Conversation
- Create physical-ai/ subdirectory with 6 media assets - Add 3 new authors (cagatay-cali, rachita-chandra, aaron-su) - Create strands-physical-ai.mdx with frontmatter and placeholder Resolves #736
Documentation Preview ReadyYour documentation preview has been successfully deployed! Preview URL: https://d3ehv1nix5p99z.cloudfront.net/pr-cms-739/docs/user-guide/quickstart/overview/ Updated at: 2026-04-06T21:12:37.922Z |
|
/strands can you copy the blog content yourself? |
|
/strands can you fix the links in the blog post that point to other pages on the docs page? They should follow this pattern when linking to another page on the docs site: Hooks |
Convert 6 external strandsagents.com documentation links to internal relative paths following the /docs/... pattern used by other blog posts: - bidirectional streaming quickstart - steering (plugins/steering, not experimental/steering) - Ollama provider - llama.cpp provider - agents-as-tools - Strands Agents homepage
github-actions
bot
changed the title
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
|
|
||
| Agentic AI systems are rapidly expanding beyond the digital world and into the physical, where AI agents perceive, reason, and act in real environments. As AI systems increasingly interact with the physical world through robotics, autonomous vehicles, and smart infrastructure, a fundamental question emerges: how do we build agents that leverage massive cloud compute for complex reasoning while maintaining millisecond-level responsiveness for physical sensing and actuation? | ||
|
|
||
| This year has been transformative for agentic AI at AWS. We [launched Strands Agents in May 2025](https://aws.amazon.com/blogs/opensource/introducing-strands-agents-an-open-source-ai-agents-sdk/), bringing a simple developer experience and [model-driven approach](https://aws.amazon.com/blogs/opensource/strands-agents-and-the-model-driven-approach/) to agent development. In July, [we released version 1.0](https://aws.amazon.com/blogs/opensource/introducing-strands-agents-1-0-production-ready-multi-agent-orchestration-made-simple/) with multi-agent orchestration capabilities and [introduced Amazon Bedrock AgentCore](https://aws.amazon.com/blogs/aws/introducing-amazon-bedrock-agentcore-securely-deploy-and-operate-ai-agents-at-any-scale/) to accelerate AI agents to production at scale. At re:Invent 2025, we expanded Strands with the [TypeScript SDK](https://github.com/strands-agents/sdk-typescript), [evaluations](https://github.com/strands-agents/evals), [bidirectional streaming for voice agents](/docs/user-guide/concepts/bidirectional-streaming/quickstart/), and [steering for guiding agents within boundaries](/docs/user-guide/concepts/plugins/steering/). Today, we're exploring how these capabilities extend to the edge and physical AI, where agents don't just process information but work alongside us in the physical world. |
There was a problem hiding this comment.
Issue: Cross-blog link uses external AWS URL instead of internal path
Line 21 links to the "model-driven approach" blog via the external AWS blog URL (https://aws.amazon.com/blogs/opensource/strands-agents-and-the-model-driven-approach/), but this blog post already exists internally at /blog/strands-agents-model-driven-approach/. Other blog posts in this repo (e.g., the steering blog) use internal cross-references for content that lives on this site.
Similarly, the "Strands Agents" and "version 1.0" blogs referenced in the same paragraph also exist as internal blog posts (introducing-strands-agents, introducing-strands-agent-sops, etc.).
Suggestion: Convert cross-references to other blog posts in this repo to internal paths (e.g., [model-driven approach](/blog/strands-agents-model-driven-approach/)) to keep readers on-site and ensure links don't break if the external URLs change.
|
|
||
| This year has been transformative for agentic AI at AWS. We [launched Strands Agents in May 2025](https://aws.amazon.com/blogs/opensource/introducing-strands-agents-an-open-source-ai-agents-sdk/), bringing a simple developer experience and [model-driven approach](https://aws.amazon.com/blogs/opensource/strands-agents-and-the-model-driven-approach/) to agent development. In July, [we released version 1.0](https://aws.amazon.com/blogs/opensource/introducing-strands-agents-1-0-production-ready-multi-agent-orchestration-made-simple/) with multi-agent orchestration capabilities and [introduced Amazon Bedrock AgentCore](https://aws.amazon.com/blogs/aws/introducing-amazon-bedrock-agentcore-securely-deploy-and-operate-ai-agents-at-any-scale/) to accelerate AI agents to production at scale. At re:Invent 2025, we expanded Strands with the [TypeScript SDK](https://github.com/strands-agents/sdk-typescript), [evaluations](https://github.com/strands-agents/evals), [bidirectional streaming for voice agents](/docs/user-guide/concepts/bidirectional-streaming/quickstart/), and [steering for guiding agents within boundaries](/docs/user-guide/concepts/plugins/steering/). Today, we're exploring how these capabilities extend to the edge and physical AI, where agents don't just process information but work alongside us in the physical world. | ||
|
|
||
|  |
There was a problem hiding this comment.
Issue: The GIF is 4.5MB which will impact page load time, especially on slower connections.
Suggestion: Consider compressing the GIF (tools like gifsicle can significantly reduce size) or converting to an optimized video format (MP4/WebM) wrapped in an HTML <video> tag with autoplay loop muted attributes, which typically achieves 80-90% size reduction over GIF.
|
Assessment: Comment This is a well-structured blog post republication that follows established patterns in the repo. The frontmatter, internal link conversions, image organization, and code formatting all look correct. Review Details
Overall the PR cleanly addresses the acceptance criteria in #736. |
2 participants
Summary
Adds the "Building intelligent physical AI: From edge to cloud" blog post to the Strands documentation blog section, republished from the AWS Open Source Blog with proper canonical URL attribution.
Changes
src/content/blog/physical-ai/with 6 media assets (1 GIF, 5 PNGs)authors.yaml:cagatay-cali,rachita-chandra,aaron-susrc/content/blog/strands-physical-ai.mdxwith full content, local image references, and Python syntax-highlighted code blocksstrandsagents.comdocumentation URLs to internal relative paths (e.g.,/docs/user-guide/concepts/multi-agent/agents-as-tools/) matching the pattern used by existing blog postsContent sections
Resolves #736