Chain of Thought | AI Agents, Infrastructure & Engineering Architecting AI Agents: The Shift from Models to Systems | Aishwarya Srinivasan
15 snips
Oct 8, 2025 Aishwarya Srinivasan, Head of AI Developer Relations at Fireworks AI, dives into the intricate world of building robust AI agents. She advocates for a shift from model-centric thinking to viewing AI as a complete software system. Aish discusses the evolution from prompt to context engineering, emphasizing high-quality data and responsible AI. She also explores the pros and cons of open-source models, the importance of evaluation-driven development, and strategies for managing agent autonomy. Her insights provide a roadmap for navigating the future of AI.
AI Snips
Chapters
Transcript
Episode notes
Context Engineering Replaces Prompt Tricks
- Context engineering replaces prompt engineering as systems grow multi-model and multi-tool.
- Data, memory, tool calls and traces make up the context that shapes agent behavior.
Sanitize Data And Curate Feedback
- Prioritize high-quality, sanitized training and eval data and filter feedback before RLHF.
- Avoid training on noisy feedback to prevent vulnerabilities like reward hacking.
Make Every Model Step Observable
- Quantify and log each model step to enable traceability and root-cause analysis.
- Checkpoints and evaluation at each stage let teams find and fix failures faster.