Copilot Studio · Modern Experience

The new Copilot Studio experience BlastBox Omega

A hands-on guide to the new Agents and Workflows in Copilot Studio. The retro-future game store, run by agents.

Copilot Studio has been rebuilt for complex, multi-step work, moving from a single chatbot to coordinated, multi-agent systems. This is a technical guide from the CAT team on building enterprise-grade scenarios on that new foundation: practical patterns for connected agents, inline MCP servers, runtime skills, and generated files, each one backed by a complete, runnable reference you can deploy and inspect. Copilot Studio has been rebuilt for complex, multi-step work, moving from a single chatbot to coordinated, multi-agent systems. BlastBox Omega is a complete, runnable reference: a parent agent that delegates to connected agents, calls multiple inline MCP servers, runs per-agent skills that generate and execute Python at runtime, and returns real generated files. End-to-end reference scenarios spanning agents and workflows in the new Copilot Studio.

store-associate-assistant
Console gave out 10 days in. Replace or refund, and cancel his BlastPass. Walk me through it.
→ asking Store Policy Agent to rule the defect
MCP search_policy warranty
→ asking Inventory & Fulfillment Agent for stock
MCP check_stock MEGA in stock
SKILL prorated-refund-calculator python
Warranty swap to MEGA · refund $76.66 applied · net due $23.34.
📄 blastbox_slip.pdf generated

The building blocks of the new agent experience

Every scenario composes the same primitives of the Copilot Studio Modern Agent Experience. The more advanced scenarios simply orchestrate more of them at once.

🤝

Connected agents

A parent orchestrator delegates to specialist child agents and weaves their answers back into a single conversation.

📝

AI Skills

Reusable procedures the agent follows to get a task done, and they can reference assets like scripts and templates along the way.

🐍

Code Interpreter

Agents generate and run code at runtime to compute, transform, and analyze, going beyond text to real calculation.

📄

File Generation

Agents produce real deliverables, PDFs, images, and documents, that users can download and hand off.

🔄

Adaptive Orchestration

The agent plans dynamically across turns, asks for clarification when a step is ambiguous, and revises its plan when the request changes.

🧠

Memory

Context and earlier results persist across the conversation, so the agent builds on what is already known instead of starting over.

📚

Knowledge

Grounded answers from connected sources, documents, sites, and structured data.

🛠️

Tools/MCP Servers

Agents call external systems and APIs as tools through MCP servers and connectors, extending what they can do beyond built-in capabilities.

Scenarios

End-to-end transcripts that put the building blocks to work, from a quick self-serve task to a full multi-agent flagship. More scenarios will land here over time.

Stand up the store

Import the solution, create the MCP connections, add the policy knowledge, publish the agents, then run the scripted prompts. Everything runs inside Power Platform. No servers, no code to host.

1
Import the solution

Upload the managed zip in Power Apps

2
Publish all customizations

Deploys the inline connector code to APIM

3
Create MCP connections

Click Create for each of the four connectors

4
Publish & play

Publish all four agents, then run the two scenarios