Skip to content
Tutorials· Tutorial

AWS Bedrock AgentCore receives extended custom evaluators

AWS is launching a new feature in Amazon Bedrock AgentCore that enables the creation of custom code-based evaluators.

By the Aheadline editorial team·7 juli 2026·2 min read·Source: AWS Machine Learning BlogVerifierad signalAI-generated
AWS Bedrock AgentCore receives extended custom evaluators
AWS Bedrock AgentCore receives extended custom evaluators
AWS Bedrock AgentCore receives extended custom evaluators
By · Policy- & EU-reporter
Last updated

What happened?

Amazon Bedrock AgentCore has been expanded with the capability to implement custom code-based evaluators. These evaluators can be developed using AWS Lambda and integrated to review agent functionality. There is the possibility to combine these with built-in evaluation tools.

Key facts

Lanseringsdatum22 maj 2024

”In this post, you will implement four Lambda-based custom code evaluators for a financial market-intelligence agent, register each with AgentCore, and run them in on-demand and online modes. You will also see how to combine custom code-based evaluators with built-in evaluators an”

— AWS Machine Learning Blog, Redaktion · AWS Machine Learning Blog

Why it matters

The feature means that developers can customise how AI agents are evaluated for specific use cases, such as financial market information. This allows for tailored control over agent performance and accuracy. System developers are thus provided with tools to ensure that agents meet business requirements, as well as to identify personally identifiable information (PII) and verify facts against external sources.

Who is affected?

Primarily affected are AI developers and companies using Amazon Bedrock to build and manage AI agents. They receive new tools to fine-tune and test their AI models. End users may also benefit indirectly through more reliable and secure AI applications.

What else you should know

The custom evaluators can be configured to run on-demand or continuously (online). This provides flexibility in how validation and monitoring occur.

Frequently asked questions

Quick answers about this story

Vad har hänt?
AWS har introducerat anpassade kodbaserade utvärderare i Amazon Bedrock AgentCore, vilket tillåter utvecklare att skapa egna utvärderingsverktyg med AWS Lambda för AI-agenter.
När hände det?
Funktionen lanserades den 22 maj 2024.
Varför spelar det roll?
Detta ger utvecklare möjlighet att finjustera och kontrollera AI-agenters prestanda och riktighet specifikt för sina egna behov, vilket leder till mer pålitliga AI-applikationer.
Nyheten handlar om
Amazon Web Services (AWS)Amazon BedrockAgentCoreAWS Lambda
Original source
AWS Machine Learning Blog·aws.amazon.com

The link opens in a new window and leads to the publisher's own site.

Verifierad signal

Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.

AI-verktyg i artikeln

LangChainLlamaIndex

Topics

#Agents
[ STAY UP TO DATE ]

Get similar news straight to your inbox

No affiliate linksCancel anytimeGDPR-friendly
[ Frequency ]
[ What do you want to read about? ]

You'll receive updates on 2 topics.

The reader's room

Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.

Sign in to submit a comment or question.

Loading comments…
How this affects you

Read the article through your role

  • Decide whether this affects strategy over 6–12 months or is just noise.
  • Discuss with leadership: do we own the right question or does ownership need to move?
  • Ask: what risk are we taking by NOT acting on this this quarter?

Generated angle — not editorial analysis of "AWS Bedrock AgentCore receives extended custom evaluators"