AAIBAST guided workshop
Academy / Inventory Rebalancing Agent
Workshop settingsOpen field guide

Evidence-grounded customer journey

Inventory Rebalancing Agent

Build this agent step by step, then show it to a customer. Easy mode lets AI do the clicks; Manual mode shows every step yourself.

About this workshop
Workshop mission: Turn motivated, open-minded, non-technical sales professionals into AI superheroes who can match the practical output and problem-solving pace of technical peers who are not using AI, while staying evidence-grounded, governed, and honest about what the tools proved.
Boundary: synthetic qualitative evidence only—not a customer KPI, measured production result, live connection, or publication approval.

Self-paced local achievements

Workshop achievements

0 total points 0 in this workshop

0 of 0 Easy checkpoints complete

  • No badges yet
View achievements and local profile

Optional public verification

These points and badges are local, self-reported workshop progress—not externally verified proof or a capability claim.

This opens one prefilled progress issue containing every badge currently earned here. Nothing syncs until you submit it. Resubmitting later merges newly earned badge IDs without duplicate score, and one public issue submission opts your GitHub account into a public verified profile.

1

Workshop setup

Open GitHub Copilot Chat

Start in GitHub Copilot Chat. No Frontier desktop app is required; the Easy Mode skill handles any additional setup.

Get ready
  1. Open VS Code with the GitHub Copilot Chat extension installed.
  2. Sign in to GitHub with an account that has Copilot access.
  3. Open the Copilot Chat panel and select Agent mode.
Expected result

GitHub Copilot Chat is open in VS Code, signed in, and set to Agent mode.

What you will learn

  • Use the single Easy Mode skill.
  • Build and prove the portable agent.
  • Deploy the reviewed solution as an unpublished Draft.
  • Confirm the behavior yourself in Copilot Studio Preview.
  • Recognize the evidence that means the module is complete.

Before you begin

  • Use VS Code with GitHub Copilot Chat in Agent mode.
  • Sign in to GitHub with Copilot access.
  • Have access to a Copilot Studio environment.
  • The skill handles setup for you.
  • Do not publish. This module ends with a validated Draft.

Easy mode

2

Prepare your Copilot

Brief your Copilot with one line

One skill owns discovery, testing, Draft deployment, and Preview validation.

Do this
  1. Open GitHub Copilot Chat in VS Code and select Agent mode.
  2. Paste this one line and send it. Copilot reads the skill itself; nothing to download.
Send this message
Go and read https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/skills/aibast-easy-mode/SKILL.md and run the Inventory Rebalancing workshop for me.
Expected result

Copilot says it has read the skill and is running the workshop. The skill owns the remaining setup and validation.

3

Prove the solution locally

Ask Easy Mode to build and test Inventory Rebalancing

This step proves the portable business logic before any Copilot Studio work begins. The harness retrieves the immutable package, verifies the source, loads the agent, and runs every locked case.

Send this message
Give me Inventory Rebalancing using Easy Mode and test it for me.
Expected result

Copilot reports a verified source and 10/10 locked local cases passed.

Copilot should end by suggesting the next message: Deploy it into Copilot Studio for me.

4

Create the reviewed Draft

Deploy the already-tested solution to Copilot Studio

The harness now uses the verified Microsoft Copilot Studio plugin to reuse or create the source-controlled Draft, synchronize the reviewed instructions and assets, validate the PAC project, and leave publication off.

Send this message
Deploy it into Copilot Studio for me.
Expected result
  • Draft: Inventory Manual Build
  • Model: Claude Opus 5
  • Knowledge files: 2
  • Skills: 10
  • Status: Draft; published: false

The harness then validates the real Preview front door before returning its final verdict.

5

Verify the real experience

Confirm the Draft in Copilot Studio Preview

The harness already runs these checks automatically. Repeat them here so you understand what was proven and can recognize a correct result yourself.

  1. Open the validated Draft.
  2. Select Preview.
  3. Choose New chat before each case.
  4. Paste the exact prompt.
  5. Compare the answer with the required and forbidden markers.
Expected result

Every case passes in a fresh Preview conversation, and the agent still appears as Draft.

IR-01 · Supply Chain Manager

Confirm the expected evidence

Which distribution centers are tight on space, and which SKU positions should my team review first?
Must include
Dallas Fulfillment CenterSKU-4406
Must not claim
I do not have access to the synthetic pilot data
IR-01 positive visual checkpoint

Visible positive anchors: Dallas Fulfillment Center; SKU-4406. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-02 · Inventory Manager

Confirm the expected evidence

Where do we have forecast-relative shortages or excess that deserve a rebalancing review?
Must include
SKU-4402SLOW-MOVING
Must not claim
I do not have access to the synthetic pilot data
IR-02 positive visual checkpoint

Visible positive anchors: SKU-4402; SLOW-MOVING. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-03 · Supply Chain Manager

Confirm the expected evidence

Show me the proposed warehouse moves, but do not move or reserve anything.
Must include
SKU-4401No inventory has been reserved
Must not claim
I do not have access to the synthetic pilot data
IR-03 positive visual checkpoint

Visible positive anchors: No inventory has been reserved; SKU-4401. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-04 · Procurement Manager

Confirm the expected evidence

Where is inventory exposure concentrated, and what trade-offs should I take to the planning meeting?
Must include
Total annual holding costsynthetic planning estimates
Must not claim
I do not have access to the synthetic pilot data
IR-04 positive visual checkpoint

Visible positive anchors: synthetic planning estimates; Total annual holding cost. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-05 · Supply Chain Manager

Confirm the expected evidence

We have $5M inventory, 30% slow-moving, warehouse 95% full. Need optimization plan.
Must include
$1.5M tied up$675KExcess safety stock
Must not claim
I do not have accessI cannot help
IR-05 positive visual checkpoint

Visible positive anchors: $1.5M tied up; $675K; Excess safety stock. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-06 · Supply Chain Manager

Confirm the expected evidence

Yes, show me a phased plan to recover cash from the slow-moving stock.
Must include
Phase 1: Immediate Actions$225K$1.2M in 90 days
Must not claim
I do not have accessI cannot help
IR-06 positive visual checkpoint

Visible positive anchors: Phase 1: Immediate Actions; $225K. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-07 · Inventory Manager

Confirm the expected evidence

What would that plan do to our warehouse space and operations?
Must include
New Utilization65%$2.8M
Must not claim
I do not have accessI cannot help
IR-07 positive visual checkpoint

Visible positive anchors: 65%; $2.8M. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-08 · Procurement Manager

Confirm the expected evidence

What are the savings and the ROI if we do this?
Must include
$640K$3.12M7,329%
Must not claim
I do not have accessI cannot help
IR-08 positive visual checkpoint

Visible positive anchors: $640K; $3.12M; 7,329%. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-09 · Supply Chain Manager

Confirm the expected evidence

Lay out the 90-day rollout with milestones I can share with stakeholders.
Must include
$307K$465KDay 45
Must not claim
I do not have accessI cannot help
IR-09 positive visual checkpoint

Visible positive anchors: $307K; $465K; Day 45. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

IR-10 · Inventory Manager

Confirm the expected evidence

How do we keep inventory optimized after the 90 days?
Must include
60 days no movementInventory turnsSuccess Metrics
Must not claim
I do not have accessI cannot help
IR-10 positive visual checkpoint

Visible positive anchors: Inventory turns; 60 days no movement; Success Metrics. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

6

Recognize completion

Know what “done” looks like

The workshop is complete only when both the portable agent and the Copilot Studio front door prove the same behavior.

Local proof10/10 locked cases passed
Preview proof10/10 locked cases passed
Draft identityInventory Manual Build
ModelClaude Opus 5
Inventory2 knowledge · 10 skills
Publication gateDraft · published false
Validated agent remains Draft

Positive visual checkpoint. Source: 1424×863 JPEG. Download original.

Final expected verdict

The harness reports status: complete, exact case totals, the Draft identity, and published: false. The module ends here; it does not offer publication.

Troubleshooting

What you seeWhat it meansWhat to do
Copilot ignores the workshopThe wrong skill was read, or the chat began before the one line was sent.Start a new Agent-mode chat and send the one line first.
Local validation is not 10/10The portable source, package, or locked behavior does not match.Stop. Do not deploy. Let the harness report the exact failed case and marker.
No active Copilot Studio environmentPAC has no selected environment.Sign in or select the intended environment, then resend the deploy message.
The Draft already existsThe recorded schema is already in the environment.The harness should clone and reconnect automatically. Treat an attendee choice prompt as a harness defect.
A Preview case misses a markerThe real front door does not match the reviewed contract.Keep the case failed. Inspect instructions and assets; do not retry until it happens to pass.
The agent is PublishedThe workshop crossed its safety boundary.Stop immediately. The module must end at Draft with published: false.
Facilitator evidence and portable download

These links support audit, troubleshooting, and offline delivery. They are not learner steps.