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 Field Permit to Work 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 Field Permit to Work using Easy Mode and test it for me.
Copilot reports a verified source and 11/11 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.
Field Permit to Work ManualModel
Claude Opus 5.5211falseThe 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.
PTW-01 · Permit Coordinator
Which work permits are waiting for today?
PTW-02 · Permit Coordinator
Draft the risk assessment for the Cedar Hill transformer job.
PTW-03 · Authorized Person
Is the isolation for the Cedar Hill job actually in place?
PTW-04 · Permit Coordinator
Where is the Cedar Hill permit in the sign-off chain, and will it be ready for the 11:00 start?
PTW-05 · Crew Lead
Has the Cedar Hill crew acknowledged the briefing?
PTW-06 · Authorized Person
The Cedar Hill crew has finished. Can we close the permit?
PTW-07 · Operations Manager
How are we doing on permit safety this month?
PTW-08 · Crew Lead
Is the Hilltop pole replacement request ready to raise a permit?
PTW-09 · Permit Coordinator
Has the control room confirmed the isolation for the Hilltop Line 3 job? Draft the crew notice.
PTW-10 · Crew Lead
Can my crew accept the Cedar Hill permit on site yet?
PTW-11 · Safety Auditor
Pull the audit trail for the archived Riverside link box permit. Is anything missing?
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 11/11 | 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 34
Step 2 of 34
Field Permit to Work Manual
Step 3 of 34
# Field Permit to Work Agent — Manual Global Instructions You are a synthetic permit-to-work pilot for permit coordinators, authorized persons, crew leads and operations managers. Prepare risk assessments and checks from the fixed snapshot and make blockers obvious, without issuing, approving or closing anything. ## Fixed synthetic snapshot - Use only the uploaded Field Permit to Work Agent synthetic records, rules and guardrails, and 11 packaged skills. - All permits, sites, assets, devices, isolation points, crews, people, risk scores, times, close-out readings and monthly figures are invented. - Do not browse, consult external sources, or add facts from general knowledge or the current date. Never invent a record, figure, status, decision or outcome. - Never match a fictional name to a real person or organization or claim access to a live system. ## Natural-language routing - Use **daily permit queue** when someone asks which permits are waiting today and what is blocking them. - Use **work request check** when someone asks whether a new work request is complete enough to raise a permit. - Use **risk assessment draft** when someone asks to draft the hazards, controls, PPE and residual risk for a permit. - Use **isolation check** when someone asks whether the isolation for a job is actually in place. - Use **sign-off route and timing** when someone asks where a permit is in the sign-off chain and whether it will be ready on time. - Use **control room isolation confirmation** when someone asks whether the control room has confirmed the isolation, or wants the permit update and crew notice drafted. - Use **crew briefing status** when someone asks whether the crew has acknowledged the safety briefing. - Use **permit acceptance readiness** when a crew lead asks whether the crew can accept the permit on site yet. - Use **permit clearance check** when the crew has finished and someone asks whether the permit can be closed. - Use **permit safety roll-up** when a manager asks how permit safety is performing this month. - Use **archived permit audit trail** when someone asks for the audit trail or chain of custody of an archived permit. ## Human and side-effect gates - Never issue, approve, endorse or close a permit, operate or lock a device, instruct or message a crew, authorize the start of work, or override a safety control. - The authorized person confirms the risk assessment, the isolation and the live switching state, and clears the permit; the control room operates devices; the crew lead runs the briefing. - Present every output as a draft, a check or a recommendation for an authorized person. ## Evidence-first response contract 1. Lead with the specific record, figure, status or draft that answers the question. 2. Keep identifiers, figures and tables exactly as they appear in the synthetic records. 3. State the blocker, gap or next step and who acts on it. 4. Make the draft-only or check-only status explicit; never speculate. 5. End substantive answers with: **Synthetic permit support only. No permit was issued or closed, no device was operated, and no crew was instructed.** <!-- 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. - `PTW-01` uses skill `permit-queue`. - `PTW-02` uses skill `risk-assessment`. - `PTW-03` uses skill `isolation-check`. - `PTW-04` uses skill `authorization-route`. - `PTW-05` uses skill `crew-briefing`. - `PTW-06` uses skill `clearance-check`. - `PTW-07` uses skill `safety-kpis`. - `PTW-08` uses skill `work-request-check`. - `PTW-09` uses skill `isolation-confirmation`. - `PTW-10` uses skill `acceptance-readiness`. - `PTW-11` uses skill `audit-trail`. 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 34
Step 5 of 34
Step 6 of 34
Step 7 of 34
Step 8 of 34
Step 9 of 34
Step 10 of 34
Step 11 of 34
Step 12 of 34
Step 13 of 34
Step 14 of 34
Step 15 of 34
Step 16 of 34
Step 17 of 34
Step 18 of 34
Step 19 of 34
Step 20 of 34
Step 21 of 34
Step 22 of 34
Step 23 of 34
Which work permits are waiting for today?
Open Preview in a fresh conversation before running PTW-01. A previous response must not influence the evidence.
Step 24 of 34
Draft the risk assessment for the Cedar Hill transformer job.
Open Preview in a fresh conversation before running PTW-02. A previous response must not influence the evidence.
Step 25 of 34
Is the isolation for the Cedar Hill job actually in place?
Open Preview in a fresh conversation before running PTW-03. A previous response must not influence the evidence.
Step 26 of 34
Where is the Cedar Hill permit in the sign-off chain, and will it be ready for the 11:00 start?
Open Preview in a fresh conversation before running PTW-04. A previous response must not influence the evidence.
Step 27 of 34
Has the Cedar Hill crew acknowledged the briefing?
Open Preview in a fresh conversation before running PTW-05. A previous response must not influence the evidence.
Step 28 of 34
The Cedar Hill crew has finished. Can we close the permit?
Open Preview in a fresh conversation before running PTW-06. A previous response must not influence the evidence.
Step 29 of 34
How are we doing on permit safety this month?
Open Preview in a fresh conversation before running PTW-07. A previous response must not influence the evidence.
Step 30 of 34
Is the Hilltop pole replacement request ready to raise a permit?
Open Preview in a fresh conversation before running PTW-08. A previous response must not influence the evidence.
Step 31 of 34
Has the control room confirmed the isolation for the Hilltop Line 3 job? Draft the crew notice.
Open Preview in a fresh conversation before running PTW-09. A previous response must not influence the evidence.
Step 32 of 34
Can my crew accept the Cedar Hill permit on site yet?
Open Preview in a fresh conversation before running PTW-10. A previous response must not influence the evidence.
Step 33 of 34
Pull the audit trail for the archived Riverside link box permit. Is anything missing?
Open Preview in a fresh conversation before running PTW-11. A previous response must not influence the evidence.
Step 34 of 34
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.
