Skip to main content
Skip to content
Menu

Open Source Intermediate 4 parts

Extend an AI agent with custom tools your team actually uses

You'll have added at least two new capabilities to an AI agent framework that automate tasks your team repeats weekly, with clear documentation on how to add more.

What you'll make

Team Agent Deployment Guide

  1. Agent Setup: framework choice and configuration
  2. Custom Tools: what you built and why
  3. Performance Comparison: model testing results
  4. Expansion Process: how to add new capabilities

The 4 parts

Each part ends with a check you can see.

  1. Map Your Automation Targets

    Identify which of your team's weekly tasks could benefit from AI agent automation

    Done when

    You have 5+ weekly tasks ranked by automation potential with specific tool requirements for the top 3

  2. Deploy and Test Agent Framework

    Set up PI agent framework and test it with a simple custom tool for one of your target tasks

    Done when

    You have a working PI agent deployment with one custom tool that successfully automates part of a real team task

  3. Compare Models for Your Use Case

    Test multiple open source models on your specific tasks to find the best cost-performance fit

    Done when

    You have tested 3+ models on your actual tasks with documented performance and cost comparison

  4. Expand Agent Capabilities

    Add a second custom tool and document the process for future expansion

    Done when

    You have 2+ working custom tools and documented process that someone else could follow to add tool #3

    Capstone: you put together your Team Agent Deployment Guide.

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

  • Deploy a working AI agent with 2+ custom tools for your team's weekly tasks
  • Document a reusable process for adding new capabilities to your agent framework
  • Test and compare multiple open source models for your specific use case
  • Distinguish when to use local vs cloud models for your team's workflow

Who it's for

  • Development teams looking to automate repetitive workflows
  • Technical leads evaluating AI agent solutions
  • Teams already using AI tools who want more control and customization

What it won't cover

  • Building agents from scratch without frameworks
  • Training custom models
  • Enterprise deployment and scaling strategies
  • Advanced prompt engineering techniques

Skills you'll practise

  • Agent framework deployment
  • Custom tool integration
  • Model performance evaluation
  • Technical documentation
  • Cost-benefit analysis of local vs cloud models