Discover how to harness AI tools securely, ethically, and responsibly — balancing speed with security and ethics with innovation — while transforming your development lifecycle.
Dreamforce passes are going fast. Don’t miss the most valuable event in business. Register now.
Register to join Dreamforce in San Francisco, or stream it free on Salesforce+.
Dreamforce is almost here and passes are going fast. Don’t miss your last chance to save $400 by September 26.
Sessions
Explore Dreamforce 2025 sessions.
Browse 1,600+ sessions from 2025 by role, topic, or industry and get inspired for the innovation coming to Dreamforce 2026.
AI with Accountability: Build Fast, Code Smart, Stay Ethical
Required equipment: Salesforce Events Mobile App required. Please bring your headphones and use Live Session Audio to hear audio and view captions.
, Salesforce Architect, Community Speaker, Lead Salesforce Engineer at MongoDB, MongoDB
Role: Administrator, Architect, Developer
Product: Agentforce
Session Level: Intermediate
Session Type: Theater
Session Summary: The session explored the evolution of artificial intelligence in software development, particularly within the Salesforce ecosystem, and how it is transforming developer workflows. Key innovations include AI-assisted coding with tools like Einstein Copilot, which accelerates development by generating and editing code based on natural language prompts, and AI-powered code reviews, which identify performance bottlenecks and ensure adherence to best practices. However, the session also highlighted critical risks such as security and privacy concerns, model biases, and overreliance on AI tools, emphasizing the importance of implementing safeguards and maintaining human oversight. Attendees were provided with actionable strategies to mitigate these risks, including avoiding hard-coded sensitive information, using approved AI tools, and rigorously testing AI-generated outputs to ensure business alignment and scalability.
Key Takeaways:
• AI is revolutionizing Salesforce development by enabling faster, smarter workflows through tools like Einstein Copilot, which supports coding, debugging, and documentation generation with natural language prompts.
• To mitigate risks such as data exposure and model inaccuracies, developers should avoid inputting sensitive information into non-approved AI tools and ensure all AI-generated code aligns with Salesforce-specific best practices.
• Maintaining a balance between AI and manual coding is essential to prevent skill degradation, with developers encouraged to rigorously review and test AI-generated outputs to ensure accuracy and compliance.
Session Summary Feedback: Report a Concern
