Scaling the Claw: Skills, Shell, CodeAct and Background Agents

From the creator

Four additions make the agent genuinely useful. Skills package domain knowledge such as valuation and risk scoring into files it discovers and loads only when a request calls for them, including skills managed centrally in Foundry that update with no redeploy. Shell access lets it reorganise a messy folder of trade confirmations, confined to one working directory. CodeAct gives it a sandbox where it writes and runs code to work out an answer rather than guessing at the arithmetic. Background agents let it research several tickers at once and pull the results back together. 📌 This event is part of a series. Learn more here: https://aka.ms/FMTA/series 🔗 Learn more by exploring the resource: https://aka.ms/AgentHarness ⌚ Chapters: 00:00 Introduction and Welcome 02:17 Defining the Agent and the Harness 04:42 Recap of Session 1 and 2 09:51 Introduction to Skills in the Harness 12:13 Demonstrating Skill Discovery and Loading 19:36 Executing Skills with the Microsoft Agent Framework 24:25 Confined Shell Access and Security Policies 28:51 Implementing Local Shell Executors 35:42 Demo: Tidy up Trade Confirmations via Shell 42:25 CodeAct and Python Scripting for Calculations 47:08 Demo: Running Portfolio Calculations with CodeAct 51:51 Introduction to Background Agents 53:25 Demo: Research Agent Orchestration #MicrosoftReactor #LearnConnectBuild [eventID:27519]

Published 2026-09-17 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.