Amazon introduced Live Data in Apps for Amazon Quick Apps, so AI-built apps can query governed Quick Sight datasets at view time instead of using build-time snapshots. The feature runs the same SQL every time a user opens a published app, and it supports SPICE and Direct Query datasets (with SPICE refresh and no refresh for Direct Query). As a result, numbers stay current and row- and column-level security plus per-dataset viewer consent are enforced for each person using the app.
Amazon Payments used contextual multi-armed bandits on AWS SageMaker AI to personalize which generated content variant to show customers across a multi-step product acquisition funnel. In a seven-week online A/B test, one customer population saw a high single-digit percentage relative lift in final-funnel conversion while another saw no improvement. The approach shifts from single-metric content testing to funnel-wide selection with contextual bandit scoring, plus a code/data setup for replicating the method on synthetic data.
Amazon Web Services released Strands Decider 2B, an open-source decision model inspired by TypeSafe’s Jev that returns calibrated choices instead of generating text. It was released as fully open-sourced software on the same week OpenAI announced a similar offering. The release expands the growing set of decision models and targets agent workflows that can use lower-latency, lower-cost “decider” steps with confidence scores.
Amazon Bedrock AgentCore provides a way to build ambient agents that start jobs from event streams like S3 uploads and then pause for human input before continuing. The reference design caps each agent turn at the AWS Lambda 15-minute timeout. This shifts agent execution from chat-based, user-initiated prompts to serverless, event-driven workflows with a single ask_human interaction that routes reviews through a Jobs interface.
AWS’s Strands Labs released Strands Decider 2B, an open-source lightweight decision model aimed at speeding up agentic workflows without generating text. The model is a 2 billion-parameter system designed to run on local machines with less than 150 milliseconds of latency. Developers can now download and run it (and experiment with it for routing, tool selection, and guardrails), enabling “hybrid agents” that use decision models for simple choices and LLMs for more complex reasoning.
AWS launched Strands Decider 2B, a locally downloadable decision-model alternative to Jev-style systems, built for scoring developer-provided answer options and intervening before agent tool calls. The release targets JevBench’s public set and AWS says it ranks first among public models with a full training recipe, with decisions reported in under 100 milliseconds on an Nvidia RTX 3090. Developers can download the model plus the training data and scripts for inspection and adaptation, and they can choose intervention actions like proceed, deny, or human confirmation before tools run, with no hosted version confirmed yet.
Every AI story that matters,
in your inbox by 8am.
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the
day in two minutes. Follow companies and topics for alerts, or get the
briefing in Slack. Free, no spam, unsubscribe anytime.
Reading TLDRocket needs no cookies, and the readership counts we rely on come from
our own cookieless analytics. Google Analytics is the exception: it sets cookies and
reports to Google, so it stays switched off until you allow it. You can change your
mind any time from “Cookie settings” in the footer.
Strictly necessary
Session security and form protection (tldrocket-session,
XSRF-TOKEN, 2 hours). The site cannot work without them,
so they need no consent.
Always on
Google Analytics 4 (_ga,
_ga_<id>, up to 2 years). Measures which
stories and sections readers use. Google acts as a third-party processor and may
store the data outside the EU. No advertising, no profiling, no data sold.
