AgentCore Evaluations now supports evaluating production agents across diverse frameworks like LangGraph, OpenAI Agents SDK, LlamaIndex, Google ADK, and more using OpenTelemetry standards. Consistent evaluation without framework-specific code! 🚀🔍 #AgentCore #OpenTelemetry #EvaluationService

Amazon Bedrock AgentCore Runtime V2 が登場、V1 との違いを整理してみた

#AWS #AgentCore

AWS Migration Guide for Healthcare Agents: Moving from Self-Managed ECS to Bedrock AgentCore Runtime

🤖 IA: It's not clickbait ✅
👥 Users: It's not clickbait ✅

#aws #agentcore #migration

👇👇👇

✍️ New blog post by Kevin Lupera

Optimicé el prompt de mi agente de IA con AWS AgentCore (y esto fue lo que pasó)

#aws #agents #agentcore #ai

https://lckhd.eu/kEo1g3

#Bedrock #AgentCore #Serverless #Agents

I like building projects with AgentCore so it's interesting to see a new AgentCore runtime.

Unit 42 finds AWS AgentCore Harness default settings allow credential exfiltration via prompt injection. The built-in 'shell' tool, enabled by default, can be abused to steal plaintext credentials. #AWS #AgentCore #AIsecurity #CloudSecurity

🌐 cyber[.]netsecops[.]io

Jevとは何か？ 従来型LLMやAIエージェントとの違いを理解する

#Jev #AIエージェント #LLM #BedrockAgentCore #AgentCore

✍️ New blog post by Davide De Sio

Deploying a real-time voice agent with AgentCore Runtime and Amplify Gen 2

#ai #aws #agentcore #amplify

AgentCoreゲートウェイの3LOが簡単なるかもしれないコンセントポータルで四苦八苦

#AWS #AgentCore #MCP #3lo #cognito

https://lckhd.eu/6ksJLI

#Bedrock #AgentCore #OAuth #MCP

Teams are building agents that call GitHub, Slack, or other apps that need OAuth grants bound to the right identity. AgentCore now hosts that flow for you, including the callback endpoint, browser sessions, and the final

Amazon Bedrock AgentCoreを活用したインタラクティブなMCPアプリケーション構築の技術報告

Amazon Bedrock AgentCoreでインタラクティブな多段階会話アプリを構築。

#AmazonBedrock #AgentCore #生成AI #LLM #会話型AI

"Amazon Bedrock AgentCore now offers runtime domain and date filtering for Web Search, providing per-call control over sources and publication dates. New features available in Europe and Asia Pacific regions. 🔍📅 #Amazon #AgentCore #WebSearch"

AWS AgentCore Evaluationsを使ってAIエージェントを評価してみた

#AWS #AgentCore #StrandsAgents #Python #AIエージェント

【AWS】Bedrock Managed Knowledge Baseの自動同期スケジューリングを試してみました

#AWS #bedrock #AgentCore #rag

https://lckhd.eu/j2lOWp

#Bedrock #AgentCore #MCP #Serverless #ConversationalAI

It helps to see demo code to understand how cloud services fit together.

https://lckhd.eu/iRRJG2

#Bedrock #AgentCore #Agents #AWS #Serverlesse

We've likely all seen cases where LLMs are really bad at math or other things that seem simple to humans. 🧵

【AgentCore Memory】「何かおかしい。なんとなくそんな気がした」〜AIエージェントはエンドレスエイトに既視感を抱けるのか〜

#AgentCore #Claude #StrandsAgents #bedrock #生成AI

https://lckhd.eu/GRFqwa

#DynamoDB #StrandsAgents #AgentCore #Serverless #Agents

Agents are more useful when they remember things across invocations. Strands agents on Lambda or AgentCore runtime forget everything when torn down, so session state, oversized tool results, and what a user said