Change
16b5b55
16b5b553cfd2f45ff527e597e4fa8b8e0930bf58 · commit on GitHub
aws-blog-feed: changed (540088 bytes, HTTP 200)
raw/aws-blog-feed/response.xml modified
- Source
- aws-blog-feed
- Lines added
- +3,281
- Lines removed
- -4,785
- Stored bytes at this commit
- 540,088
- Timestamp
- observed
- Raw artifact at this commit
- raw/aws-blog-feed/response.xml
Recorded headers
| observed_at | 2026-10-08T06:04:39.223Z |
|---|---|
| origin_date | null |
| status | 200 |
| final URL | https://aws.amazon.com/blogs/machine-learning/feed/ |
| etag | null |
| last-modified | Wed, 07 Oct 2026 23:32:20 GMT |
| date | Thu, 08 Oct 2026 06:04:39 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>Tue, 06 Oct 2026 22:43:32 +0000</lastBuildDate>+
<lastBuildDate>Wed, 07 Oct 2026 23:32:02 +0000</lastBuildDate> <language>en-US</language> <sy:updatePeriod> hourly </sy:updatePeriod>@
@@ -13,215 +13,170 @@ 1 </sy:updateFrequency> <item>-
<title>Building a context-aware AI assistant on AgentCore and OpenClaw</title>-
<link>https://aws.amazon.com/blogs/machine-learning/building-a-context-aware-ai-assistant-on-agentcore-and-openclaw/</link>+
<title>Introducing Claude Haiku 5.5 on AWS</title>+
<link>https://aws.amazon.com/blogs/machine-learning/introducing-claude-haiku-5-5-on-aws/</link> -
<dc:creator><![CDATA[Thiago Verney]]></dc:creator>-
<pubDate>Tue, 06 Oct 2026 19:19:15 +0000</pubDate>-
<category><![CDATA[Advanced (300)]]></category>-
<category><![CDATA[Amazon Bedrock AgentCore]]></category>-
<category><![CDATA[Technical How-to]]></category>-
<guid isPermaLink="false">923519c839c137326cec150f20986e906ba708bc</guid>-
-
<description>Off-the-shelf AI assistants forget you between conversations. This post shows how to build a personal assistant that accumulates context using OpenClaw on Amazon Bedrock AgentCore runtime, with AgentCore memory turning disposable chats into durable, structured knowledge you can ret…-
<content:encoded><p>Off-the-shelf AI assistants answer individual questions well, but they fall short on a different axis: continuity. Ask a stateless assistant about your garden today and it has no idea that you mentioned your fast-draining raised beds three weeks ago, that you only…-
<p>The problem isn’t the quality of the answers, but that the assistant has no memory of you. This post shows how to build a personal assistant that accumulates context using <a href="https://openclaw.ai/" target="_blank" rel="noopener">OpenClaw</a>, an open source agentic system, …-
<p>Our running example is Sprout, a gardening assistant, but the architecture is domain-agnostic. Swap the persona and the skills manifest, and the same pipeline serves a support bot, a fitness coach, or an internal help desk. The entire system lives in a single AWS CloudFormation template, de…-
<h2 id="solution-overview">Solution overview</h2>-
<p>AgentCore is a platform to build, connect, and optimize agents at scale, with any framework or model. The following diagram shows the end-to-end request flow, from an inbound Telegram webhook through the AgentCore runtime, and its supporting AWS services.</p>-
<div id="attachment_140908" style="width: 4750px" class="wp-caption alignnone">-
<img aria-describedby="caption-attachment-140908" class="size-full wp-image-140908" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/06/ml21227_.drawio.png" alt="" width="4740" height="2270">-
<p id="caption-attachment-140908" class="wp-caption-text">Figure 1: Telegram webhooks and Amazon EventBridge schedules both invoke the same AgentCore runtime agent, which coordinates the OpenClaw gateway, AgentCore memory, and Amazon Bedrock</p>-
</div>-
<p>Two entry points converge on one agent. Telegram messages arrive through Amazon API Gateway and a webhook AWS Lambda function, while scheduled jobs such as morning watering reminders arrive through Amazon EventBridge Scheduler and a cronjob Lambda function. Both call the <code>InvokeA…-
<h2 id="prerequisites">Prerequisites</h2>-
<p>To deploy your own version using the Launch Stack button or scripts/<code>deploy.sh</code> (described in the Grow your own section), you will need:</p>-
<ul>-
<li>Amazon Bedrock AgentCore access, including AgentCore runtime and AgentCore memory.</li>-
<li>Model access granted for the models you plan to route to: Claude Haiku 4.5 for text and Claude Sonnet 4.5 for vision (or the equivalents available in your account).</li>-
<li>Docker with <code>linux/arm64</code> build support, plus the AWS Command Line Interface (AWS CLI) configured. This is needed only if you plan to build and push your own image.</li>-
<li>A Telegram bot token (from BotFather) to serve as the assistant’s front door.</li>-
<li>Basic familiarity with agent orchestration concepts and CloudFormation.</li>-
</ul>-
<h2 id="the-architecture-a-serverless-agent-on-agentcore-runtime">The architecture: A serverless agent on AgentCore runtime</h2>-
<p>Every component lives in a single CloudFormation template, and no build tooling is required to launch. The following sections walk through the load-bearing decisions.</p>-
<h3 id="agentcore-runtime-pay-only-for-active-compute">AgentCore runtime: Pay only for active compute</h3>-
<p>The agent lives in a container on AgentCore runtime, which uses consumption-based pricing. You’re billed for the compute your agent actively consumes, not for wall-clock uptime, and you don’t pay for the time when waiting for I/O such as model response. For a personal assistant used in shor…-
<p>The runtime enforces a minimal container contract: listen on port 8080, and expose <code>GET /ping</code> for health and <code>POST /invocations</code> as the agent entry point. Our container is <code>linux/arm64</code>, built multi-stage from the officia…-
<h3 id="openclaw-as-the-agent-substrate">OpenClaw as the agent substrate</h3>-
<p>OpenClaw provides the agent loop, tool use, and a skills system. It runs a wrapper (<code>server.py</code>) that adapts it to <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-http-protocol-contract.html" target="_blank" rel="noopener">AgentCor…-
<ul>-
<li>On container start, <code>server.py</code> launches <code>openclaw gateway run</code> as a subprocess and health-checks it.</li>-
<li><code>GET /ping</code> returns healthy quickly, so the AgentCore readiness probe passes.</li>-
<li><code>POST /invocations</code> does the real work: parse the payload, retrieve memory, assemble context, forward the turn to the gateway, and persist the result. One callout: AgentCore can thaw a frozen container whose subprocess has exited. So invocation path doesn’t assume t…-
</ul>-
<p>This wrapper pattern generalizes to other use cases. Any agent framework that runs as a local process can be adapted to the AgentCore runtime the same way, without modifying the framework itself.</p>-
<h3 id="two-models-routed-by-task">Two models, routed by task</h3>-
<p>Text chat and image understanding have different cost and quality tradeoffs, so the assistant routes them to different Claude models on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Bedrock</a>:</p>-
<ul>-
<li><strong>Claude Haiku 4.5 for text:</strong> Fast and cheap for the high-volume conversational turns that dominate daily use.</li>-
<li><strong>Claude Sonnet 4.5 for vision:</strong> Stronger multimodal reasoning for the less frequent but harder task of diagnosing a plant from a photo.</li>-
</ul>-
<p>Text turns flow through the OpenClaw gateway, which brings skills and session state. Image turns call the large language model (LLM) from Bedrock directly from <code>server.py</code>, passing the image bytes as multimodal content blocks. We route images around the gateway delibe…-
<p>The model IDs are environment variables (<code>MODEL_ID</code>, <code>VISION_MODEL_ID</code>), so you can swap models per deployment without rebuilding the image.</p>-
<h3 id="skills-as-the-reusable-capability-unit">Skills as the reusable capability unit</h3>-
<p>Capabilities are declared as skills in a <code>community-skills.json</code> manifest. A deploy-time script materializes them into the container and registers them in the OpenClaw config before the image is built. Sprout ships with weather, reminders, and plant notes skills at th…-
<h3 id="telegram-as-the-serverless-front-door">Telegram as the serverless front door</h3>-
<p>Telegram is a practical channel for a personal assistant since it’s webhook-based, and it keeps everything serverless. It requires no client development, works on every device the user already owns, and supports text, images, and rich formatting through a straightforward bot API. BotFather …-
<p>One formatting lesson to note: Telegram’s legacy markdown model is unforgiving about unescaped characters and a single stray underscore in a model response can make the whole message fail to send. Rendering replies as HTML is reliable so the assistant converts model output to Telegram-safe …-
<h2 id="memory-turning-disposable-chats-into-durable-knowledge">Memory: Turning disposable chats into durable knowledge</h2>-
<p>The architecture described so far is a capable, cheap, serverless agent, but on its own it still forgets you between conversations. Memory is what changes that. Imagine mentioning weeks ago that you garden organically, and today the assistant recommends a treatment and adds, on its own, tha…-
<h3 id="the-mental-model-short-term-events-long-term-extraction">The mental model: Short-term events, long-term extraction</h3>-
<p>AgentCore memory has two layers. <strong>Short-term memory</strong> stores every conversation turn as an event through <code>CreateEvent</code>, keyed by <code>actorId</code> (the Telegram chat ID) and <code>sessionId</code>. This is the raw t…-
<ul>-
<li><code>USER_PREFERENCE</code>: explicit choices the gardener stated (“I only use organic fertilizer”).</li>-
<li><code>SEMANTIC</code>: inferred facts (“grows Mexican petunias in a Corten steel raised bed”).</li>-
<li><code>SUMMARIZATION</code>: episodic session summaries (“discussed yellowing lower leaves during a heat wave”).</li>-
</ul>-
<h3 id="namespaces-one-garden-per-gardener">Namespaces: One garden per gardener</h3>-
<p>Sprout files records into per-user namespaces, so no two chats ever mix:</p>-
<ul>-
<li><code>sprout/{chat_id}/long_term</code>: preferences and semantic facts.</li>-
<li><code>sprout/{chat_id}/episodic/{session_id}</code>: session summaries.</li>-
</ul>-
<p>The chat ID is the only variable segment, which makes isolation straightforward to reason about and to test: each unique gardener maps to exactly one namespace, and no two gardeners collide.</p>-
<h3 id="the-retrieval-assembly-and-injection-pipeline">The retrieval, assembly, and injection pipeline</h3>-
<p>On every turn, the agent retrieves the relevant long-term records, ranks them, and injects them into the system prompt. Here is what happens on every single message, inside <code>server.py</code>:</p>-
<ul>-
<li><strong>Retrieve.</strong> Call <code>RetrieveMemoryRecords</code> against <code>sprout/{chat_id}/long_term</code>, using the user’s message as the search query, capped at 50 results, under a 3-second budget. If retrieval times out or errors, we degrade…-
</ul>-
<div class="hide-language">-
<pre><code class="language-python">try:-
records = memory_client.retrieve_memory_records(-
memoryId=MEMORY_ID,-
namespace=f'sprout/{chat_id}/long_term',-
searchCriteria={-
'searchQuery': user_message,-
'topK': 50,-
'metadataFilters': []-
},-
) # 3s timeout-
except Exception:-
records = [] # fall back to answering without memory</code></pre>-
</div>-
<p><em>Snippet 1: Retrieving long-term records for the current turn (representative. See the repo for full source).</em></p>-
<p>Assemble function adds additional custom logic. We want the explicit preferences to rank ahead of inferred facts, order is stable within each class, and the result is capped before injection:</p>-
<div class="hide-language">-
<pre><code class="language-python">def assemble(records, cap=50):-
explicit = [r for r in records if r.type == 'USER_PREFERENCE']-
inferred = [r for r in records if r.type != 'USER_PREFERENCE']-
# explicit beats inferred; stable order within each class-
ordered = explicit + inferred-
return ordered[:cap]</code></pre>+
<dc:creator><![CDATA[Aamna Najmi]]></dc:creator>+
<pubDate>Wed, 07 Oct 2026 18:52:10 +0000</pubDate>+
<category><![CDATA[Amazon Bedrock]]></category>+
<category><![CDATA[Announcements]]></category>+
<category><![CDATA[Intermediate (200)]]></category>+
<guid isPermaLink="false">0ff2b32f3802714df60aafa631f537ec3996dfd3</guid>+
+
<description>Claude Haiku 5.5 is now available on Amazon Bedrock and Claude Platform on AWS. According to Anthropic, it is the fastest, most efficient model in the Claude 5.5 family, built for subagents and high-volume, cost-sensitive work, and costs around 75% less than Claude Haiku 4.5 for mo…+
<content:encoded><p>Today, we’re excited to announce the availability of Claude Haiku 5.5 on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a> and <a href="https://aws.amazon.com/blogs/machine-learning/introducing-claude-platfo…+
<p>Amazon Bedrock gives you Haiku 5.5 capabilities while keeping your data within AWS infrastructure with Regional data residency. It works with the AWS controls your team already uses, including AWS Identity and Access Management (IAM) for access, AWS CloudTrail for audit, Amazon CloudWatch f…+
<p>Claude Platform on AWS gives you direct access to Anthropic’s native platform experience and capabilities through the AWS Management Console. Build, test, and deploy with the same APIs, features, and console experience you’d get working with Anthropic directly, unified with AWS billing and …+
<p>This post covers Claude Haiku 5.5’s improvements, practical guidance on when to choose Haiku 5.5, and how to get started on Amazon Bedrock.</p>+
<h2 id="what-makes-claude-haiku-5.5-different">What makes Claude Haiku 5.5 different</h2>+
<p>Claude Haiku 5.5 is Anthropic’s most capable Haiku model, across coding, tool use, computer use, and agentic tasks. It’s also the first Haiku model with effort controls, so you can tune cost against intelligence for each task instead of picking one setting for an entire workload.</p>+
<p>The improvements stand out on quick and repeatable work at scale. For coding tasks, it acts as a subagent routing requests, reviewing code and classifying long documents. For knowledge work, Haiku 5.5 pulls key information from small-to-medium documents, does initial scans, and answers quic…+
<p>Haiku 5.5 handles agentic coding and multi-step tool use, and supports high-resolution images. Haiku 5.5 can be used as a strong computer use subagent for repetitive browser and desktop tasks, at a cost that holds up at scale. In development workflows, it’s a good fit for iterating quickly …+
<h2 id="pairing-claude-haiku-5.5-with-opus-5.5">Pairing Claude Haiku 5.5 with Opus 5.5</h2>+
<p>Haiku 5.5 pairs with the recently announced Claude Opus 5.5. Together, they make a strong team: Opus 5.5 plans and makes the judgment calls, and Haiku 5.5 carries out well-defined tasks quickly and at scale. You get careful reasoning where it counts and lower cost and latency everywhere.<…+
<ol type="1">+
<li><strong>Claude Opus 5.5 plans the work and makes the judgment calls.</strong> It breaks down complex problems, decides the approach, and takes on the hardest reasoning, such as release debugging, security review of large pull requests, and long analyses that end in a finished …+
<li><strong>Claude Haiku 5.5 takes on the fast layer of subagents.</strong> It handles quick, high-volume tasks, such as routing requests, classifying and summarizing, rewriting long documents, and applying small, specific changes across many files. As a review subagent, it can qu…+
</ol>+
<h2 id="getting-started-with-claude-haiku-5.5-on-amazon-bedrock">Getting started with Claude Haiku 5.5 on Amazon Bedrock</h2>+
<p>To try Haiku 5.5, open the <a href="https://console.aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock console</a>, choose <strong>Test</strong>, then <strong>Playground</strong>, and select Haiku 5.5 as the model. From there, you can …+
<div id="attachment_140971" style="width: 1314px" class="wp-caption alignnone">+
<img aria-describedby="caption-attachment-140971" class="size-full wp-image-140971" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/07/Screenshot-2026-10-07-at-1.27.14 PM.png" alt="" width="1304" height="764">+
<p id="caption-attachment-140971" class="wp-caption-text">Figure 1: Selecting an Anthropic Claude model in the Amazon Bedrock console Playground</p></div>-
<p><em>Snippet 2: The assembly step ranks explicit preferences before inferred facts.</em></p>-
<h3 id="metadata-subgrouping-memories-inside-a-namespace">Metadata: Subgrouping memories inside a namespace</h3>-
<p>Namespaces answer whose memory a record is, but metadata answers what it’s about. Inside <code>sprout/{chat_id}/long_term</code>, a semantic search for “my petunias are wilting”, would return everything that is close in meaning. For a gardener, that means a fertilizer preference…-
<p>One rule shapes every decision here. A metadata key is only filterable server-side if you declare it as an indexed key. You can read more in <a href="https://aws.amazon.com/blogs/machine-learning/structured-memory-filtering-with-metadata-in-agentcore-memory/" target="_blank" rel="noopene…+
<p>Programmatically, you can call the model with the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html" target="_blank" rel="noopener">Anthropic Messages API</a> against <code>bedrock-runtime</code> through the…+
<h3 id="prerequisites">Prerequisites</h3>+
<p>You must have the following prerequisites:</p>+
<ol type="1">+
<li>Active AWS account with Amazon Bedrock access.</li>+
<li>AWS Command Line Interface (AWS CLI) installed and configured.</li>+
<li>Python 3.10+.</li>+
<li>Boto3 installed: <code>pip install boto3</code>.</li>+
<li>Anthropic SDK installed: <code>pip install anthropic</code>.</li>+
<li>The Amazon Bedrock Token Generator for Amazon Bedrock authentication installed: <code>pip install aws_bedrock_token_generator</code>.</li>+
<li>AWS Identity and Access Management (IAM) permissions: <code>bedrock:InvokeModel</code>, <code>bedrock:InvokeModelWithResponseStream</code>.</li>+
</ol>+
<p>Here’s a quick example using the AWS SDK for Python (Boto3) with the InvokeModel API:</p><div class="hide-language">-
<pre><code class="language-yaml">IndexedKeys: # on the AWS::BedrockAgentCore::Memory resource-
- Key: type # seperate the kinds of records-
Type: STRING-
- Key: section # which bed or area it describes-
Type: STRING-
- Key: plants # what is growing there-
Type: STRINGLIST</code></pre>+
<pre><code class="language-python">import boto3+
import json+
+
# Create a Bedrock Runtime client+
bedrock_runtime = boto3.client(+
service_name="bedrock-runtime",+
region_name="us-east-1"+
)+
+
# Invoke Claude Haiku 5.5+
response = bedrock_runtime.invoke_model(+
modelId="global.anthropic.claude-haiku-5-5",+
contentType="application/json",+
accept="application/json",+
body=json.dumps({+
"anthropic_version": "bedrock-2023-05-31",+
"max_tokens": 4096,+
"messages": [+
{+
"role": "user",+
"content": "Can you explain the features of Amazon Bedrock?"+
}+
]+
})+
)+
+
result = json.loads(response["body"].read())+
# Haiku 5.5 may return a thinking block before the text block,+
# so select the text block rather than a fixed index.+
print(next(b["text"] for b in result["content"] if b["type"] == "text"))</code></pre></div>-
<p>Each entry names a key, which must match an indexed key to be filterable, and sets <code>extractionType</code> to either <code>STRICTLY_CONSISTENT</code>, passed through from the event, or <code>LLM_INFERRED</code>, extracted from the conversation. For in…-
<h3 id="persisting-the-turn-and-closing-the-loop">Persisting the turn and closing the loop</h3>-
<p>After the model responds, <code>server.py</code> calls <code>CreateEvent</code> with both the user turn and the assistant turn. That new event feeds the extraction strategies, which enrich the long-term store for next time.</p>+
<p>You can also use the Amazon Bedrock Converse API for a unified multi-model experience:</p><div class="hide-language">-
<pre><code class="language-python">memory.create_event(-
memoryId=MEMORY_ID,-
actorId=chat_id,-
sessionId=session_id,-
payload=[-
{'role': 'user', 'content': user_message},-
{'role': 'assistant', 'content': reply},+
<pre><code class="language-python">import boto3+
+
# Create a Bedrock Runtime client+
bedrock_runtime = boto3.client(+
service_name="bedrock-runtime",+
region_name="us-east-1"+
)+
+
# Invoke Claude Haiku 5.5+
response = bedrock_runtime.converse(+
modelId="global.anthropic.claude-haiku-5-5",+
messages=[+
{+
"role": "user",+
"content": [+
{+
"text": "Can you explain the features of Amazon Bedrock?"+
}+
]+
} ],-
) # feeds USER_PREFERENCE / SEMANTIC / SUMMARIZATION extraction; errors are logged, never fatal</code></pre>-
</div>-
<p><em>Snippet 3: Persisting the turn so the extraction strategies can enrich long-term memory asynchronously.</em></p>-
<p>Extraction is asynchronous, so a fact mentioned in this session typically becomes retrievable in a later one. Design for that delay: short-term session events cover the current conversation, and long-term records cover everything before it.</p>-
<h3 id="putting-it-together-a-personalized-watering-plan">Putting it together: A personalized watering plan</h3>-
<p>Here is where the full pipeline works end-to-end. Over a few conversations you catalog your whole garden, one plant at a time, in plain language. Each mention becomes an event. The extraction strategies extract information about the plant, its location, and its sun exposure into <code>…-
<div style="width: 810px" class="wp-caption alignnone">-
<a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-2.jpeg" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-2.jpeg" alt="Telegram chat where S…-
<p class="wp-caption-text">Figure 2: Sprout answers a question about the garden by recalling the stored plant inventory and growing conditions</p>+
inferenceConfig={+
"maxTokens": 4096+
}+
)+
+
if 'output' in response:+
blocks = response['output']['message']['content']+
print('\n'.join(b.get('text', '') for b in blocks if 'text' in b))</code></pre></div>-
<p>Using the scheduler skill on the Amazon EventBridge → Cron path, Sprout can also turn that plan into proactive reminders (“skip the herbs, the soil is still damp from yesterday”) and adjusts them against the weather skill when rain or a heat wave is coming.</p>-
<p>Memory and vision also compound each other. When the user sends a photo of a wilting plant, the image goes to Claude Sonnet 4.5 while the system prompt still carries everything the memory layer knows. The assistant matches the photo to the Mexican petunias already in the user’s saved invent…-
<div style="width: 810px" class="wp-caption alignnone">-
<a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-3.png" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-3.png" alt="Telegram chat where Spr…-
<p class="wp-caption-text">Figure 3: Vision and memory working together. The photo goes to the vision model while the system prompt carries the user’s stored garden context</p>+
<p>You can also use the Anthropic Messages API through the anthropic SDK package for a streamlined experience:</p>+
<div class="hide-language">+
<pre><code class="language-python">from anthropic import Anthropic+
from aws_bedrock_token_generator import provide_token+
+
token = provide_token(region="us-east-1")+
+
client = Anthropic(+
base_url="https://bedrock-runtime.us-east-1.amazonaws.com/anthropic",+
api_key=token,+
)+
+
# Invoke Claude Haiku 5.5+
response = client.messages.create(+
model="global.anthropic.claude-haiku-5-5",+
max_tokens=1024,+
messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}],+
)+
print(response)</code></pre></div>-
<p>Vision models aren’t infallible. In an earlier exchange without the inventory context, the same plant was confidently identified as a morning glory, a species with similar trumpet-shaped purple flowers. Grounding the vision model with the user’s own stored inventory is what turned a plausib…-
<h3 id="keeping-inference-costs-low-with-prompt-caching">Keeping inference costs low with prompt caching</h3>-
<p>Injecting memory into every turn makes the system prompt large, and a naive implementation would pay for those tokens on every request. Prompt caching on Amazon Bedrock addresses this. The assistant structures its prompt so that the stable prefix, the persona and the assembled memory block,…-
<p>The ordering rule matters more than any single setting: put stable content first, volatile content last, and keep the memory block’s internal ordering deterministic (which the preceding assembly function facilitates) so the prefix actually matches between requests.</p>-
<h2 id="design-guidelines-to-build-on-agentcore-and-openclaw">Design guidelines to build on AgentCore and OpenClaw</h2>-
<p>Sprout is one assistant, but the decisions behind it generalize. If you’re building your own assistant on this stack, the following guidelines are the ones we would carry to any domain.</p>-
<ul>-
<li><strong>Wrap, don’t fork.</strong> Adapt your agent framework to the AgentCore container contract with a thin HTTP wrapper rather than modifying the framework. The contract is small, port 8080 with <code>/ping</code> and <code>/invocations</code>, and a…-
<li><strong>Design namespaces before you store anything.</strong> Memory namespaces are your isolation boundary. Make the user ID the only variable segment, and choose it from a channel-native ID you already trust, such as the chat ID. Multi-tenant designs get audits and deletion …-
<li><strong>Treat memory as an enhancement, never a dependency.</strong> Every memory operation should be allowed to fail gracefully. Retrieval failures should produce a memoryless answer without blocking the reply. Users forgive a forgetful turn far more readily than a failed one…-
<li><strong>Route models by task.</strong> Use a fast, cost-effective model for high-volume text and reserve a stronger multimodal model for the turns that need it. Keep model IDs in environment variables so routing changes are configuration, not code.</li>-
<li><strong>Order prompts for the cache.</strong> Stable persona and memory first, volatile user input last, deterministic ordering throughout. This one structural habit is where most of the inference savings come from.</li>-
<li><strong>Plan for extraction latency.</strong> Long-term memory is extracted asynchronously, so don’t promise same-session recall of new facts. Let short-term session events cover the current conversation and long-term records cover prior ones.</li>-
<li><strong>Put a budget on it from day one.</strong> A consumption-based agent is inexpensive until a retry loop or a chatty user makes it otherwise. An AWS Budgets alert at 80 percent and 100 percent of a monthly cap costs nothing and catches surprises early.</li>-
<li><strong>Keep skills small and single-purpose.</strong> A skill should do one thing a user would name in a sentence, such as check the weather or set a reminder. Small skills are independently testable, independently swappable, and easy for the model to select correctly. A do-e…-
</ul>-
<h2 id="grow-your-own">Grow your own</h2>-
<p>Two ways to plant it, same garden:</p>-
<ul>-
<li><strong>Single-step Launch Stack:</strong> the CloudFormation template points at a public Amazon Elastic Container Registry (Amazon ECR) image, so it deploys nothing but a Telegram bot token.</li>-
<li>Build your own: The scripts/<code>deploy.sh</code> script validates the template, builds and pushes your own ARM64 image to your private Amazon ECR repository, deploys the stack, and registers the Telegram webhook, for a fully customizable build.</li>-
</ul>-
<p>Light personal use runs about $5–9/month as of July 2026 (roughly $2 infrastructure, $1–3 Haiku text, $2 Sonnet vision), with a built-in AWS Budget that alerts at 80 percent and 100 percent of a cap you set.</p>-
<p>The full source code is available in the <a href="https://github.com/aws-samples/sample-agentcore-memory-openclaw" target="_blank" rel="noopener">sample-agentcore-memory-openclaw GitHub repository</a>.</p>-
<h2 id="clean-up">Clean up</h2>-
<p>When you are done experimenting, tear everything down to avoid ongoing charges. Because the whole system is one CloudFormation stack, cleanup is mostly a single delete:</p>-
<ol type="1">-
<li>Delete the CloudFormation stack. This removes the AgentCore runtime agent, API Gateway, the Lambda functions, the Amazon EventBridge schedule, and the associated AWS Identity and Access Management (IAM) roles.</li>-
<li>Delete the AgentCore memory store (and its namespaces) so no user records are retained.</li>-
<li>Delete any images you pushed to your private ECR repository, and the repository itself if it’s no longer needed.</li>-
<li>Remove the AWS Budget alert if you created one outside the stack.</li>-
<li>Revoke Telegram’s webhook (or delete the bot through BotFather), and revoke Bedrock model access if you no longer need it.</li>-
</ol>-
<h2 id="conclusion">Conclusion</h2>-
<p>The reusable core of this solution is a serverless agent on Amazon Bedrock AgentCore with a skills system and managed memory. AgentCore memory removes the need to build custom vector stores and extraction pipelines while leaving you full control over what the agent remembers and forgets, co…-
<p>To go further, start with a single domain such as watering reminders and expand memory scope incrementally, explore episodic memory so the agent can reference specific past conversations (“last time we discussed the fig tree, you decided to hold off on fertilizer”), or fork the <a href="…-
<p>To learn more, refer to the <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html" target="_blank" rel="noopener">AgentCore documentation</a>. The following related posts cover the building blocks in more depth:</p>-
<ul>-
<li><a href="https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentcore-memory-building-context-aware-agents/" target="_blank" rel="noopener">Amazon Bedrock AgentCore memory: Building context-aware agents</a></li>-
<li><a href="https://aws.amazon.com/blogs/machine-learning/building-smarter-ai-agents-agentcore-long-term-memory-deep-dive/" target="_blank" rel="noopener">Building smarter AI agents: AgentCore long-term memory deep dive</a></li>-
<li><a href="https://aws.amazon.com/blogs/machine-learning/effectively-use-prompt-caching-on-amazon-bedrock/" target="_blank" rel="noopener">Effectively use prompt caching on Amazon Bedrock</a></li>-
<li><a href="https://aws.amazon.com/blogs/machine-learning/securely-launch-and-scale-your-agents-and-tools-on-amazon-bedrock-agentcore-runtime/" target="_blank" rel="noopener">Securely launch and scale your agents and tools on Amazon Bedrock AgentCore runtime</a></li>-
</ul>+
<p>You can explore the <a href="https://github.com/aws-samples/anthropic-on-aws/blob/main/notebooks/claude_haiku_5_5_getting_started/claude-haiku-5-5-getting-started.ipynb" target="_blank" rel="noopener">Getting Started notebook</a> for more examples. You can monitor usage, perform…+
<h2 id="availability">Availability</h2>+
<p>Claude Haiku 5.5 is available today on Amazon Bedrock through the US Geo CRIS (us.), EU Geo CRIS (eu.), AU Geo CRIS (au.), JP Geo CRIS (jp.) and Global CRIS (global.) inference profiles on <code>bedrock-runtime</code>. In AWS GovCloud (US), it’s available on both the <code>…+
<p>See the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-anthropic.html" target="_blank" rel="noopener noreferrer">Amazon Bedrock documentation</a> for the full list of supported AWS Regions. For pricing information, see <a href="https://aws.amazon.co…+
<p>Give Claude Haiku 5.5 a try on the <a href="https://console.aws.amazon.com/bedrock" target="_blank" rel="noopener">Amazon Bedrock console</a>, in <a href="https://aws.amazon.com/blogs/machine-learning/introducing-claude-platform-on-aws-anthropics-native-platform-through-your-…<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/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-4.jpg" alt="Thiago Verney" width="100" height="133">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/09/18/ML-21953-2.jpg" alt="Aamna Najmi" width="100" height="133"> </div>-
<h3 class="lb-h4">Thiago Verney</h3>-
<p style="overflow: hidden">Thiago is a Front-End Engineer on the One MHS team at Amazon, specializing in AI-powered interfaces using React, TypeScript, and modern federated microfrontend architecture. He builds user-focused interfaces for operations-leader in FC, drawing on prior work on th…+
<h3 class="lb-h4">Aamna Najmi</h3>+
<p style="overflow: hidden">Aamna is a Senior Specialist Solutions Architect for Generative AI focusing on Anthropic models and operationalizing and governing generative AI systems at scale on Amazon Bedrock. She helps ISVs solve their challenges, embrace innovation, and create new business … </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/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-5.jpg" alt="Sathya Balakrishnan" width="100" height="133">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/05/11/ml-20969-image-6.png" alt="Dani Mitchell" width="100" height="133"> </div>-
<h3 class="lb-h4">Sathya Balakrishnan</h3>-
<p style="overflow: hidden">Sathya is a Pr. Cloud Architect in the Professional Services team at Amazon Web Services (AWS), specializing in data and machine learning (ML) solutions. He works with US federal financial clients. He is passionate about building pragmatic solutions to solve custo…+
<h3 class="lb-h4">Dani Mitchell</h3>+
<p style="overflow: hidden">Dani is a Senior Specialist Solutions Architect for Generative AI at AWS, working on go-to-market for Anthropic on Amazon Bedrock. He helps enterprises across the world design and deploy generative AI solutions using Anthropic’s models and capabilities on Amazon B… </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/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/02/ML-21277-6.jpg" alt="Akarsha Sehwag" width="100" height="133">+
<img loading="lazy" class="alignnone size-full" src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/10/07/ML-22086-1.jpg" alt="Alfredo Castillo" width="100" height="133"> </div>-
<h3 class="lb-h4">Akarsha Sehwag</h3>-
<p style="overflow: hidden">Akarsha is a Sr.&nbsp;Gen AI Data Scientist for Amazon Bedrock AgentCore GTM team. With over 7 years of expertise in AI/ML, she has built production-ready enterprise solutions across diverse customer segments in Generative AI, Deep Learning and Computer Vision…+
<h3 class="lb-h4">Alfredo Castillo</h3>+
<p style="overflow: hidden">Alfredo is a Senior Specialist Solutions Architect for Generative AI at AWS, focusing on Anthropic models go-to-market on Amazon Bedrock. He works with Financial Services customers to design and scale generative AI solutions across distributed systems and turn gen…+
</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/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/04/21/ml-20855-image-2.png" alt="Sofian Hamiti" width="100" height="133">+
</div>+
<h3 class="lb-h4">Sofian Hamiti</h3>+
<p style="overflow: hidden">Sofian is a technology leader with over 12 years of experience building AI solutions, and leading high-performing teams to maximize customer outcomes. He is passionate about empowering diverse talents to drive global impact and achieve their career aspirations.<… </div></footer></content:encoded> @
@@ -229,71 +184,85 @@ except Exception: </item> <item>-
<title>Responsible AI governance: How AWS positions customers to align with ISO/IEC 42005:2025</title>-
<link>https://aws.amazon.com/blogs/machine-learning/responsible-ai-governance-how-aws-positions-customers-to-align-with-iso-iec-420052025/</link>+
<title>Rethinking access control for RAG with Amazon Quick and Amazon Bedrock</title>+
<link>https://aws.amazon.com/blogs/machine-learning/rethinking-access-control-for-rag-with-amazon-quick-and-amazon-bedrock/</link> -
<dc:creator><![CDATA[Adam Powers]]></dc:creator>-
<pubDate>Tue, 06 Oct 2026 15:53:28 +0000</pubDate>-
<category><![CDATA[Intermediate (200)]]></category>-
<category><![CDATA[Responsible AI]]></category>-
<category><![CDATA[Thought Leadership]]></category>-
<guid isPermaLink="false">3a55da10835515b8cd207733e9488cdc59af5b6a</guid>-
-
<description>AWS invests in tools that help customers align with international standards for responsible AI governance. In this post, we explore the AI system impact assessment: what it is, how it improves enterprise-wide risk management, and how ISO/IEC 42005:2025 codifies best practices for c…-
<content:encoded><p>With generative AI adoption moving <a href="https://hai.stanford.edu/assets/files/ai_index_report_2026_chapter_4_economy.pdf" target="_blank" rel="noopener">faster than the personal computer or the internet</a> and <a href="https://hai.stanford.edu/…-
<p>We support this facilitator population in instituting or improving systematic approaches to AI governance within their organization through review of the international standard <a href="https://www.iso.org/standard/42005" target="_blank" rel="noopener">ISO/IEC 42005:2025,</a> ex…-
<p>Standards-based governance frameworks offer a practical path forward — and AWS has invested in making them actionable. At Amazon we have been proponents of the <a href="https://www.iso.org/home.html" target="_blank" rel="noopener">International Organization for Standardization (ISO)&l…-
<h2 id="ai-system-impact-assessments">AI system impact assessments</h2>-
<p>An AI system impact assessment is a documented process of AI system risk identification by which organizations developing, providing, or using AI systems consider impacts to the organization, individuals, communities, groups, and societies. An AI system impact assessment process also channe…-
<h2 id="ai-impact-assessments-facilitate-enterprise-wide-risk-management">AI impact assessments facilitate enterprise-wide risk management</h2>-
<p>AI system impact assessments are an integral part of an organization’s overall risk management process. ISO/IEC 42005 provides explicit guidance on how to integrate AI system impact assessments into existing impact assessment processes within an enterprise, which often include different kin…-
<p>For organizations with a robust impact assessment ecosystem, Annex D of ISO/IEC 42005 provides a process that organizations can use to simplify impact assessments and avoid duplication, helping organizations coordinate the relevant reviews required by an AI system impact assessment (for exa…-
<p>For organizations that prefer a standalone AI impact assessment, Annex E of ISO/IEC 42005 provides a ready-to-use template for self-contained implementation.</p>-
<h3 id="how-isoiec-42005-connects-you-to-your-ai-governance-process">How ISO/IEC 42005 connects you to your AI governance process</h3>-
<p>ISO/IEC 42005 unlocks a more integrated AI governance process for customers. Specifically, the standard provides guidance on how to develop the content of AI system impact assessments, how to perform AI system impact assessments, when to integrate AI system impact assessments within the sta…-
<h3 id="creating-repeatable-and-scalable-ai-system-impact-assessment-processes">Creating repeatable and scalable AI system impact assessment processes</h3>-
<p>Customers aiming to develop a structured, consistent approach to performing and documenting AI system impact assessments will find guidance in ISO/IEC 42005. The standard specifically covers the full assessment life cycle (including scoping and execution, analysis and reporting, and ongoing…-
<p>When establishing the timing for assessment and reassessment that fit within the broader AI development lifecycle, the standard recommends considering what triggers (evaluating both external and internal factors) might point to the need for a reassessment, for example, applicable legal requ…-
<h3 id="designing-assessments-the-questions-your-assessment-needs-to-answer">Designing assessments: The questions your assessment needs to answer</h3>-
<p>Customers looking for where to start with establishing AI system impact assessments will find ISO/IEC 42005 specifies the specific information that should be documented in an AI system impact assessment via a templated assessment approach, explaining how to also leverage other risk assessme…-
<ul>Diff display stops at 400 lines. The line counts above are from the whole diff. 64 lines shown here cut at 300 characters. The raw artifact at this commit is linked above.