Technology / WORLD

AWS publishes AgentCore example for source-grounded presentations

The sample creates PowerPoint presentations from financial and compliance documents. In AWS’s internal test, it produced six slides from the 90-page Amazon 2024 Annual Report in 70–90 seconds.

The source does not state the event date; the period shown is the source review period.

Reading sizeSources ↓Share story ↗
Conceptual illustration of technology, processors and connected information.Illustration
Symbolic illustration

The October 14 technical post describes a financial-services workflow that extracts information from hundreds of pages and organizes slides and visuals. A supervisor on AgentCore selects document-generation or summarization tools; OpenSearch Serverless retrieves source material and Bedrock Guardrails checks outputs.

The example uses Claude Sonnet 4.6 for writing, Titan Text Embeddings v2 for search and Stability AI for images. AWS’s internal test produced six slides from the 90-page Amazon 2024 Annual Report in 70–90 seconds; this result is specific to that test input and output.

Data

Timeline

AWS technical post published

AWS published a technical guide to an AgentCore architecture for source-based presentation generation on October 14.

  1. · Occurred

    AWS technical post published

    AWS published a technical guide to an AgentCore architecture for source-based presentation generation on October 14. In AWS’s internal test, the system produced six slides from the 90-page Amazon 2024 Annual Report in 70–90 seconds.

Methodology

The date is the publication date shown by the AWS primary source; no launch or deployment date beyond the source is inferred.

Updated:

Structured coverage

Subjects and places

Subject proposals

Taxonomy version: IPTC Media Topics 2026-Q2

Continue reading

Technology

AWS publishes deployment and evaluation workflow for JumpStart

An October 14 AWS guide shows how SageMaker Python SDK v3 can find and deploy a model from JumpStart, then measure it with sample prompts. The example records latency, approximate output length and single-request generation rate.

AWS1 min read Data included
Technology

AWS evaluates Grok 4.7 agents on long-horizon tasks

An October 13 AWS technical post tested a tool-using agent with Grok 4.7 on Bedrock across three synthetic search tasks. Each task had one answer verified by brute force; six runs at each of four reasoning levels made 72 runs in total.

AWS1 min read Data included