AWS Engineer Chambers: A Single Forward-Pass Decision Model Allows Agents to Skip Unnecessary Memory Retrieval
Mike Chambers, a Senior AI DevEx Engineer at AWS, presented a pattern at AGNTCon + MCPCon North America 2026: using a decider model to perform a lightweight judgment before an agent's memory retrieval. For simple inputs like greetings, the system skips retrieval calls entirely. The decider model returns calibrated probability scores via a single forward pass without generating free-form text, allowing it to be embedded in code branches like an if-statement with language understanding capabilities. Chambers emphasized that this experiment is still in its early stages and developers must verify the reliability of the scores themselves.
Say “good morning” to an AI agent, and it might search its long-term memory before saying hello back. Somewhere in that system, a service performs a semantic lookup to determine whether your greeting requires understanding your beverage preferences. Even if you take your coffee very seriously, this seems like a lot of infrastructure for two words.
Mike Chambers, a Senior AI DevEx Engineer at Amazon Web Services (AWS), presented a solution to The New Stack Editor-in-Chief Nick Lucchesi at AGNTCon + MCPCon North America 2026: using a decider model to handle the small judgments that accumulate inside an agent. These models are also known as decision models or System One models; they select from a fixed set of options or rate inputs, returning calibrated probabilities without generating free-form text. This concept was popularized by Jev of TypeSafe AI, and AWS’s Strands Labs released the open-source Strands Decider 2B, a model with two billion parameters, on October 1.
Chambers describes this approach as having an agentic-powered, language-aware if-statement within your code. Developers have used classifiers for years, but what distinguishes this generation of decider models is that general-purpose pretraining allows you to try them on new classification tasks without first training your own model. You provide natural-language context, ask a question, and receive a numerical score that the application uses to choose a branch. In the models Chambers describes, this score is returned in a single forward pass, with no token sequence requiring generation.