Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: Lin-dev/introduction-to-ai-engineering
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Choose a base ref
...
head repository: obinnaokechukwu/introduction-to-ai-engineering
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 3 commits
  • 2 files changed
  • 1 contributor

Commits on Jul 22, 2025

  1. Remove incorrect Constitutional AI section from Chapter 10 

    The Constitutional AI section was incorrectly described and not properly related
to prompting strategies. The implementation example showed a safety-focused
prompt pattern rather than actual Constitutional AI techniques.

Changes made:
- Removed entire 'Strategy 4: Constitutional AI' section including explanation,
  code example, and usage guidelines
- Updated Learning Objectives to remove Constitutional AI bullet point
- Updated Conclusion to remove Constitutional AI references and clean up
  the chaining example
- Chapter now focuses on three core advanced prompting strategies:
  Self-Consistency, Tree-of-Thought, and ReAct

This ensures the chapter content is accurate and properly focused on
actual prompting strategies that readers can implement.
    @obinnaokechukwu
    obinnaokechukwu committed Jul 22, 2025
    Configuration menu
    Copy the full SHA
    a691a8b View commit details
    Browse the repository at this point in the history

  2. Add Multi-Agent Debate and Reflexion techniques to Chapter 10 

    Added two new advanced prompting strategies to complement existing techniques:

Multi-Agent Debate:
- Creates multiple AI agents with different perspectives (optimistic, conservative, practical)
- Implements structured debate with initial views, debate rounds, and final synthesis
- Reduces bias and improves robustness for complex decisions
- Includes complete Python implementation with example usage

Reflexion:
- Enables AI agents to reflect on their own reasoning and improve iteratively
- Implements three-phase workflow: solution generation, self-reflection, iterative improvement
- Particularly valuable for complex problems where initial solutions are likely incomplete
- Includes complete Python implementation with reflection history tracking

Both techniques follow the book's pattern of conceptual explanation before implementation.
Updated learning objectives and conclusion to include the new strategies.
    @obinnaokechukwu
    obinnaokechukwu committed Jul 22, 2025
    Configuration menu
    Copy the full SHA
    ab457be View commit details
    Browse the repository at this point in the history

  3. Update README.md with new Chapter 10 techniques and resources 

    Updated Chapter 10 description to include the new advanced prompting strategies:
- Multi-Agent Debate for reducing bias and improving robustness
- Reflexion for iterative self-improvement
- Enhanced descriptions for existing techniques

Added PromptingGuide.ai to the Prompt Engineering resources section
as a comprehensive reference for prompting techniques.
    @obinnaokechukwu
    obinnaokechukwu committed Jul 22, 2025
    Configuration menu
    Copy the full SHA
    a085a42 View commit details
    Browse the repository at this point in the history
Loading