Skip to content

[Issue 2332] Create "Software Engineering in the Age of AI" topic outline #2337

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 5 commits into from
May 6, 2025
Merged

[Issue 2332] Create "Software Engineering in the Age of AI" topic outline #2337

merged 5 commits into from
May 6, 2025

Conversation

daaimah123
Copy link
Collaborator

📝 Description

This PR adds a new comprehensive topic outline focused on helping our program population understand and thrive in software engineering roles in the age of AI. The outline addresses concerns about AI-generated code and provides practical guidance on developing skills that complement rather than compete with AI capabilities.

🔂 Changes Made

  • Added a new topic outline markdown file
  • Created a structured curriculum with:
    • Table of contents with hyperlinks
    • "Specific Things to Learn" section highlighting essential skills
    • Four detailed interactive activities with guided practice
    • Common misconceptions section
    • Starter code examples for activities

⚙️ Related Issue

Issue Number: #2332

🍏 Type of Change

New Topic Outline

🎁 Acceptance Criteria

  • Topic outline addresses the core questions from the issue (role of SWE with AI-generated code, career opportunities, key tech skills)
  • Content is structured according to Techtonica's curriculum format with all required sections
  • Activities are interactive, guided, and include specific time allocations
  • "Specific Things to Learn" section includes clear calls to action for continued learning
  • Starter code examples are provided for relevant activities

🧪 How to test or what to evaluate

  1. Review the topic outline for completeness and alignment with the issue requirements
  2. Verify that all links to existing Techtonica curriculum are correct and functional
  3. Evaluate the activities for practicality and educational value:
    • Activity 1: Ensure the AI tool exploration exercise is feasible with commonly available tools
    • Activity 2: Check that the problem-solving scenarios are realistic and appropriately challenging
    • Activity 3: Review the starter code for intentional issues that are educational to identify
    • Activity 4: Assess whether the career development planning exercise provides actionable guidance
  4. Test the table of contents links to ensure they navigate to the correct sections

@daaimah123 daaimah123 self-assigned this Apr 30, 2025
@daaimah123 daaimah123 assigned daaimah123 and unassigned daaimah123 Apr 30, 2025
@daaimah123 daaimah123 linked an issue May 1, 2025 that may be closed by this pull request
Create a new topic outline about relevant SWE skills in the age of AI #2332
Closed
MichelleGlauser
MichelleGlauser reviewed May 1, 2025
View reviewed changes
Copy link
Member

@MichelleGlauser MichelleGlauser left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could be good to get @gsong's eyes on this.

@daaimah123 daaimah123 requested a review from gsong May 1, 2025 17:14
@gsong
Copy link
Collaborator

gsong commented May 2, 2025 •
edited
Loading

This is fantastic. I have the following feedback:

  • Understanding the different capabilities of models and why they matter:
    • Token count
    • Reasoning/hybrid
    • STEM
    • Multimodality
    • Research
  • Embrace the concept of hybrid team, where your co-workers are different models—know which model to collaborate with for which tasks. Expert mode: orchestrate multiple models to collaborate on a single task.
  • How to best provide context for solving problems? This remains the most important skill regardless of model and problem, except for trivial problems. This is worth diving into as it makes a world of difference—identifying how much context to give the model to solve non-trivial problems. E.g. how would you upgrade a package where there are breaking changes?
  • Why not use models to help solve some of the tasks in the lesson? E.g. collaborate with a reasoning model to flesh out requirements.
  • An additional exercise to consider, how would you use AI to help understand a codebase? How would you use AI to generate a README for a medium sized repo?
  • One thing I don't see emphasized is how do you help a model validate its own work? Perhaps in cases where TDD is obvious, ask the model to write the tests first and validate its own code against the test cases? E.g. email value validity.

@daaimah123
expand "specific things to learn" section
7a5934a 
I've updated the "Specific Things to Learn" section to include all the suggested feedback

Understanding different model capabilities:
1. Added a new subsection "Understanding AI Model Capabilities and Limitations" with detailed information about token count, reasoning/hybrid models, STEM capabilities, multimodality, and research capabilities
2. Each capability includes why it matters, key concepts, and specific action items

Hybrid team concept:
1. Created a new subsection "Working with AI as Team Members" that covers the hybrid team concept
2. Added content on model selection for different tasks
3. Included information on multi-model orchestration for complex problems

Context provision for problem-solving:
1. Added a dedicated section on "Effective Context Provision" that explains why context matters
2. Included specific examples like package upgrades with breaking changes
3. Added action items for experimenting with different context formats

Using models to help solve tasks:
1. Added a note in the "Requirements Gathering and Refinement" section about collaborating with reasoning models to flesh out requirements
2. Incorporated this concept throughout various action items

Using AI to understand codebases and generate documentation:
1. Added a new subsection "Codebase Understanding and Documentation" under Advanced AI Collaboration Techniques
2. Included specific action items for using AI to analyze codebases and generate READMEs

Helping models validate their own work:
1. Added a new subsection "AI Self-Validation Techniques" that covers test-driven development with AI
2. Included the specific example of email validation with test cases
3. Added action items for creating workflows where AI generates tests before implementation
@daaimah123
Copy link
Collaborator Author

@gsong I have incorporated your feedback in 7a5934a, these are really powerful additions that I have learned painfully overtime and didn't think to include! 🙏🏾

@daaimah123 daaimah123 merged commit 7b998cb into main May 6, 2025
@daaimah123 daaimah123 deleted the swe-age-of-ai branch May 6, 2025 06:26
@github-project-automation github-project-automation bot moved this from Needs Reviewed to Done in Open-Source Curriculum TO-DO Board May 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@MichelleGlauser MichelleGlauser MichelleGlauser left review comments

@gsong gsong gsong approved these changes

@monikkaelyse monikkaelyse Awaiting requested review from monikkaelyse

@kaylahrose kaylahrose Awaiting requested review from kaylahrose

Assignees

@daaimah123 daaimah123

Labels
None yet
Projects
Open-Source Curriculum TO-DO Board
Status: Done
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Create a new topic outline about relevant SWE skills in the age of AI
3 participants
@daaimah123 @gsong @MichelleGlauser