Chain of Thought Architecting AI Agents: The Shift from Models to Systems | Aishwarya Srinivasan, Fireworks AI Head of AI Developer Relations
11 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
Models Are Parts Of Systems
- Treat LLMs as parts of software systems, not magic boxes that solve everything.
- Architect interactions, fallbacks, and boundaries across models and tools for reliability.
Limit Autonomy With Human Checkpoints
- Define human-in-the-loop checkpoints based on risk and user journey.
- Limit autonomy where failures have high impact and add deterministic review points.
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.