Every time you send a message to an AI, a precise sequence of events unfolds. Most users never see it. Understanding what happens inside that cycle isn’t just interesting; it’s foundational to using AI more effectively, managing costs, and knowing why longer conversations behave differently than fresh ones. This infographic maps the full journey of a single turn.
⬇Download the PDFKey Takeaways
Comprehension of a "turn" is foundational to understanding the concepts of token engineering and token usage. Here are the four things worth internalizing:
- Project instructions are re-read every turn. Any custom instructions you’ve set are sent to the model again with every single message, and they occupy space in the context window each time. Providers may cache the unchanged portion to reduce what you pay for it, but the instructions are still part of the input on every turn.
- Conversation history grows; input tokens snowball. Every prior message in the thread gets included in the context each turn. The longer the conversation, the more tokens are consumed just to carry the history forward.
- Tool calls add extra input and output cycles. When an AI uses a tool (like web search or code execution), that triggers a full additional loop; the tool result re-enters as new input, generating new output tokens before you see a final response.
- The context window is finite. Window sizes vary widely by model, from tens of thousands of tokens to a million or more, and they change as vendors ship new versions. Whatever the limit, once it is approached, older messages get truncated or dropped, which can cause the AI to "forget" earlier parts of the conversation.
Every article here is written to our AI standard. How we use AI →
