"How much memory does an agent actually need?"
Memory is the feature everyone asks for and almost nobody needs as much of as they think. Most agent tasks are done in one sitting and should forget everything afterwards. Here is how I separate state from memory, why summarisation is riskier than it looks, and when persistent memory genuinely earns its keep.
"Can it remember things?" is usually the second question I get asked about any agent, right after "what can it do?". The honest answer is that most agents should remember far less than their owners want them to, and the ones that remember too much develop problems that are much harder to debug than forgetfulness. Before adding memory to anything, it is worth being precise about what the word actually means, because three different things hide behind it.
Have an AI feature stuck between demo and production?
The gap — reliability, evals, cost control, the plumbing that keeps it running unattended — is exactly the work I do. If that sounds familiar, a short conversation is usually enough to point you the right way.
Book a free consultation