Tell the Robot What You Want — Sandhya Subramani, AWS
Source
youtube.com
Author
AI Engineer
Date
Context
A robot can gain a natural-language interface while retaining its existing movement controllers. The publisher's description of this talk presents Scout, a four-legged robot whose AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → layer chooses among preset actions. The agent decides what to do; a trained movement policy handles how to execute the selected action.
This separation explains the proposed extension: hardware actions become tools an agent can select in response to a request. It does not mean the LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → has learned a new physical agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition →. The description also reports failures during the demonstration, so conversational flexibility should not be mistaken for reliable physical execution.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
videoDeploying AI Inside a Bank Is Not an Engineering Problem — Paden Gayle, Applied AI Engineers
videoThe Agent Works. Does Anyone Trust It? — Michele Grant, Leading at Scale
videoWhat Technical Due Diligence Finds When the Deck Says “70% Automated” — Soukaïna Abelhad
videoTokens Are the Cheap Part — Steve Jamison, Jellyfish
