Madeline Egan
A member of the Azure Cosmos DB team and a host of the 'Code with Azure Cosmos DB' video series.
Timeline (last 90 days)
Azure Cosmos DB product manager Madeline Egan points out that by default most AI applications start with no persistent memory, no preferences, no history, and no context.
Marko Haari and Madeline Egan said in the video that the root cause of AI Agent production problems is often not insufficient model capability, but the team's lack of visibility into the agent's actual behavior.
Egan believes the most expensive Agent is rarely the optimal choice, and optimization should narrow the gap between actual spending and user experience.
All Facts (3)
Azure Cosmos DB product manager Madeline Egan points out that by default most AI applications start with no persistent memory, no preferences, no history, and no context.
50%UnverifiedMarko Haari and Madeline Egan said in the video that the root cause of AI Agent production problems is often not insufficient model capability, but the team's lack of visibility into the agent's actual behavior.
50%UnverifiedEgan believes the most expensive Agent is rarely the optimal choice, and optimization should narrow the gap between actual spending and user experience.
50%