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
Latest episode with Aishwarya Srinivasan · EP 42
Architecting AI Agents: The Shift from Models to Systems | Aishwarya Srinivasan
Aishwarya Srinivasan, Fireworks AI ·
Episodes
In their words
I think vision is definitely one of the areas where it is harder for the open source models, at least the ones that are out there compared to the proprietary models which are available in the market. Apart from that, yes, there are some level of performance gap that comes with how open source model look like on the benchmarks that we have publicly available.
Architecting AI Agents: The Shift from Models to Systems | Aishwarya Srinivasan