Dev Interrupted Making Sense of Agentic AI | ThoughtWorks Birgitta Boeckeler
12 snips
Nov 12, 2024 Birgitta Boeckeler, Global Lead for AI Assisted Software Delivery at ThoughtWorks, dives into the transformative potential of AI in software development. She shares her insights on agentic AI, discussing its real-world applications and the limitations developers face, especially with legacy codes. Birgitta also emphasizes the importance of clear use cases for successful AI integration and the balance needed to avoid tool fatigue. Joining her, Dan Lines highlights how engineering leaders can measure AI's impact on their teams and refine coding practices for better outcomes.
AI Snips
Chapters
Transcript
Episode notes
Legacy Code Experiment
- Birgitta Boeckeler used a real-world open-source medical records system (BAMNI/OpenMRS) to test AI tools.
- She simulated a new developer trying to understand the codebase and implement a ticket, focusing on practical application.
AI Needs Examples
- AI models often struggle without concrete examples to reference.
- Test generation works better with existing tests and established mocking setups.
Focus on Specific Problems
- Focus on specific problems for agentic AI, like straightforward code additions within existing codebases.
- Avoid broad, unrealistic expectations of AI solving any software problem.