Skip to main content
Skip to content
Menu

Codex Beginner 2 parts Updated

Map your coding tasks by model fit

You'll have a one-page visual matrix showing which types of coding work you do and which AI model or tool is strongest for each.

What you'll make

Coding Task-Model Fit Matrix

  1. Rows: Your 6-8 most common coding task types
  2. Columns: 3-4 AI models you tested
  3. Cells: Strength ratings and specific reasons
  4. Legend: Rating scale and decision criteria

Upload a screenshot or photo of your completed matrix — handdrawn, spreadsheet, or any visual format that shows the mappings

The 2 parts

Each part ends with a check you can see.

  1. Test Models Across Task Types

    Run your real coding work through multiple AI models to discover which excels at which type of task.

    Done when

    6+ coding tasks tested across 3+ models with documented results showing specific strengths and failures for each model-task combination.

  2. Build the Decision Matrix

    Transform your testing results into a visual matrix that makes model selection obvious for future coding work.

    Done when

    A visual matrix showing task-model mappings with decision criteria that you can reference in under 10 seconds for any new coding task.

    Capstone: you put together your Coding Task-Model Fit Matrix.

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

  • Run coding tasks on 3+ different AI models and document which model works best for which type of code you write
  • Create a visual matrix mapping your real coding work to the strongest AI model for each task type
  • Have tested criteria for choosing between models on future coding tasks based on task characteristics, not just preference

Who it's for

  • Developers who use multiple AI coding tools but haven't systematically compared their strengths
  • Engineers who want to optimize their AI coding workflow beyond just using whatever's convenient
  • Technical leads deciding which AI coding tools to standardize on for their team

What it won't cover

  • Setting up API keys or tool installation — assume you have access
  • Advanced prompt engineering for coding — this is about model selection, not prompt craft
  • Cost optimization or enterprise deployment decisions
  • Non-coding AI tasks like documentation or planning

Skills you'll practise

  • Comparative AI tool evaluation
  • Task-model fit analysis
  • Systematic testing methodology
  • Decision criteria development