Message History
After every answer we hang up - the next call starts from zero. Context only exists because we read the full transcript aloud at the start of every call.
Basics
Free for everyone: the concept, the analogy, the why.
The call from part 1 is stateless. To hold a conversation, the harness keeps a transcript and reads it out from the top on every call. That's the message history - and the reason "memory" means something entirely different for LLMs than you'd expect.
Every LLM call is stateless. For an agent to stay coherent across steps you must send the message history along - and you pay for it in tokens. Memory is therefore always a trade-off: enough context for coherence, little enough for cost and focus.
This tier is currently being written. Here is the outline it will follow:
- The messages array - Roles system, user and assistant - how separate calls become a conversation.
- Reading it out costs - Why every turn carries the full history along, and what that means in tokens.
- The stress test - Drop one message from the log and watch what the agent forgets instantly.
Try it interactively
With a free account: hands-on experiments and the quiz for this phase.
Going deeper
With a free account: experiments, quizzes and the deeper material.
Deep dive
For pro members: the depth for everyone who wants to actually build it.