Reminder: for the next AGT event, we're looking for presenters and panelists to discuss and demo successful AI projects and what it takes to make them work. If you'd like to participate or can suggest someone, fill out this form.

Hi all, here are today's three links:

Making Sense of Memory in AI Agents

Leonie Monigatti goes over how agents remember, recall, and forget:

Memory in AI agents is the ability to remember and recall important information across multiple user interactions. This ability enables agents to learn from feedback and adapt to user preferences, thereby enhancing the system’s performance and improving the user experience.

Agentic AI advances

McKinsey provides an update on where AI agents are being used in industry:

AI is becoming widely used, but only a minority of companies are scaling more sophisticated capabilities, such as agents, into workstreams in ways that can transform their businesses.

Demystifying evals for AI agents

Anthropic with a thorough breakdown of agent evaluations:

Teams without evals get bogged down in reactive loops - fixing one failure, creating another, unable to distinguish real regressions from noise. Teams that invest early find the opposite: development accelerates as failures become test cases, test cases prevent regressions, and metrics replace guesswork.

If you have any agent-related links you'd like to feature, let me know!

Cheers,
Ivan