Create a blank Copilot Studio agent
Step 1 of 26
Action
Create a blank Copilot Studio agentExpected resultA blank Copilot Studio agent is visible in the captured Draft workspace.
Manual mode · literal browser construction
Build Field Service Dispatch Agent manually.
No PAC CLI, YAML import, or plugin architect. Follow each action and its evidence boundary, compare only the reviewed references, and stop at Draft.
Synthetic disclosure: this is qualitative workflow evidence using packaged synthetic inputs. It is not a customer KPI or a live-system result.
Progress will remain available on this page, but it will not persist after you leave.
Found something inaccurate? Use Report an issue on that step. It opens a prefilled GitHub issue for review and does not submit automatically.
Build and verify
Name Field Service Dispatch Manual
Step 2 of 26
Action
Name Field Service Dispatch ManualField Service Dispatch Manual
Expected resultThe page header shows the recorded manual build name: Field Service Dispatch Manual.
Enter the reviewed global instructions
Step 3 of 26
Action
Enter the reviewed global instructions# Field Service Dispatch Agent — Manual Global Instructions Use only the uploaded synthetic knowledge and operation skills. Treat every organization, person, identifier, date, measurement, status, score, cost, and recommendation as fictional pilot evidence. ## Boundaries - Never assign, notify, reroute, or dispatch a crew; change a job; stage inventory; contact a customer; or authorize field action. A human dispatcher applies safety, labor, SLA, and emergency procedures. - Do not browse for replacement facts or invent missing records. - Keep public value statements qualitative; numbers belong only to the synthetic evidence. - If a requested identifier is absent, say so rather than substituting another record. - A model response is never evidence that an external action occurred. ## Routing - The demo is a metro utility: tomorrow's 12 jobs across crews A-1 (Marcus Chen), B-2, C-3 and D-4, standby crews E-7 and F-8, and the downtown outage (1,247 customers, 2 hospitals, Substation 7B). Short "yes, ..." follow-ups continue the workflow; call the agent first. - Use **dispatch dashboard** for Field Operations Manager questions like: “What does tomorrow's job list look like by crew, and which crews are on standby?” - Use **route optimization** for Service Director questions like: “I need help optimizing our field technician schedules for tomorrow. We have 15 service calls.” - Use **technician assignment** for Dispatch Coordinator questions like: “Yes, show me Crew A-1's detailed route” - Use **emergency response** for Emergency Duty Manager questions like: “URGENT: Major power outage downtown - 1,200 customers affected. Dispatch emergency crews now!” - Use **incident status** for Control Room Operator questions like: “Yes, give me live updates and customer impact” - Use **post incident review** for Reliability Engineer questions like: “The outage is resolved. Show me the post-incident review and how we prevent the next one.” - Use **work orders report** for Operations Analyst questions like: “Yes, create the work orders and show me the monthly operations report” ## Response contract 1. Lead with the specific synthetic record and operation result. 2. Explain the source evidence and material uncertainty. 3. Separate analysis or drafting from any future write action. 4. Name the authorized reviewer and approved production connection needed next. 5. End with the no-write boundary relevant to the operation. <!-- 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. - `FIELD_SERVICE_DISPATCH-01` uses skill `field-service-dispatch-dispatch-dashboard`. - `FIELD_SERVICE_DISPATCH-02` uses skill `field-service-dispatch-route-optimization`. - `FIELD_SERVICE_DISPATCH-03` uses skill `field-service-dispatch-technician-assignment`. - `FIELD_SERVICE_DISPATCH-04` uses skill `field-service-dispatch-emergency-response`. - `FIELD_SERVICE_DISPATCH-05` uses skill `field-service-dispatch-incident-status`. - `FIELD_SERVICE_DISPATCH-06` uses skill `field-service-dispatch-post-incident-review`. - `FIELD_SERVICE_DISPATCH-07` uses skill `field-service-dispatch-work-orders-report`. 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 -->
Expected resultThe reviewed manual/GLOBAL-INSTRUCTIONS.md policy is visible or saved without unrecorded edits.
Save the instruction policy
Step 4 of 26
Action
Save the instruction policyExpected resultThe reviewed manual/GLOBAL-INSTRUCTIONS.md policy is visible or saved without unrecorded edits.
Remove default web search
Step 5 of 26
Action
Remove default web searchExpected resultThe captured inventory no longer lists the default web-search capability.
Add knowledge: field-service-dispatch-rules-and-controls.md
Step 6 of 26
Action
Add knowledge: field-service-dispatch-rules-and-controls.mdExpected resultThe exact knowledge file linked for this step is attached under its complete filename. Wait for processing to finish before continuing. This step does not require the final inventory or prove the other uploads.
Add knowledge: field-service-dispatch-synthetic-records.md
Step 7 of 26
Action
Add knowledge: field-service-dispatch-synthetic-records.mdExpected resultThe exact knowledge file linked for this step is attached under its complete filename. Wait for processing to finish before continuing. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_dispatch-dashboard_01
Step 8 of 26
Action
Add skill: aibast_dispatch-dashboard_01Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_emergency-response_04
Step 9 of 26
Action
Add skill: aibast_emergency-response_04Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_incident-status_05
Step 10 of 26
Action
Add skill: aibast_incident-status_05Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_post-incident-review_06
Step 11 of 26
Action
Add skill: aibast_post-incident-review_06Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_route-optimization_02
Step 12 of 26
Action
Add skill: aibast_route-optimization_02Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_technician-assignment_03
Step 13 of 26
Action
Add skill: aibast_technician-assignment_03Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Add skill: aibast_work-orders-report_07
Step 14 of 26
Action
Add skill: aibast_work-orders-report_07Expected resultThe linked SKILL.md appears with its frontmatter name and description. Open it and compare the complete instructions with the source file. This step does not require the final inventory or prove the other uploads.
Review model, skills, knowledge, and safety boundaries
Step 15 of 26
Action
Review model, skills, knowledge, and safety boundariesExpected resultThe screenshot visibly confirms Claude Opus 5, 7 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the skill list (7 skills)
Step 16 of 26
Action
Review the skill list (7 skills)Expected resultThe screenshot visibly confirms Claude Opus 5, 7 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the rest of the skill list
Step 17 of 26
Action
Review the rest of the skill listExpected resultThe screenshot visibly confirms Claude Opus 5, 7 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Open a fresh Preview conversation
Step 18 of 26
Action
Open a fresh Preview conversationExpected resultA fresh Preview surface or its recorded qualitative result is visible; only the evidence file defines a pass.
Pass FIELD_SERVICE_DISPATCH-01: Field Operations Manager
Step 19 of 26
Action
Pass FIELD_SERVICE_DISPATCH-01: Field Operations ManagerWhat does tomorrow's job list look like by crew, and which crews are on standby?
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-01 with the recorded identifiers J-101, Marcus Chen, No job; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-01. A previous response must not influence the evidence.
Pass FIELD_SERVICE_DISPATCH-02: Service Director
Step 20 of 26
Action
Pass FIELD_SERVICE_DISPATCH-02: Service DirectorI need help optimizing our field technician schedules for tomorrow. We have 15 service calls.
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-02 with the recorded identifiers 34%, 187 miles, $1,840/day; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-02. A previous response must not influence the evidence.
Pass FIELD_SERVICE_DISPATCH-03: Dispatch Coordinator
Step 21 of 26
Action
Pass FIELD_SERVICE_DISPATCH-03: Dispatch CoordinatorYes, show me Crew A-1's detailed route
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-03 with the recorded identifiers Marcus Chen, Truck, Underground cable certified; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-03. A previous response must not influence the evidence.
Pass FIELD_SERVICE_DISPATCH-04: Emergency Duty Manager
Step 22 of 26
Action
Pass FIELD_SERVICE_DISPATCH-04: Emergency Duty ManagerURGENT: Major power outage downtown - 1,200 customers affected. Dispatch emergency crews now!
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-04 with the recorded identifiers 1,247, $26,140/hour, No crew was dispatched; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-04. A previous response must not influence the evidence.
Pass FIELD_SERVICE_DISPATCH-05: Control Room Operator
Step 23 of 26
Action
Pass FIELD_SERVICE_DISPATCH-05: Control Room OperatorYes, give me live updates and customer impact
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-05 with the recorded identifiers Phase B insulator, $12,400, 93 min; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-05. A previous response must not influence the evidence.
Pass FIELD_SERVICE_DISPATCH-06: Reliability Engineer
Step 24 of 26
Action
Pass FIELD_SERVICE_DISPATCH-06: Reliability EngineerThe outage is resolved. Show me the post-incident review and how we prevent the next one.
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-06 with the recorded identifiers 87 Minutes, 785% ROI, Substation 7B; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-06. A previous response must not influence the evidence.
Pass FIELD_SERVICE_DISPATCH-07: Operations Analyst
Step 25 of 26
Action
Pass FIELD_SERVICE_DISPATCH-07: Operations AnalystYes, create the work orders and show me the monthly operations report
Expected resultThe captured Preview evidence records FIELD_SERVICE_DISPATCH-07 with the recorded identifiers WO-2847, $29,260/month, none was created; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running FIELD_SERVICE_DISPATCH-07. A previous response must not influence the evidence.
Confirm Draft and stop before publish
Step 26 of 26
Action
Confirm Draft and stop before publishExpected resultThe agent remains Draft and no Publish action is taken.
Troubleshooting
A screenshot or browserfilm frame is missing
Do not invent, recreate, or substitute an image. Keep the step open until its actual evidence is captured and reviewed. Remove --allow-pending only after all workshop evidence gates are met.
A knowledge file is still processing
Wait for ingestion to finish before Preview. A partial answer is not evidence.
A skill upload fails
Use the linked raw SKILL.md. Fix the reviewed source deliberately; do not silently skip the action.
The model differs from Easy mode
Record the substitution and stop the parity claim until Easy and Manual use the same reviewed model.
The Preview answer misses an identifier
Mark the recorded case failed, inspect instructions and inventory, then replay the exact prompt in a fresh conversation.
Should I publish?
No. Keep the same owned manual agent in Draft. Do not choose Publish as part of this tutorial.