Search “Meta”

English translation is being prepared.

English translation is being prepared.

AWS Publishes Agent Registry Runtime Tool Discovery Practice

AWS introduces the Agent Registry runtime tool discovery approach: agents use hybrid semantic and keyword search to find approved MCP servers and A2A agents, then instantly build clients from descriptors to execute requests. The sample code is based on Amazon Bedrock AgentCore Gateway and runtime, integrates an order management MCP server and two A2A agents for pricing and customer service, and demonstrates a return and refund scenario using pure semantic matching. The registry returns only connection metadata; invocation credentials must be obtained separately through Cognito OAuth or IAM, and new capabilities require no changes to orchestrator code.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

GM teaches engineers to fail fast and 'speak fearlessly,' taking on Chinese EVs with battery technology

General Motors has invested $900 million to build a battery cell development center at its Warren Technical Center in Michigan, and is advancing its in-house LMR (lithium manganese-rich) cells, with plans to mass-produce them in 2028 in partnership with LG Energy Solution. Its LMR cells have a nickel content of about 30% to 40%, lower than the roughly 85% in current high-nickel cells, and an energy density about one-third higher than mainstream LFP cells, at a comparable cost. GM says the technology is independently developed and does not rely on Chinese licensing, with the goal of giving large electric pickups and full-size SUVs cheaper batteries with longer range.

English translation is being prepared.

Vectorial raises $3 million seed round to test products with simulated users

Vectorial has closed a $3 million seed round with investors including Smilegate, SenseAI Ventures and Dent Capital, to expand its behavioral dataset and develop the SAPIENS 2.0 model. Its platform first uses behavioral data to build models of target audiences, then lets product, design and marketing teams simulate product journeys, marketing concepts and AI agent conversations before reaching real users. The company says it has modeled over 2.5 million people and completed more than 30,000 simulations, with simulations reproducing existing user research findings with over 85% accuracy, and SAPIENS predicting behavior 30% more accurately than general-purpose large language models.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

AI startup Vectorial raises $3 million to use AI to simulate human behavior for consumer research

AI startup Vectorial has closed a $3 million seed round co-led by Smilegate and SenseAI Ventures to launch its consumer research platform that simulates human behavior. The platform is based on the behavioral model SAPIENS, whose training data covers more than 2.5 million real consumers; it predicts consumer behavior 30% more accurately than general-purpose models and achieves about 86% accuracy compared with real user research. Customers including GoodRx, Boat, Everkind and Concrete Software run an average of 600 simulations per month, and the company will use the new funding to build SAPIENS 2.0.