Aishwarya Srinivasan
Fireworks AI
1 episode on Chain of Thought
At the time of the conversation, Aishwarya Srinivasan was Head of AI Developer Relations at Fireworks AI, with a large following for her AI content on LinkedIn. On Chain of Thought she argued that most agents are built backwards, starting from models instead of system architecture, and walked through the move from prompt engineering to context engineering.
AI AgentsAgent MemoryOpen Source AIAI Evaluation & ReliabilityAI ObservabilityContext ManagementEnterprise AIAI Engineering
Episodes
In their words
inside a large language model and through the system. People who have not done that or people who are coming from non machine learning backgrounds, I feel primarily are confused, are figuring out because they have a solid business need of why they need to build this product, but they lack that engineering expertise.
Architecting AI Agents: The Shift from Models to Systems | Aishwarya Srinivasan