failure checks, and answer two quiz questions. Plan 3 to 5 hours each week, plus time for six larger projects.

Required exercises use standard Python in the browser with fictional records and simulated AI responses. No paid account, API key, or external automation service is required. The first run downloads Python. Notebooks also work locally. An optional visual workflow plan can be mapped to a tool you already use, such as n8n or Make.

The lab does not call a live AI model, send messages, or connect your accounts. Simulations teach workflow logic, not measured model quality. Before a live pilot, add provider-specific authentication, durable state, evaluation, access controls, and approval for external actions.

Review Python foundations

Workflow foundations

Modules 01 to 05

MODULE 01

Find the right work to automate

Map a repeated task, choose a useful goal, and decide where AI belongs.

  1. Triggers, steps, and outcomes
  2. Rules, AI, and human decisions
  3. Practical: Measure a useful starting point
3 lessons1h 50m
MODULE 02

Work with records and decisions

Use small Python functions to clean inputs and route work.

  1. Clean a text field
  2. Build a new record
  3. Practical: Route a small request queue
3 lessons1h 50m
MODULE 03

Exchange and validate JSON

Read structured messages and reject invalid input before it spreads.

  1. Parse a JSON message
  2. Check required fields and types
  3. Practical: Separate valid and invalid intake
3 lessons1h 50m
MODULE 04

Handle triggers and duplicate events

Filter event types and prevent repeat deliveries from creating repeat work.

  1. Select events deliberately
  2. Keep the first delivery
  3. Practical: Build an event inbox
3 lessons1h 50m
MODULE 05

Understand APIs and HTTP

Represent requests and interpret responses without making live calls.

  1. Describe an API request
  2. Interpret response statuses
  3. Practical: Simulate an API adapter
3 lessons1h 50m

AI inputs and outputs

Modules 06 to 10

MODULE 06

Write prompts for repeatable tasks

Define the task, separate source data, and make missing information visible.

  1. Make the output contract explicit
  2. Separate instructions from source text
  3. Practical: Build a reusable prompt template
3 lessons1h 50m
MODULE 07

Validate AI output

Treat generated labels and JSON as proposals that must pass checks.

  1. Accept only known labels
  2. Check a structured prediction
  3. Practical: Parse, validate, then route
3 lessons1h 50m
MODULE 08

Build an AI-assisted triage flow

Compare a simple baseline with simulated predictions and review uncertain work.

  1. Start with a rule baseline
  2. Set an explicit review threshold
  3. Practical: Measure routing coverage
3 lessons1h 50m
MODULE 09

Extract facts with evidence

Preserve missing values and connect extracted fields to source text.

  1. Represent an unknown value
  2. Attach a source quote
  3. Practical: Check an extraction packet
3 lessons1h 50m
MODULE 10

Ground answers in approved sources

Retrieve relevant material, respect access, and abstain when support is missing.

  1. Retrieve a simple source
  2. Filter sources by access
  3. Practical: Abstain without supporting evidence
3 lessons1h 50m

Reliable automation

Modules 11 to 15

MODULE 11

Control tool use and agent loops

Validate tool proposals and bound the work an AI agent can request.

  1. Allow only named tools
  2. Bound the agent loop
  3. Practical: Build a restricted tool dispatcher
3 lessons1h 50m
MODULE 12

Add meaningful human approval

Tie approval to the exact draft and keep changed or expired work on hold.

  1. Require an explicit decision
  2. Bind approval to a version
  3. Practical: Enforce an approval gate
3 lessons1h 50m
MODULE 13

Recover from failures

Use bounded retries and separate temporary failures from permanent problems.

  1. Plan a backoff delay
  2. Classify retryable errors
  3. Practical: Finish or escalate a retry run
3 lessons1h 50m
MODULE 14

Save state and resume work

Track durable outcomes and design replay-safe steps.

  1. Resume from a checkpoint
  2. Choose an idempotency key
  3. Practical: Simulate an operation ledger
3 lessons1h 50m
MODULE 15

Schedule and batch work

Use explicit time zones and prepare bounded batches and useful digests.

  1. Compare aware timestamps
  2. Split a queue into batches
  3. Practical: Prepare a daily operations digest
3 lessons1h 50m

Testing and delivery

Modules 16 to 20

MODULE 16

Evaluate the whole workflow

Measure errors, review load, and regressions with fixed examples.

  1. Calculate exact-match accuracy
  2. Measure false automatic routes
  3. Practical: Compare a candidate with a baseline
3 lessons1h 50m
MODULE 17

Track cost and operational health

Set budgets, record useful logs, and notice when a workflow degrades.

  1. Estimate a run cost
  2. Keep useful, minimal logs
  3. Practical: Stop when a budget or error limit is reached
3 lessons1h 50m
MODULE 18

Protect data and action boundaries

Treat external text as data and keep sensitive fields out of unnecessary steps.

  1. Select the minimum model input
  2. Ignore actions embedded in model output
  3. Practical: Enforce a destination allowlist
3 lessons1h 50m
MODULE 19

Move from a lab to a small pilot

Map the workflow into visual tools and prepare a controlled release.

  1. Map logic to visual workflow nodes
  2. Choose a release mode
  3. Practical: Review a pilot readiness record
3 lessons1h 50m
MODULE 20

Deliver an automation capstone

Combine the course ideas into a tested workflow and a clear handover.

  1. Orchestrate a draft workflow
  2. Report test evidence honestly
  3. Practical: Finish the workshop assistant
3 lessons1h 50m
ABOUT THE LEARNING LAB

Free, open and run by a nonprofit.

This page is part of AI Automation, a free course of 20 modules and 60 lessons in the engineering.fit( ) Learning Lab. The Learning Lab is built and run by engineering.fit( ), a nonprofit founded by Abdullateef Opeyemi Bakare that helps African engineering students gain research experience. You do not need an account or pay a fee to learn.

Course outline · Project lab · Visit engineering-fit.org