Evidence-grounded customer journey
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.
Self-paced local achievements
0 of 0 Easy checkpoints complete
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.
Workshop setup
Start in GitHub Copilot Chat. No Frontier desktop app is required; the Easy Mode skill handles any additional setup.
GitHub Copilot Chat is open in VS Code, signed in, and set to Agent mode.
Prepare your Copilot
One skill owns discovery, testing, Draft deployment, and Preview validation.
Go and read https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/skills/aibast-easy-mode/SKILL.md and run the Resource Utilization workshop for me.
Copilot says it has read the skill and is running the workshop. The skill owns the remaining setup and validation.
Prove the solution locally
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.
Give me Resource Utilization using Easy Mode and test it for me.
Copilot reports a verified source and 8/8 locked local cases passed.
Copilot should end by suggesting the next message: Deploy it into Copilot Studio for me.
Create the reviewed Draft
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.
Deploy it into Copilot Studio for me.
Resource Utilization ManualClaude Opus 528falseThe harness then validates the real Preview front door before returning its final verdict.
Verify the real experience
The harness already runs these checks automatically. Repeat them here so you understand what was proven and can recognize a correct result yourself.
Every case passes in a fresh Preview conversation, and the agent still appears as Draft.
RU-01 · Operations Leader
Where are we under target today, and which parts of the workforce are sitting available?
RU-02 · Resource Manager
What capacity is coming free, and how does it line up with the opportunities expected over the next quarter?
RU-03 · Finance Director
Show me who is on the bench, the skills we are carrying, and the cost exposure we need to address.
RU-04 · Resource Manager
Which available consultants fit the strongest pipeline needs, and who still needs another path?
RU-05 · Operations Leader
Give me an upskilling and internal-innovation plan for the people we cannot place directly, including the business case.
RU-06 · Operations Leader
Our board wants utilization up to 85% by next quarter. We have 200 consultants currently at 72% billable. I need an optimization plan that shows how we get there without compromising quality.
RU-07 · Finance Director
What is the complete financial impact of this plan by month, quarter, and year?
RU-08 · Operations Leader
Create a tracking dashboard and summarize what we accomplished.
Recognize completion
The workshop is complete only when both the portable agent and the Copilot Studio front door prove the same behavior.
The harness reports status: complete, exact case totals, the Draft identity, and published: false. The module ends here; it does not offer publication.
| What you see | What it means | What to do |
|---|---|---|
| Copilot ignores the workshop | The 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 8/8 | The 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 environment | PAC has no selected environment. | Sign in or select the intended environment, then resend the deploy message. |
| The Draft already exists | The 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 marker | The 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 Published | The workshop crossed its safety boundary. | Stop immediately. The module must end at Draft with published: false. |
These links support audit, troubleshooting, and offline delivery. They are not learner steps.
Manual mode · see how it was built
Optional. Easy mode already did all of this for you from one skill file. This path replays every action the AI took, one real browser frame per step, so you can understand the agent before you adapt it. No PAC CLI, YAML import, or plugin architect; stop at Draft.
Manual-mode progress is saved on this device and contributes to the same achievement profile.
Step 1 of 28
Step 2 of 28
Resource Utilization Manual
Step 3 of 28
# Resource Utilization Agent — Global Instructions ## Mission Help operations, resource, and finance leaders review the packaged synthetic utilization, capacity, bench, pipeline-match, and workforce-development scenarios while keeping staffing and investment decisions under human control. ## Grounding - Use only `aibast_resource-synthetic-roster.md` and `aibast_resource-pipeline-and-workforce-rules.md`. - Treat the roster, project endings, opportunity probabilities, costs, and pathway economics as one frozen synthetic planning snapshot. - Do not browse, search the web, query HR or PSA systems, or invent people, skills, availability, assignments, demand, probabilities, rates, costs, or benefits. - Do not describe pipeline, utilization, revenue, or payback scenarios as live, committed, forecast, or guaranteed. - Count each consultant once in any projected utilization view. ## Routing - Current utilization, targets, and availability: use the utilization dashboard. - Upcoming project endings and weighted demand: use the capacity forecast. - Bench people, skills, and carrying-cost scenarios: use bench analysis. - Skill-and-level matches and unmatched resources: use staffing recommendations. - Upskilling and internal-innovation options: use the workforce plan. - The board goal (utilization to 85%, 200 consultants at 72%, optimization plan): use the optimization plan first (the demo default). - Where expensive capacity sits idle: bench analysis. Confirmed project pipeline: staffing recommendations. The 5 cloud architects / skill mismatch: workforce plan (shadow model). - Complete financial impact: financial impact. Tracking dashboard and session summary: executive summary (a draft specification; nothing is deployed). ## Workforce and authorization gates - Never assign, reserve, deploy, reallocate, hire, terminate, evaluate, or contact a person. - Never change employment, project, utilization, training, or HR records. - Never approve training, internal work, client staffing, revenue, or financial benefits. - Preserve resource-manager, people-leader, finance, business-owner, and leadership approval for every staffing or capability-building decision. ## Evidence-first response contract 1. Lead with the utilization, capacity, bench, match, or pathway finding. 2. Cite exact packaged consultant IDs, skills, levels, dates, probabilities, and scenario values. 3. Separate direct matches, unmatched needs, uncertainty, and approval dependencies. 4. State the next authorized staffing or workforce-planning review. 5. End with: `Synthetic workforce planning evidence; no assignment, employment action, training approval, or revenue commitment occurred.` <!-- locked-preview-anchors:start --> ## Skill routing map Route from the user's natural-language intent to the correct skill below. Do not narrate internal retrieval, tool selection, restrictions, or implementation mechanics; present only the user-facing result. - `RU-01` uses skill `workforce-utilization-dashboard`. - `RU-02` uses skill `workforce-capacity-forecast`. - `RU-03` uses skill `professional-services-bench-analysis`. - `RU-04` uses skill `pipeline-staffing-recommendation`. - `RU-05` uses skill `strategic-workforce-plan`. - `RU-06` uses skill `optimization-plan`. - `RU-07` uses skill `financial-impact`. - `RU-08` uses skill `executive-summary`. These skill names above are the ONLY valid skill identifiers. Never invent, guess, or reference any other skill name. If the correct skill or its knowledge cannot be loaded after one retry in the same turn, say so honestly and stop. Do not answer using values you already know from these instructions or from general knowledge -- a response with no real citation is not acceptable output. <!-- locked-preview-anchors:end -->
Step 4 of 28
Step 5 of 28
Step 6 of 28
Step 7 of 28
Step 8 of 28
Step 9 of 28
Step 10 of 28
Step 11 of 28
Step 12 of 28
Step 13 of 28
Step 14 of 28
Step 15 of 28
Step 16 of 28
Step 17 of 28
Step 18 of 28
Step 19 of 28
Step 20 of 28
Where are we under target today, and which parts of the workforce are sitting available?
Open Preview in a fresh conversation before running RU-01. A previous response must not influence the evidence.
Step 21 of 28
What capacity is coming free, and how does it line up with the opportunities expected over the next quarter?
Open Preview in a fresh conversation before running RU-02. A previous response must not influence the evidence.
Step 22 of 28
Show me who is on the bench, the skills we are carrying, and the cost exposure we need to address.
Open Preview in a fresh conversation before running RU-03. A previous response must not influence the evidence.
Step 23 of 28
Which available consultants fit the strongest pipeline needs, and who still needs another path?
Open Preview in a fresh conversation before running RU-04. A previous response must not influence the evidence.
Step 24 of 28
Give me an upskilling and internal-innovation plan for the people we cannot place directly, including the business case.
Open Preview in a fresh conversation before running RU-05. A previous response must not influence the evidence.
Step 25 of 28
Our board wants utilization up to 85% by next quarter. We have 200 consultants currently at 72% billable. I need an optimization plan that shows how we get there without compromising quality.
Open Preview in a fresh conversation before running RU-06. A previous response must not influence the evidence.
Step 26 of 28
What is the complete financial impact of this plan by month, quarter, and year?
Open Preview in a fresh conversation before running RU-07. A previous response must not influence the evidence.
Step 27 of 28
Create a tracking dashboard and summarize what we accomplished.
Open Preview in a fresh conversation before running RU-08. A previous response must not influence the evidence.
Step 28 of 28
Stop. Do not invent, recreate, or substitute an image. Capture the real frame, update the browserfilm manifest, and regenerate without --allow-pending.
Wait for ingestion to finish before Preview. A partial answer is not evidence.
Use the linked raw SKILL.md. Fix the reviewed source deliberately; do not silently skip the action.
Record the substitution and stop the parity claim until Easy and Manual use the same reviewed model.
Mark the recorded case failed, inspect instructions and inventory, then replay the exact prompt in a fresh conversation.
No. Keep this manual duplicate in Draft unless publication is separately approved. Do not choose Publish as part of this tutorial.
