AI in the Software Lifecycle: Opportunities and Limits
summary
Speakers from Crédit Agricole describe how AI tools are being introduced across the software lifecycle—from writing specifications, generating code, testing and deployment to production monitoring—naming use cases and concrete integration approaches in development pipelines. They explain which practices change application delivery, the operational and trust-related challenges encountered in a banking context, and practical mitigations and levers to accelerate responsible AI adoption in delivery teams.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 4:54Dev challenges
- 7:22AI for requirements
- 12:17AI design standards
- 14:45Automated acceptance
- 18:17AI code dev & review
- 20:41AI test automation
- 23:58AI deployment impact
- 24:19AI specs & emerging
- 27:45Generative AI limits
- 32:19AI creativity best practices
- 36:12Conclusion
- 38:20Q&A
related talks
19mAI in the trenches: Real-world wins without breaking things
31mAI & Finance - How to Achieve Scalable Impact
37mAI Under Control: accelerating safely
13mAI as a Strategic Asset: Building Competitive Advantage
26mAI in Use: Industry Perspectives
01mAI Is Changing How We Developer Software!
42mAI for IT: Cost Reduction and Activity Optimization
44mPanel Discussion: The BFSI Playbook - Scaling AI with Trust and Quality