AWS blog explains using decision models for AgentCore evaluations
What happened
On 5 November 2026, the AWS Machine Learning Blog published a post on using decision models with Amazon Bedrock AgentCore Evaluations for agent evaluation. According to the post, AgentCore Evaluations can connect to decision models through code-based evaluators, converting evaluation inputs into decision-model requests and turning probabilities back into evaluation results. Examples connect TypeSafe's managed decision model Jev and Strands Agents' open-source 2B-parameter model Strands Decider 2B, both of which support noul, choice and score question types. The report does not mention previous evaluation methods or comparison data.
Written by AI from the reports · updated 2 h ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogUse decision models with Amazon Bedrock AgentCore Evaluations
Some agent-evaluation questions are narrow and repeatable, and decision models answer exactly that kind of question. This post shows how to connect two decision models, Jev and Strands Decider, to Amazon Bedrock AgentCore Evaluations through code-based evaluators, and how to validate a decision-model check before you gate a release on it.
Heat of this event
Not enough continuous observations yet to draw a trend.