<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf" -->

---
title: Tell the Robot What You Want — Sandhya Subramani, AWS
description: A live demo showcases a rover robot named Scout controlled through an agentic AI layer built on AWS's open-source Strands Agents framework. The robot runs on a...
canonical: https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Tell the Robot What You Want — Sandhya Subramani, AWS | daily.dev
og:description: A live demo showcases a rover robot named Scout controlled through an agentic AI layer built on AWS's open-source Strands Agents framework. The robot runs on a...
og:url: https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf
og:image: https://api.daily.dev/og/posts/Ebko1VATf.png
og:image:alt: Tell the Robot What You Want — Sandhya Subramani, AWS
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Tell the Robot What You Want — Sandhya Subramani, AWS

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 17 min read · 1 upvotes · 0 comments

## Summary

A live demo showcases a rover robot named Scout controlled through an agentic AI layer built on AWS's open-source Strands Agents framework. The robot runs on a Raspberry Pi connected via 4G, using three simultaneous Strands agents (thinker, communication, and voice) to perceive its environment, converse in natural language via Telegram and web app, and decide which preset robot policies to invoke. Under the hood it uses Anthropic Claude Opus for reasoning and OpenAI's real-time voice model for speech, demonstrating how a hardware 'robot tool' can be wired into an LLM agent with just five lines of code, alongside a vision of VLA models eventually growing as capable as large language models.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=S6aSoQ6_u5A>

## Questions this post answers

### What is Strands Agents and how does it work with robots?

Strands Agents is an open-source agentic framework built by AWS that lets a large language model orchestrate which preset robot tool or policy to call based on natural language instructions, rather than requiring explicit step-by-step programming. It supports more than 40 different robots across eight categories, and getting started requires roughly five lines of code, importing the strands agent and assigning a robot tool.

_Developers experimenting with agentic robot control can follow frameworks like Strands Agents on daily.dev._

### How does an agent decide which robot policy or action to execute?

The agentic layer sits atop four layers: the agent itself, a policy provider, a backend interface (simulation or real hardware chip), and the physical robot output. The agent interprets a natural language command, selects the appropriate policy from those it has access to via a policy provider, and that policy runs as a VLA model on the backend before producing a physical action on the robot.

_Anyone architecting agent-to-hardware pipelines can track frameworks like this one on daily.dev._

### Which LLM powers the Strands agent in this robot demo?

The underlying brain is Anthropic's Claude Opus model, configured through a system prompt that defines the agent's rules and the tools it has access to, while voice responses are generated using OpenAI's real-time voice model. The Strands harness uses this configuration to decide which tool to invoke based on the natural language command given.

_Developers comparing model choices for agentic systems can keep tabs on setups like this via daily.dev._

## Similar posts on daily.dev

- [AWS creates a sandbox for its agent experiments](https://daily.dev/posts/aws-creates-a-sandbox-for-its-agent-experiments-r5p1skjmm) · The New Stack · 0 upvotes · 0 comments
- [Build and Run Your Own AI Agent in the Cloud](https://daily.dev/posts/build-and-run-your-own-ai-agent-in-the-cloud-aoostzrec) · Towards Data Science · 1 upvotes · 0 comments
- [AWS Launches Strands Labs for Experimental AI Agent Projects](https://daily.dev/posts/aws-launches-strands-labs-for-experimental-ai-agent-projects-h0ycai6cx) · InfoQ · 1 upvotes · 0 comments
- [I Built My First AI Agent With AWS AgentCore, and the Hardest Part Wasn't the AI](https://daily.dev/posts/i-built-my-first-ai-agent-with-aws-agentcore-and-the-hardest-part-wasn-t-the-ai-z5jrclpu6) · DEV · 2 upvotes · 0 comments

---

Tags: [#aws](https://daily.dev/tags/aws), [#ai-agents](https://daily.dev/tags/ai-agents), [#robotics](https://daily.dev/tags/robotics), [#agentic-ai](https://daily.dev/tags/agentic-ai)

[View this post on daily.dev](https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Tell the Robot What You Want — Sandhya Subramani, AWS","url":"https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf"},"datePublished":"2026-08-29T18:39:27.484Z","dateModified":"2026-09-14T06:56:03.883Z","description":"A live demo showcases a rover robot named Scout controlled through an agentic AI layer built on AWS's open-source Strands Agents framework. The robot runs on a...","image":"https://i.ytimg.com/vi/S6aSoQ6_u5A/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/S6aSoQ6_u5A/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"aws,ai-agents,robotics,agentic-ai","timeRequired":"PT17M","video":{"@type":"VideoObject","name":"Tell the Robot What You Want — Sandhya Subramani, AWS","description":"A live demo showcases a rover robot named Scout controlled through an agentic AI layer built on AWS's open-source Strands Agents framework. The robot runs on a...","thumbnailUrl":"https://i.ytimg.com/vi/S6aSoQ6_u5A/sddefault.jpg","uploadDate":"2026-08-29T18:39:27.484Z","duration":"PT17M","url":"https://api.daily.dev/r/Ebko1VATf","embedUrl":"https://www.youtube.com/embed/S6aSoQ6_u5A"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Tell the Robot What You Want — Sandhya Subramani, AWS"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tell-the-robot-what-you-want-sandhya-subramani-aws-ebko1vatf#faq","mainEntity":[{"@type":"Question","name":"What is Strands Agents and how does it work with robots?","acceptedAnswer":{"@type":"Answer","text":"Strands Agents is an open-source agentic framework built by AWS that lets a large language model orchestrate which preset robot tool or policy to call based on natural language instructions, rather than requiring explicit step-by-step programming. It supports more than 40 different robots across eight categories, and getting started requires roughly five lines of code, importing the strands agent and assigning a robot tool. Developers experimenting with agentic robot control can follow frameworks like Strands Agents on daily.dev."}},{"@type":"Question","name":"How does an agent decide which robot policy or action to execute?","acceptedAnswer":{"@type":"Answer","text":"The agentic layer sits atop four layers: the agent itself, a policy provider, a backend interface (simulation or real hardware chip), and the physical robot output. The agent interprets a natural language command, selects the appropriate policy from those it has access to via a policy provider, and that policy runs as a VLA model on the backend before producing a physical action on the robot. Anyone architecting agent-to-hardware pipelines can track frameworks like this one on daily.dev."}},{"@type":"Question","name":"Which LLM powers the Strands agent in this robot demo?","acceptedAnswer":{"@type":"Answer","text":"The underlying brain is Anthropic's Claude Opus model, configured through a system prompt that defines the agent's rules and the tools it has access to, while voice responses are generated using OpenAI's real-time voice model. The Strands harness uses this configuration to decide which tool to invoke based on the natural language command given. Developers comparing model choices for agentic systems can keep tabs on setups like this via daily.dev."}}]}
```

