Skip to main content
Skip to content
Menu

Future of Work Intermediate 3 parts

Design and test an AI agent workflow for a repeatable task in your domain

You'll have a working agent pattern (prompt + tool integrations + feedback loop) that handles one end-to-end task with minimal human intervention, documented for your team.

What you'll make

Agent Workflow Blueprint

  1. Task Breakdown: human vs AI steps
  2. Tool Chain: what connects to what
  3. Testing Results: what worked and what didn't
  4. Handoff Instructions: how others can use this

The 3 parts

Each part ends with a check you can see.

  1. Map Your Automation Boundaries

    Break one recurring task into steps and identify which need human judgment vs which AI can handle.

    Done when

    You have a step-by-step breakdown of one task with clear human/AI boundaries and at least 3 steps identified for AI automation.

  2. Build Your Tool Chain

    Connect AI tools to handle your automatable steps and test each connection.

    Done when

    You have a working sequence of 3+ AI tools that can process your task data with documented inputs, outputs, and failure points.

  3. Test Edge Cases and Document Handoffs

    Run your workflow on problem cases and create instructions for others to use it.

    Done when

    You have documentation that enables a teammate to use your workflow, including 3+ tested edge cases and clear guidance on when to use human override.

    Capstone: you put together your Agent Workflow Blueprint.

Where this helps

An elective: a single lesson that sits outside rtwo's job certificates and doesn't count toward one.

About this lesson

What you'll be able to do

  • Build and test a working AI agent workflow that reduces manual work on one recurring task
  • Document workflow patterns your team can adapt to other tasks
  • Judge when agent automation helps vs creates more work than it saves

Who it's for

  • Operations professionals who handle repetitive workflows
  • Team leads looking to scale support functions
  • Anyone who does the same multi-step task weekly or daily

What it won't cover

  • Advanced programming or API development
  • Enterprise AI security policies
  • Multi-agent orchestration across departments

Skills you'll practise

  • Workflow decomposition
  • AI tool evaluation
  • Automation boundary-setting
  • Process documentation