Change
d7a7468
d7a74687f4690a01b9667d03ec9a16c37a0126e5 · commit on GitHub
aws-blog-feed: changed (687276 bytes, HTTP 200)
raw/aws-blog-feed/response.xml modified
- Source
- aws-blog-feed
- Lines added
- +4,159
- Lines removed
- -4,204
- Stored bytes at this commit
- 687,276
- Timestamp
- observed
- Raw artifact at this commit
- raw/aws-blog-feed/response.xml
Recorded headers
| observed_at | 2026-09-09T04:42:47.947Z |
|---|---|
| origin_date | null |
| status | 200 |
| final URL | https://aws.amazon.com/blogs/machine-learning/feed/ |
| etag | null |
| last-modified | Wed, 09 Sep 2026 00:16:42 GMT |
| date | Wed, 09 Sep 2026 04:42:47 GMT |
| age | null |
| cache-control | null |
| cf-cache-status | null |
| content-encoding | null |
| content-length | null |
@
@@ -5,7 +5,7 @@ <atom:link href="https://aws.amazon.com/blogs/machine-learning/feed/" rel="self" type="application/rss+xml"/> <link>https://aws.amazon.com/blogs/machine-learning/</link> <description>Official Machine Learning Blog of Amazon Web Services</description>-
<lastBuildDate>Fri, 04 Sep 2026 21:45:52 +0000</lastBuildDate>+
<lastBuildDate>Tue, 08 Sep 2026 22:06:58 +0000</lastBuildDate> <language>en-US</language> <sy:updatePeriod> hourly </sy:updatePeriod>@
@@ -13,203 +13,145 @@ 1 </sy:updateFrequency> <item>-
<title>Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore</title>-
<link>https://aws.amazon.com/blogs/machine-learning/deploy-a-multimodal-whatsapp-ordering-assistant-with-amazon-bedrock-agentcore/</link>+
<title>Take on your most ambitious work with GPT-6 Astra on Amazon Bedrock</title>+
<link>https://aws.amazon.com/blogs/machine-learning/take-on-your-most-ambitious-work-with-gpt-6-astra-on-amazon-bedrock/</link> -
<dc:creator><![CDATA[Salman Ahmed]]></dc:creator>-
<pubDate>Fri, 04 Sep 2026 21:45:52 +0000</pubDate>-
<category><![CDATA[Amazon Bedrock AgentCore]]></category>-
<category><![CDATA[Expert (400)]]></category>-
<category><![CDATA[Technical How-to]]></category>-
<guid isPermaLink="false">1cc1445c2783ef202a00ff4aadacbc028620a9eb</guid>-
-
<description>Learn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single business number, built on Amazon Bedrock AgentCore with Amazon Nova 2. The channel and ordering layers stay separate, and one sha…-
<content:encoded><p>This post shows how to deploy a multimodal WhatsApp ordering assistant built with <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-get-started-toolkit.html" target="_blank" rel="noopener">Amazon Bedrock AgentCore</a> and…-
<p>A single WhatsApp Business number hosts the assistant. A customer can text the restaurant, send a voice note, or place a voice call. An AI agent takes the order end to end, from greeting to confirmation. All three channels share one backend and one cross-channel memory. A customer who texts…-
<p>The solution uses the <a href="https://developers.facebook.com/docs/whatsapp/cloud-api/" target="_blank" rel="noopener">Meta WhatsApp Business Platform</a> as the customer front door. Amazon Bedrock AgentCore hosts the agents. <a href="https://aws.amazon.com/nova/models/" tar…-
<h2 id="solution-overview">Solution overview</h2> -
<p>The design keeps three things apart: (1) the WhatsApp layer handles the conversation, (2) three agent runtimes run the conversations for their channels, and (3) the backend holds the menu, carts, orders, and locations. Inbound traffic arrives on a single HTTPS webhook, is acknowledged with …-
<p>The customer front door is the <a href="https://developers.facebook.com/docs/whatsapp/cloud-api/" target="_blank" rel="noopener">Meta WhatsApp Business Platform</a>. It exposes the Cloud API webhook, Messages API, Media API, and Calling API. Meta manages this service. You set it…-
<p>You use the AWS CDK to deploy the following AWS resources as a set of stacks in dependency order, grouped here by function.</p> -
<ul> -
<li><a href="https://aws.amazon.com/api-gateway/" target="_blank" rel="noopener">Amazon API Gateway</a> provides two REST APIs. The first is a regional HTTPS webhook on an AWS managed certificate. It’s the only public endpoint. The second is an AWS Identity and Access Management (…-
<li><a href="https://aws.amazon.com/lambda/" target="_blank" rel="noopener">AWS Lambda</a> runs the webhook ingest, the webhook worker, the message sender, and the ordering business logic.</li> -
<li><a href="https://aws.amazon.com/sqs/" target="_blank" rel="noopener">Amazon Simple Queue Service (Amazon SQS)</a> provides the inbound queue, with a dead-letter queue, that decouples the quick acknowledgment from the rest of the processing.</li> -
<li><a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agents-tools-runtime.html" target="_blank" rel="noopener">AgentCore runtime</a>, a capability of Amazon Bedrock AgentCore, hosts the three agents. Each conversation runs in its own microVM. Sessions stay is…-
<li>Amazon Nova 2 Lite (text through the Converse API) and Amazon Nova 2 Sonic (speech-to-speech for voice) are invoked through <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>.</li> -
<li><a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway.html" target="_blank" rel="noopener">AgentCore Gateway</a>, a capability of Amazon Bedrock AgentCore, is a managed MCP server that exposes the backend REST API as MCP tools the agents call by name.&…-
<li><a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory.html" target="_blank" rel="noopener">AgentCore memory</a>, a capability of Amazon Bedrock AgentCore, is one shared, cross-channel record keyed by a hashed customer ID.</li> -
<li><a href="https://aws.amazon.com/dynamodb/" target="_blank" rel="noopener">Amazon DynamoDB</a> stores customer profiles, orders, menu items, carts, and locations. It also holds a <em>last inbound</em> window table for the WhatsApp layer.</li> -
<li><a href="https://aws.amazon.com/location/" target="_blank" rel="noopener">Amazon Location Service</a> handles geocoding and nearest-location lookups.</li> -
<li><a href="https://aws.amazon.com/kinesis/video-streams/" target="_blank" rel="noopener">Amazon Kinesis Video Streams (Amazon KVS)</a> provides a signaling channel that the voice-call runtime uses to mint credentials for the managed Traversal Using Relays around NAT (TURN) relay…-
<li><a href="https://aws.amazon.com/vpc/" target="_blank" rel="noopener">Amazon Virtual Private Cloud (Amazon VPC)</a> with a single network address translation (NAT) gateway is the outbound path for the voice-call runtime. This is the only runtime that requires a VPC.</li> -
<li><a href="https://aws.amazon.com/secrets-manager/" target="_blank" rel="noopener">AWS Secrets Manager</a> holds the Meta Access Token, App Secret, and Verify Token, created as empty containers you populate out-of-band. <a href="https://aws.amazon.com/systems-manager/" target…-
<li><a href="https://aws.amazon.com/ecr/" target="_blank" rel="noopener">Amazon Elastic Container Registry (Amazon ECR)</a>, <a href="https://aws.amazon.com/codebuild/" target="_blank" rel="noopener">AWS CodeBuild</a>, and <a href="https://aws.amazon.com/s3/" target…-
<li><a href="https://aws.amazon.com/cloudwatch/" target="_blank" rel="noopener">Amazon CloudWatch</a> captures logs and metrics, and <a href="https://aws.amazon.com/kms/" target="_blank" rel="noopener">AWS Key Management Service (AWS KMS)</a> encrypts data at rest.<…-
</ul> -
<h2 id="architecture-diagram">Architecture diagram</h2> -
<p>Figure 1 shows the full architecture. The diagram organizes the solution into labeled groups A through G that carry the request path. Two supporting groups sit outside that path, handling a build pipeline that runs once at deploy time to build the agent images and security and monitoring se…-
<div style="width: 810px" class="wp-caption alignnone">-
<a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-1.png" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-1.png" alt="Architecture diagram of…-
<p class="wp-caption-text">Figure 1: Multimodal WhatsApp ordering architecture on AWS</p>-
</div> -
<ul> -
<li>A. WhatsApp ingress and delivery: The webhook API Gateway, the ingest, worker, and sender Lambdas, and the Amazon SQS queue. The ingest verifies the Meta signature and enqueues the message. The worker handles the remaining processing. The Sender Lambda delivers replies.</li> -
<li>B. Agent runtimes: Three agents on AgentCore runtime, each an ARM64 container, one per channel: chat (Amazon Nova 2 Lite), voice note (Amazon Nova 2 Sonic), and voice call (Amazon Nova 2 Sonic over Web Real-Time Communication, or WebRTC). Only the voice-call runtime runs in a VPC.</li&…-
<li>C. Artificial intelligence and machine learning (AI/ML): Amazon Nova 2 Lite and Amazon Nova 2 Sonic invoked through Amazon Bedrock, plus the shared AgentCore memory keyed by a hashed <code>customer_id</code> for cross-channel continuity.</li> -
<li>D. MCP server (managed): AgentCore Gateway exposes the backend REST API as discoverable MCP tools (<code>GetMenu</code>, <code>AddToCart</code>, <code>PlaceOrder</code>, and more) that every runtime calls by name.</li> -
<li>E. API and compute: The IAM-authorized backend API Gateway and the ordering Lambdas that hold the business logic.</li> -
<li>F. Data storage: Amazon DynamoDB stores customer profiles, orders, menu items, carts, and locations.</li> -
<li>G. Networking and location: Amazon Location Service for geocoding and nearest-location lookups, the Amazon KVS managed TURN relay for voice-call media, and the VPC with a NAT gateway as the outbound path for the voice-call runtime.</li> -
</ul> -
<p>Two supporting groups sit outside the request path. The build pipeline (AWS CDK, AWS CodeBuild, Amazon ECR, and Amazon S3) runs once at deploy time to build and store the ARM64 agent images. It is not in the path of any request. Security and monitoring (AWS Secrets Manager, AWS Systems Mana…-
<p>The following steps trace a single request end to end through the architecture:</p> -
<ol type="1"> -
<li>Meta delivers an inbound webhook (text, voice note, or call event) to the Webhook API Gateway and the Webhook Ingest Lambda.</li> -
<li>The ingest verifies the Meta signature, enqueues to Amazon SQS, and returns <code>200</code> within Meta’s window.</li> -
<li>The Webhook Worker derives a pseudonymous <code>customer_id</code> using the pepper in AWS Systems Manager Parameter Store.</li> -
<li>The worker fetches media from the Meta Media API and invokes the matching agent on Amazon Bedrock AgentCore runtime (chat, voice note, or voice call) with <code>session_id = customer_id</code>.</li> -
<li>The runtime reads the customer’s long-term insights from AgentCore memory at session start.</li> -
<li>It runs the conversation with Amazon Nova 2 Lite (text) or Amazon Nova 2 Sonic (voice) through Amazon Bedrock.</li> -
<li>AgentCore Gateway is the managed MCP server. It exposes the backend REST API as MCP tools the agent calls by name.</li> -
<li>Tools route through the backend API Gateway to AWS Lambda, Amazon DynamoDB, and Amazon Location Service. Voice-call media uses the Amazon KVS TURN relay (runtime in a VPC).</li> -
<li>Replies go out through the Sender Lambda (text) or the worker (voice). Events are written back to memory at session end.</li> -
<li>AWS CDK builds ARM64 images through AWS CodeBuild into Amazon ECR. Amazon CloudWatch logs components and AWS KMS encrypts data at rest.</li> -
</ol> -
<p>In short, every request flows from Meta’s webhook through the ingest, queue, worker, and agent runtime to the backend tools, then back to the customer on WhatsApp.</p> -
<h2 id="channel-flows">Channel flows</h2> -
<p>All three channels share the same front door, backend tools, and memory. What differs is the media on the wire and the runtime that handles it.</p> -
<p>Text message: A text message arrives on the webhook. The worker derives <code>customer_id</code> and invokes the chat runtime, which reads memory, streams Amazon Nova 2 Lite through the Converse API, and calls backend tools through the MCP gateway as needed. Replies go through t…-
<p>Figure 2 shows the text flow, from the inbound webhook through Amazon Nova 2 Lite on the Converse API to the reply delivered by the Sender Lambda.</p> -
<div style="width: 810px" class="wp-caption alignnone">-
<a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-2.gif" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-2.gif" alt="Text-message flow from …-
<p class="wp-caption-text">Figure 2: Text flow with Amazon Nova 2 Lite</p>-
</div> -
<p>Voice note (speech-to-speech): A voice note arrives as an audio message. The worker downloads the OGG Opus bytes and invokes the voice-note runtime. After reading memory, the audio is decoded to 16 kHz pulse-code modulation (PCM) and fed into a bounded Amazon Nova 2 Sonic speech-to-speech s…-
<p>Figure 3 shows the voice-note flow, a bounded Amazon Nova 2 Sonic speech-to-speech session that returns a spoken reply with no transcription in the path.</p> -
<div style="width: 810px" class="wp-caption alignnone">-
<a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-3.gif" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-3.gif" alt="Voice-note flow with a …-
<p class="wp-caption-text">Figure 3: Voice note flow with Amazon Nova 2 Sonic</p>-
</div> -
<p>Voice call (WebRTC): The customer selects Call, and Meta’s Calling API delivers a connect webhook with the WebRTC Session Description Protocol (SDP) offer. The worker relays it to the voice-call runtime in <code>turnOnly</code> mode, because it has no public IP. TURN credentials…-
<p>Figure 4 shows the voice-call flow, where WebRTC media is relayed through the Amazon KVS managed TURN relay and Amazon Nova 2 Sonic drives the conversation.</p> -
<div style="width: 810px" class="wp-caption alignnone">-
<a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-4.gif" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-4.gif" alt="Voice-call flow with We…-
<p class="wp-caption-text">Figure 4: Voice call flow with Amazon Nova 2 Sonic</p>-
</div> -
<h2 id="prerequisites">Prerequisites</h2> -
<p>This solution has prerequisites in two areas: your AWS account and your Meta WhatsApp setup. Complete both prior to running the deployment, because it asks you for specific WhatsApp values and the agent cannot reply until they are in place.</p> -
<h3 id="aws-prerequisites">AWS prerequisites</h3> -
<ul> -
<li>You need an active AWS account with Amazon Bedrock model access enabled for Amazon Nova 2 Lite (<code>amazon.nova-2-lite-v1:0</code>) and Amazon Nova 2 Sonic (<code>amazon.nova-2-sonic-v1:0</code>) in your deployment Region. Your IAM user or role must have permissi…-
</ul> -
<p>The agent containers build inside AWS CodeBuild on ARM64, so you do not need Python, Docker, or audio toolchains locally. Deploy in an AWS Region where Amazon Nova 2 Lite, Amazon Nova 2 Sonic, and AgentCore runtime, Gateway, and memory are all available. The US East (N. Virginia) Region (us…-
<p>For model availability by Region, refer to <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html" target="_blank" rel="noopener">Supported models by AWS Region in Amazon Bedrock</a>.</p> -
<h3 id="whatsapp-business-platform-meta-prerequisites">WhatsApp Business Platform (Meta) prerequisites</h3> -
<p>The WhatsApp side is set up once in the Meta consoles, as a prerequisite rather than a step in this walkthrough. No AWS API can create a Meta app for you, so complete it first and have the values on hand before you deploy. For a demo, the Meta sandbox test number, which is available at no a…-
<p>Have these items ready before you deploy.</p> -
<ul> -
<li>A Meta Developer App with the WhatsApp product added, linked to a Business portfolio. Adding the product provisions a WhatsApp Business Account (WABA) and a sandbox test number at no additional cost. Refer to <a href="https://developers.facebook.com/docs/whatsapp/cloud-api/get-started"…-
<li>The App ID and App Secret. The App Secret is the key Meta uses to sign each webhook, and the webhook Lambda recomputes that signature.</li> -
<li>An Access Token. The temporary token works for a quick test and expires in about 24 hours. For something longer-lived, create a <a href="https://developers.facebook.com/documentation/business-messaging/whatsapp/access-tokens" target="_blank" rel="noopener">System User token</a>…-
<li>The Business portfolio ID (the setup CLI can auto-discover the Phone Number ID and WABA ID).</li> -
<li>A Verify Token that you invent. It is a hard-to-guess string Meta echoes back during the one-time <a href="https://developers.facebook.com/docs/graph-api/webhooks/getting-started" target="_blank" rel="noopener">webhook verification handshake</a>.</li> -
<li>For voice calls, the <a href="https://developers.facebook.com/docs/whatsapp/cloud-api/calling" target="_blank" rel="noopener">WhatsApp Calling API</a> enabled on the number.</li> -
</ul> -
<p>Store none of these in source control. The Access Token, App Secret, and Verify Token are secrets and go into AWS Secrets Manager during deployment, not into the CDK templates.</p> -
<h2 id="deploy-the-solution-with-aws-cdk">Deploy the solution with AWS CDK</h2> -
<p>The full solution is in the <a href="https://github.com/aws-samples/sample-multimodal-whatsapp-restaurant-agent" target="_blank" rel="noopener">sample repository on GitHub</a>. The repository contains three agent containers, the AWS CDK infrastructure code, and setup scripts tha…-
<div class="hide-language"> -
<pre><code class="language-bash">git clone https://github.com/aws-samples/sample-multimodal-whatsapp-restaurant-agent.git-
cd sample-multimodal-whatsapp-restaurant-agent-
./scripts/preflight-check.sh-
./scripts/deploy-all.sh --deploymentPrefix qsr-wa</code></pre> -
</div> -
<p>The script provisions every stack in dependency order. It passes each stack’s outputs to the next. First it deploys the shared VPC. Then it deploys the backend: Amazon DynamoDB, Amazon Location Service, the ordering Lambdas, and the backend REST API. Next it deploys AgentCore Gateway and th…-
<p>How the WhatsApp values reach the deployment matters for security. The CDK creates empty Secrets Manager containers for the three secrets. It does not take a secret as a CDK parameter, which would bake it into the synthesized template. You populate the secret values out-of-band, while the n…-
<div class="hide-language"> -
<pre><code class="language-bash">cd scripts/whatsapp-setup-
npm start # choose "Pre-deploy", then "Post-deploy" after deploy-
node whatsapp-setup.mjs --doctor # read-only end-to-end check</code></pre> -
</div> -
<p>Once the webhook is subscribed and the secrets are populated, the number is live and the agent replies across all three channels.</p> -
<h2 id="acknowledging-fast-and-processing-asynchronously">Acknowledging fast and processing asynchronously</h2> -
<p>Meta expects a prompt HTTP response with a <code>200 OK</code> status code. Taking an order, fetching media, invoking an agent, and relaying call signaling needs a little more than that brief acknowledgment window allows. So the work splits in two. The Webhook Ingest Lambda does…-
<h2 id="one-memory-across-three-channels">One memory across three channels</h2> -
<p>What makes this feel like one assistant is shared memory. A single AgentCore memory resource is keyed by a hashed <code>customer_id</code>, and all three runtimes use the same key. Each runtime reads the customer’s long-term insights at session start and writes events back at th…-
<h2 id="connecting-the-agents-to-backend-tools-with-mcp">Connecting the agents to backend tools with MCP</h2> -
<p>No AgentCore runtime calls the backend Lambda functions directly. AgentCore Gateway is a managed MCP server. Each AgentCore runtime connects to it as an MCP client over HTTPS, authenticated with the runtime’s IAM role, and discovers the tools by name. Each runtime carries its own role, so t…-
<h2 id="storing-menus-carts-and-orders">Storing menus, carts, and orders</h2> -
<p>Amazon DynamoDB tables cover the workflow. They are Customers (profiles for recognizing returning customers), Orders (history with pickup location and channel), Menu (items, prices, and availability), Carts (in-progress carts with a time-to-live), and Locations (coordinates, hours, and tax …-
<h2 id="finding-a-pickup-location">Finding a pickup location</h2> -
<p><a href="https://docs.aws.amazon.com/location/latest/developerguide/what-is.html" target="_blank" rel="noopener">Amazon Location Service</a> helps a customer find a pickup spot without much typing. The agent passes a ZIP code or address to be geocoded into coordinates. The backe…-
<h2 id="recognizing-a-customer-without-a-login">Recognizing a customer without a login</h2> -
<p>A WhatsApp customer doesn’t sign in, so the system uses the phone number as the basis for identity. It hashes the E.164 number with a secret pepper in AWS Systems Manager Parameter Store, and the result becomes the <code>customer_id</code> (<code>"wa-" + sha256(E164 || Pep…-
<h2 id="ordering-walkthrough">Ordering walkthrough</h2> -
<p>There is no web UI or test client. Message or call the WhatsApp Business number from a phone with WhatsApp installed. This example shows a typical exchange (lines prefixed “Agent” are the assistant’s replies, tool calls in brackets).</p> -
<div class="hide-language"> -
<pre><code class="language-text">Customer: What's on the menu near 75201?-
-
Agent: [tools: GeocodeAddress, GetNearestLocations, GetMenu]-
Here's what's available at Amazing Burgers - Dallas:-
- Burger Combo ($8.99)-
- Chicken Tenders ($6.49)-
...-
-
Customer: A burger combo and a milkshake, please.-
-
Agent: [tools: AddToCart, GetCart]-
Added to your cart:-
- 1x Burger Combo - $8.99-
- 1x Milkshake - $3.49-
Total: $12.48. Want me to place the order?-
-
Customer: Yes.-
-
Agent: [tools: PlaceOrder]-
Your order is placed and is being prepared for pickup at-
Amazing Burgers - Dallas. I'll let you know when it's ready.</code></pre> -
</div> -
<p>Voice notes and voice calls run the same flow through Amazon Nova 2 Sonic. You speak your order and the agent replies with voice. As the order advances, the order-notifier delivers proactive status updates back to WhatsApp. You can follow conversations in Amazon CloudWatch Logs.</p> -
<h2 id="cost">Cost</h2> -
<p>You pay for the AWS services the system uses, and separately for Meta’s WhatsApp messaging fees. Costs scale primarily with conversation volume and the share of voice traffic, which consumes more resources per session than text. This example deploys all three channels (text, voice note, and…-
<h2 id="things-to-consider">Things to consider</h2> -
<p>WhatsApp can also receive images and documents. This solution focuses on order taking and does not act on those attachments. If your use case needs them, you can configure the backend and the chat agent to handle them, because Amazon Nova 2 Lite is already multimodal. The agent could read a…-
<p>The pattern also reaches beyond restaurants. The core building blocks are one business number, several conversation channels, shared memory, and MCP tools in front of a backend. The same shape fits retail support, healthcare intake, field service scheduling, and many other domains. You adap…-
<p>For production deployments, consider enabling <a href="https://aws.amazon.com/bedrock/guardrails/" target="_blank" rel="noopener">Amazon Bedrock Guardrails</a> to add content filtering and grounding validation. This helps make sure agent responses stay within policy boundaries a…-
<h2 id="clean-up-resources">Clean up resources</h2> -
<p>To avoid ongoing charges, remove the resources when you are done. The cleanup script destroys stacks in reverse order, each consumer before its producers.</p> -
<div class="hide-language"> -
<pre><code class="language-bash">./scripts/cleanup-all.sh --dry-run # preview without removing anything-
./scripts/cleanup-all.sh # delete every stack the deploy created</code></pre> -
</div> -
<p>Cleanup is destructive. It deletes the order history in Amazon DynamoDB, the pepper in Parameter Store, the Secrets Manager secrets, and the images in Amazon ECR. Back up anything you want to keep first. It does not touch the Meta side, so unsubscribe the webhook and revoke tokens in the Me…+
<dc:creator><![CDATA[Tanvi Girinath]]></dc:creator>+
<pubDate>Tue, 08 Sep 2026 22:06:58 +0000</pubDate>+
<category><![CDATA[Amazon Bedrock]]></category>+
<category><![CDATA[Announcements]]></category>+
<category><![CDATA[Intermediate (200)]]></category>+
<guid isPermaLink="false">68d48019de714857964056351fc4d79e51c3ab9f</guid>+
+
<description>GPT-6 Astra from OpenAI is now generally available on Amazon Bedrock. It brings deeper reasoning and sharper judgment to your most demanding tasks, running on the Amazon Bedrock inference engine built for high performance, security, and scale.</description>+
<content:encoded><p><em>GPT-6 Astra from OpenAI brings greater depth and judgment to your most demanding tasks and runs on the Amazon Bedrock inference engine built for high performance, security, and scale.</em></p> +
<p>Organizations are already running AI agents that write code, analyze data, and automate complex workflows at production scale on Amazon Bedrock. GPT-6 Astra raises the potential of what those agents can deliver. It applies deeper reasoning and sharper judgment to complex business decisions,…+
<p>Today, GPT-6 Astra, the latest and most capable OpenAI model, is generally available on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>. You can call the <a href="https://aws.amazon.com/bedrock/openai/" target="_blank" rel="noopener…+
<h2 id="greater-depth-for-complex-decisions">Greater depth for complex decisions</h2> +
<p>GPT-6 Astra brings greater depth to work that requires you to reconcile competing inputs, trace dependencies, and determine what to prioritize. When performing financial analysis, it can help you reconcile conflicting data sources and identify discrepancies that could change a recommendatio…+
<p>For workflows that reuse the same context across requests, such as recurring document review, codebase analysis, or agents grounded in company standards, GPT-6 Astra supports both implicit and explicit prompt caching. With explicit caching, you can set cache breakpoints to control which con…+
<h2 id="layered-security-and-governance-for-production-ai">Layered security and governance for production AI</h2> +
<p>Model-level safeguards work alongside the security and governance controls of Amazon Bedrock. OpenAI evaluated GPT-6 Astra through its <a href="https://cdn.openai.com/pdf/18a02b5d-6b67-4cec-ab64-68cdfbddebcd/preparedness-framework-v2.pdf" target="_blank" rel="noopener">Preparedness Fr…+
<p>Amazon Bedrock protects your inference data and governs access at every model invocation. Zero-operator access is enforced at the chip, so even AWS operators can’t access your prompts and completions during inference. Data is encrypted in transit and at rest. Access is governed by your AWS …+
<p>Your inference data isn’t used for model training, and using GPT-6 Astra doesn’t require you to opt into sharing your data with OpenAI. For <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/abuse-detection.html" target="_blank" rel="noopener">automated abuse detection</…+
<h2 id="build-code-and-work-with-astra">Build, code, and work with Astra</h2> +
<p>You can use&nbsp;GPT-6 Astra for inference, knowledge work, and software development.</p> +
<h3 id="for-platform-and-application-teams">Integrate Astra into your applications</h3> +
<p>You can integrate GPT-6 Astra directly into your applications using supported Amazon Bedrock APIs. Use it to power autonomous agents that handle complex, multistep workflows, build internal tools that analyze and synthesize documents at scale, or create customer-facing applications that req…+
<h3 id="for-business-and-operations-teams">Turn complex tasks into finished deliverables</h3> +
<p>ChatGPT Work is a productivity agent for turning complex business tasks into finished deliverables. With GPT-6 Astra, it can gather information across applications and files, use the web, and produce spreadsheets, slides, documents, and sites. You can control which applications and websites…+
<p>ChatGPT Work is available through the ChatGPT desktop app for Mac and Windows. New enterprise plugins introduced alongside this release extend browser-use capabilities across business intelligence tools, Workday, Navan, and Avalara for tasks across data analytics, operations, and finance. T…+
<h3 id="for-development-teams">Build, test, and ship code faster</h3> +
<p>Codex is a software engineering agent that works with local files, repositories, terminals, developer tools, and development environments to write features, fix bugs, run tests, and open pull requests. When you configure Codex to use GPT-6 Astra on Amazon Bedrock, it applies Astra’s reasoni…+
<p>You can access Codex through the ChatGPT desktop app, CLI, VS Code, JetBrains IDEs, and Xcode. For AWS development, the&nbsp;<a href="https://docs.aws.amazon.com/agent-toolkit/latest/userguide/quick-start.html" target="_blank" rel="noopener">Agent Toolkit for AWS</a>&nbs…+
<h2 id="get-started">Get started</h2> +
<p>You can get started in the <a href="https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/" target="_blank" rel="noopener">Amazon Bedrock console</a> or programmatically through supported Amazon Bedrock APIs. For information about supported <a href="https://…+
<p><em>Interested in how Amazon Bedrock can support your team? <a href="https://pages.awscloud.com/Amazon-Bedrock-Contact-Us.html" target="_blank" rel="noopener">Connect with us</a> to start the conversation.</em></p> +
<p style="clear: both"></p> +
<hr style="width: 100%"> +
<h2>About the authors</h2> +
<footer> +
<div class="blog-author-box" style="padding-top: 2.0em"> +
<div class="blog-author-image" style="margin-right: 1.0em">+
<img class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21849-1.jpg" alt="Tanvi Girinath" width="100" height="133">+
</div> +
<h3 class="lb-h4">Tanvi Girinath</h3> +
<p style="overflow: hidden">Tanvi is a Product Marketing Manager for Amazon Bedrock at Amazon Web Services (AWS), where she helps customers adopt and scale AI applications and agents with Amazon Bedrock.</p> +
</div> +
<div class="blog-author-box" style="padding-top: 2.0em"> +
<div class="blog-author-image" style="margin-right: 1.0em">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21849-2.jpg" alt="Chris Dickens" width="100" height="133">+
</div> +
<h3 class="lb-h4">Chris Dickens</h3> +
<p style="overflow: hidden">Chris is a Member of Product Staff at OpenAI focused on the OpenAI APIs. His work includes collaboration with AWS on Amazon Bedrock to make OpenAI’s frontier models widely accessible to developers.</p> +
</div> +
<div class="blog-author-box" style="padding-top: 2.0em"> +
<div class="blog-author-image" style="margin-right: 1.0em">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21849-3.jpg" alt="Manish Rathaur" width="100" height="133">+
</div> +
<h3 class="lb-h4">Manish Rathaur</h3> +
<p style="overflow: hidden">Manish is a Senior Product Manager for Amazon Bedrock.</p> +
</div> +
</footer></content:encoded>+
+
+
+
</item>+
<item>+
<title>Pathway’s brain-inspired architecture development on Amazon SageMaker HyperPod</title>+
<link>https://aws.amazon.com/blogs/machine-learning/pathways-brain-inspired-architecture-development-on-amazon-sagemaker-hyperpod/</link>+
+
<dc:creator><![CDATA[Paulo Aragão]]></dc:creator>+
<pubDate>Tue, 08 Sep 2026 19:12:51 +0000</pubDate>+
<category><![CDATA[Amazon SageMaker HyperPod]]></category>+
<category><![CDATA[Announcements]]></category>+
<category><![CDATA[Intermediate (200)]]></category>+
<category><![CDATA[Amazon SageMaker]]></category>+
<category><![CDATA[distributed training]]></category>+
<category><![CDATA[PyTorch]]></category>+
<guid isPermaLink="false">7b62a76bc3853bd9ada742693ec9cd3b09d199a8</guid>+
+
<description>Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway develops and scales BDH on Amazon SageMaker HyperPod, and how BDH-CQ set a new cost-efficiency mark on …+
<content:encoded><p>As AI systems take on more complex tasks, much of the industry’s progress has come from increasing model scale, training data, context length, and inference-time computation. Instead of externalizing reasoning work as a chain-of-thought (generating extra tokens se…+
<p>Large language models (LLMs) have transformed AI, changing how we approach tasks from code generation to creative writing. However, fundamental questions remain about general intelligence and their ability to reason over long time periods in a coherent way. Their architecture, kept roughly …+
<p>Pathway’s BDH integrates with well-known frameworks such as PyTorch and uses <a href="https://aws.amazon.com/sagemaker/ai/hyperpod/" target="_blank" rel="noopener">Amazon SageMaker HyperPod</a> to scale out their training. Amazon SageMaker HyperPod helps their applied AI scienti…+
<h2 id="transformers-architecture-and-fundamental-limitations">Transformers: architecture and fundamental limitations</h2> +
<p>The transformer architecture, while widely adopted for natural language processing (NLP), faces significant limitations in both training and inference workloads.</p> +
<p>During training, transformers struggle with systematic generalization beyond their training data, particularly for long chain-of-thought reasoning tasks, and require massive amounts of data and computational effort to compensate for this limitation. The transformer architecture’s dense comp…+
<p>At inference, transformers face other inefficiencies: the structure of their attention mechanism limits scalability, while their dense activation patterns, even with Mixture of Experts techniques, result in excessive computation and memory bandwidth usage. The fixed context window and growi…+
<p>These challenges are fundamentally tied to the architecture’s design choices rather than only implementation details, suggesting the need for alternative approaches that better align with both computational efficiency and natural intelligence principles.</p> +
<blockquote>+
<p><em>“Today’s AI pays a steep token cost for reasoning, but that cost is imposed by architecture, not by any law of intelligence. Currently, every reasoning step consumes context, adds latency, and burns compute. We show that a different architecture changes the game and opens up a wh…+
</blockquote> +
<p>— Zuzanna Stamirowska, CEO and co-founder, Pathway</p> +
<h2 id="bdh-a-unified-architecture-for-artificial-and-natural-intelligence">BDH: A unified architecture for artificial and natural intelligence</h2> +
<p><a href="https://pathway.com/" target="_blank" rel="noopener">Pathway</a>’s vision is to fundamentally change the way models think. Their BDH architecture is a post-transformer model that continually learns, evolves, and reasons. BDH’s architecture represents a new way to build …+
<p>As in the brain, the interactions of BDH are defined to be sparse and local, and the connections between the neurons encode the memory and reasoning functions. This sparse activation profile (only 5 percent of neurons are typically active at a given time) supports efficient computation. The…+
<p>BDH implements attention through a linear mechanism that operates on fixed, high-dimensional states without incurring the increased complexity characteristic of transformer models for long contexts. This allows the model to process longer sequences more efficiently, without the context leng…+
<p>Recently, Pathway built <a href="https://arxiv.org/pdf/2608.09888" target="_blank" rel="noopener">BDH-CQ, a reasoning system built on top of BDH</a>. It extends BDH with in-context learning and latent iterative reasoning for visual problem-solving.</p> +
<p>As the following sections show, BDH-CQ excels at in-context learning. Its recurrent computations over latent states support efficient parallel hypothesis exploration, where communities of neurons can represent different candidate solutions for a problem at hand. The model achieves a reasoni…+
<blockquote>+
<p><em>“Customers are increasingly exploring how to move advanced reasoning from experimentation into production, where performance, efficiency, and scalability all matter. Pathway’s work training BDH-CQ on Amazon SageMaker HyperPod points to a promising path toward deploying high-perfo…+
</blockquote> +
<p>— Nicolas Tarducci, Head of Solution Architecture for Startups EMEA, Amazon Web Services</p> +
<h2 id="developing-bdh-architecture-on-amazon-sagemaker-hyperpod">Developing BDH architecture on Amazon SageMaker HyperPod</h2> +
<p>Pathway uses <a href="https://aws.amazon.com/sagemaker/ai/hyperpod/" target="_blank" rel="noopener">Amazon SageMaker HyperPod</a> for developing its BDH architecture. Amazon SageMaker HyperPod is a purpose-built infrastructure solution for training LLMs and foundation models (FM…+
<p>For Pathway to develop AI architectures beyond transformers, comprehensive observability of their training infrastructure is critical. Amazon SageMaker HyperPod integration with advanced monitoring tools, such as <a href="https://aws.amazon.com/prometheus/" target="_blank" rel="noopener"…+
<p>This comprehensive observability stack helps reduce development cycles when iterating on new architectural approaches, optimizes cost-performance ratio for resource-intensive training, and ensures reliability and reproducibility of results across training runs. For more information about th…+
<p>Amazon Elastic Fabric Adapter (EFA) integrates natively with the NVIDIA CUDA platform for GPU-accelerated computation and the NVIDIA Collective Communications Library (NCCL) for communication across GPUs. It allows distributing data, weights, activations, and more, in a reliable and scalabl…+
<h2 id="proof-of-bdh-architecture-bdh-cq-achieving-29.2-pass2-on-arc-agi">Proof of BDH architecture: BDH-CQ achieving 29.2% pass@2 on ARC-AGI</h2> +
<p>BDH-CQ achieved 29.2 percent pass@2 on the ARC-AGI benchmark at a cost of US $0.0007 per task.</p> +
<p>Thanks to Pathway’s new approach to reasoning, in-context task acquisition and iterative latent computation, BDH-CQ changed the cost-accuracy Pareto frontier on the ARC-AGI-1 benchmark, as of August 2026.</p> +
<p>ARC-AGI-1 presents an AI system with a small number of before-and-after examples that illustrate an unknown visual rule. The system must then infer that rule and apply it to a new grid, a capability often associated with human-like intelligence. BDH-CQ performs iterative computation inside …+
<p>The pattern that ARC-AGI explores resembles real-world challenges where systems must reason reliably as information and constraints change, such as investigating cyber security incidents, coordinating transportation networks, responding to real-time industrial operations, and operating auto…<h2 id="conclusion">Conclusion</h2> -
<p>This post walked through the architecture and deployment of a multimodal WhatsApp ordering assistant that takes an order end to end over text, voice notes, and voice calls on a single business number. An asynchronous webhook accepts traffic fast and queues the rest of the work. Three runtim…+
<p>BDH is a new large language model architecture inspired by scale-free biological networks. It draws on principles biology got right, namely local interaction, sparse activity, persistent state, and continual adjustment, and applies them to a modern sequence model. It offers a GPU-friendly i…+
<p>To begin exploring and implementing the BDH architecture, you can access detailed <a href="https://arxiv.org/abs/2608.09888" target="_blank" rel="noopener">technical documentation</a> and a sample implementation through Pathway’s <a href="https://github.com/pathwaycom/bdh" ta…+
<p>Teams that push the boundaries of AI model development can use Amazon SageMaker HyperPod to maintain efficiency and reliability at scale. Amazon SageMaker HyperPod training offers a robust solution to common challenges in large model training. To learn more about Amazon SageMaker HyperPod, …<p style="clear: both"></p> <hr style="width: 100%"> <h2>About the authors</h2> <footer> <div class="blog-author-box" style="padding-top: 2.0em"> <div class="blog-author-image" style="margin-right: 1.0em">-
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-5.jpg" alt="Salman Ahmed" width="100" height="133">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21697-1.jpg" alt="Paulo Aragão" width="100" height="133"> </div> -
<h3 class="lb-h4">Salman Ahmed</h3> -
<p style="overflow: hidden">Salman is a Senior Technical Account Manager at AWS, specializing in helping customers design, implement, and optimize their AWS environments. He combines deep networking expertise with a passion for exploring emerging technologies to help organizations get the mo…+
<h3 class="lb-h4">Paulo Aragão</h3> +
<p style="overflow: hidden">Paulo is a Principal WW Specialist Solutions Architect focused on helping customers build their Frontier AI strategy on AWS. With over 20 years of experience dealing with High Performance Computing and AIML projects, he is passionate about working backwards from c… </div> <div class="blog-author-box" style="padding-top: 2.0em"> <div class="blog-author-image" style="margin-right: 1.0em">-
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-6.jpg" alt="Sergio Barraza" width="100" height="133">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21697-2.jpg" alt="Rodrigo Merino" width="100" height="133"> </div> -
<h3 class="lb-h4">Sergio Barraza</h3> -
<p style="overflow: hidden">Sergio is a Senior Technical Account Manager at AWS, helping customers design and optimize cloud solutions. With more than 25 years in software development, he guides customers through AWS services adoption. Outside work, Sergio is a multi-instrument musician play…+
<h3 class="lb-h4">Rodrigo Merino</h3> +
<p style="overflow: hidden">Rodrigo is a Generative AI Solutions Architect Manager at AWS. With over a decade of experience deploying emerging technologies, from IoT to GenAI, Rodrigo guides customers to accelerate their AI/ML and generative AI journeys. He specializes in helping organizatio… </div> <div class="blog-author-box" style="padding-top: 2.0em"> <div class="blog-author-image" style="margin-right: 1.0em">-
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/ML-21164-7.jpg" alt="Ravi Kumar" width="100" height="133">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/02/ML-21697-3.jpg" alt="Ludovic Arnould" width="100" height="133"> </div> -
<h3 class="lb-h4">Ravi Kumar</h3> -
<p style="overflow: hidden">Ravi is a Senior Technical Account Manager in AWS Enterprise Support who helps customers in the travel and hospitality industry to streamline their cloud operations on AWS. He is a results-driven IT professional with over 20 years of experience. Ravi is passionate…+
<h3 class="lb-h4">Ludovic Arnould</h3> +
<p style="overflow: hidden">Ludovic is a Frontier AI Model Solutions Architect at Pathway, specializing in the design and deployment of advanced AI solutions for enterprise customers. He holds a PhD in Machine Learning from Sorbonne Université and has published research at ICML, ICLR, and AI… </div> </footer></content:encoded> @
@@ -217,461 +159,659 @@ Agent: [tools: PlaceOrder] </item> <item>-
<title>Designing lifecycle policies for AgentCore memory</title>-
<link>https://aws.amazon.com/blogs/machine-learning/designing-lifecycle-policies-for-agentcore-memory/</link>+
<title>Amazon SageMaker Feature Store introduces UpdateRecord for feature-level writes</title>+
<link>https://aws.amazon.com/blogs/machine-learning/amazon-sagemaker-feature-store-introduces-updaterecord-for-feature-level-writes/</link> -
<dc:creator><![CDATA[Akarsha Sehwag]]></dc:creator>-
<pubDate>Fri, 04 Sep 2026 17:20:04 +0000</pubDate>-
<category><![CDATA[Advanced (300)]]></category>-
<category><![CDATA[Amazon Bedrock AgentCore]]></category>+
<dc:creator><![CDATA[Mona Mona]]></dc:creator>+
<pubDate>Tue, 08 Sep 2026 18:29:15 +0000</pubDate>+
<category><![CDATA[Amazon Machine Learning]]></category>+
<category><![CDATA[Amazon SageMaker AI]]></category>+
<category><![CDATA[Announcements]]></category>+
<category><![CDATA[Artificial Intelligence]]></category>+
<category><![CDATA[Intermediate (200)]]></category> <category><![CDATA[Technical How-to]]></category>-
<category><![CDATA[Thought Leadership]]></category>-
<guid isPermaLink="false">bf15bf1accc979b1b510192d304b5091e2a44dc0</guid>+
<guid isPermaLink="false">ea7f9667a432b227c77a23d10cd0038932138567</guid>-
<description>Long-running AI agents accumulate outdated memories that degrade quality and create compliance risk. Learn how to design memory lifecycle policies for Amazon Bedrock AgentCore: scoring, consolidating, and pruning agent memories on a nightly AWS Step Functions workflow, with a deplo…-
<content:encoded><p>Memory lifecycle policies help long-running agents on Amazon Bedrock AgentCore stay effective by systematically managing what they remember and forget. Your agent generates memories from every conversation it conducts. If you don’t actively manage these memories, …-
<p>After months of production use, problems emerge. We observed a customer support agent reference a billing dispute resolved four months earlier, treating it as active. Another agent repeated outdated deployment advice because its memory still contained a superseded runbook.</p> -
<p>In this post, we introduce memory lifecycle management for AI agents: the practice of systematically scoring, consolidating, and pruning agent memories over time. We walk through a deployable architecture using <a href="https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentco…-
<p>This solution targets agents that accumulate high volumes of interaction data over weeks or months, such as customer support agents, sales advisors, and IT helpdesk bots. For lower-volume agents like personal assistants, you might start with time-to-live (TTL) expiration and General Data Pr…-
<h2 id="solution-overview">Solution overview</h2> -
<p>This solution combines a shared memory taxonomy with three lifecycle policies that run as a nightly workflow. We begin with the memory types that shape those policies.</p> -
<h3 id="memory-types">Memory types</h3> -
<p>Before designing lifecycle policies, we need a shared vocabulary for what agents remember. We categorize agent memory into three types, each with different retention requirements.</p> +
<description>Amazon SageMaker Feature Store now supports feature-level writes. With the new UpdateRecord API, you can update one or more feature values in a single call without reading or rewriting the entire record. It is available for both the Standard (Amazon DynamoDB) and In-Memory (Amazon …+
<content:encoded><p>We are excited to announce <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_feature_store_UpdateRecord.html"><em>feature-level writes</em></a> for Amazon SageMaker Feature Store. <a href="https://aws.amazon.com/sage…+
<h2 id="the-challenge-full-record-writes-for-every-change">The challenge: Full-record writes for every change</h2> +
<p>A Feature Group is a logical collection of features that are related, and are used by one or more ML models to either train a new model or generate inference predictions. Until now, updating even a single feature value in a feature group required a full read-modify-write cycle using <a h…+
<ol type="1"> +
<li><strong>Read</strong> the complete record (all features) by using <a href="https://docs.aws.amazon.com/boto3/latest/reference/services/sagemaker-featurestore-runtime/client/get_record.html" target="_blank" rel="noopener">GetRecord</a>.</li> +
<li><strong>Merge</strong> the new value in application code.</li> +
<li><strong>Write</strong> the entire record back with <a href="https://docs.aws.amazon.com/boto3/latest/reference/services/sagemaker-featurestore-runtime/client/put_record.html" target="_blank" rel="noopener">PutRecord</a>.</li> +
</ol> +
<p>This pattern added extra latency per update, consumed unnecessary read capacity, and introduced race conditions when multiple pipelines concurrently updated different features in the same record. In the worst case, one pipeline’s write could silently overwrite another’s. This is a classic l…+
<p>Beyond latency and correctness issues, the read-modify-write pattern also carries a cost overhead. The additional GetRecord calls required before each write generate extra <a href="https://aws.amazon.com/sagemaker/ai/pricing/" target="_blank" rel="noopener">Read Capacity Units (RCUs)&…+
<h2 id="introducing-updaterecord">Introducing UpdateRecord</h2> +
<p>The <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_feature_store_UpdateRecord.html" target="_blank" rel="noopener">UpdateRecord API</a> call removes the read-modify-write cycle. You provide only the features that you want to change, and Amazon SageMaker F…+
<h3 id="updaterecord-api-data-flow">UpdateRecord API data flow</h3> +
<p>The following diagram illustrates how the UpdateRecord API processes a partial write request and synchronizes with the offline store.</p> +
<div id="attachment_138746" style="width: 1634px" class="wp-caption alignleft">+
<img aria-describedby="caption-attachment-138746" loading="lazy" class="size-full wp-image-138746" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/03/Screenshot-2026-09-03-at-11.34.17 AM.png" alt="" width="1624" height="710">+
<p id="caption-attachment-138746" class="wp-caption-text">Figure 1: UpdateRecord API data flow to the online and offline stores</p>+
</div> +
<p>The client application calls the UpdateRecord API with only the changed features. The Feature Store service validates AWS Identity and Access Management (IAM) permissions, checks EventTime ordering to reject stale writes, and performs an atomic merge. The blue arrow represents the single op…+
<h3 id="request-shape">Request shape</h3> +
<div class="hide-language"> +
<pre><code class="language-plaintext">POST /FeatureGroup/{FeatureGroupName}/Record+
+
{+
"RecordIdentifierValueAsString": "user_123",+
"Features": [+
{ "FeatureName": "risk_score", "ValueAsString": "0.87" },+
{ "FeatureName": "last_login", "ValueAsString": "2026-07-21T08:15:00Z" }+
],+
"TtlDuration": { // optionalDiff display stops at 400 lines. The line counts above are from the whole diff. 94 lines shown here cut at 300 characters. The raw artifact at this commit is linked above.