Create a blank Copilot Studio agent
Step 1 of 24
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 Regulatory Reporting 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 Regulatory Reporting Manual
Step 2 of 24
Action
Name Regulatory Reporting ManualRegulatory Reporting Manual
Expected resultThe page header shows the recorded manual build name: Regulatory Reporting Manual.
Enter the reviewed global instructions
Step 3 of 24
Action
Enter the reviewed global instructions# Regulatory Reporting 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 sign, certify, transmit, or claim completion of a regulator filing, and never predict an audit result. Authorized regulatory owners approve source evidence and every filing action. - 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 - Use **report status** for Regulatory Reporting Lead questions like: “Which filing is overdue and who owns it?” - Use **data validation** for Data Analyst questions like: “Which report data is incomplete or below quality threshold?” - Use **submission tracker** for Compliance Manager questions like: “Show filing state and confirm you did not transmit anything.” - Use **audit readiness** for Internal Auditor questions like: “What high-severity reporting evidence is still open?” - Use **emissions summary** for Environmental Manager questions like: “I need to prepare our quarterly EPA emissions report. Can you pull the data?” - Use **prepare submission** for Regulatory Affairs Director questions like: “Yes, generate the submission file and show me any compliance risks.” The file is a draft for authorized upload. ## 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. - `ENERGY_REGULATORY_REPORTING-01` uses skill `energy-regulatory-reporting-report-status`. - `ENERGY_REGULATORY_REPORTING-02` uses skill `energy-regulatory-reporting-data-validation`. - `ENERGY_REGULATORY_REPORTING-03` uses skill `energy-regulatory-reporting-submission-tracker`. - `ENERGY_REGULATORY_REPORTING-04` uses skill `energy-regulatory-reporting-audit-readiness`. - `ENERGY_REGULATORY_REPORTING-05` uses skill `energy-regulatory-reporting-emissions-summary`. - `ENERGY_REGULATORY_REPORTING-06` uses skill `energy-regulatory-reporting-prepare-submission`. 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 24
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 24
Action
Remove default web searchExpected resultThe captured inventory no longer lists the default web-search capability.
Add knowledge: energy-regulatory-reporting-rules-and-controls.md
Step 6 of 24
Action
Add knowledge: energy-regulatory-reporting-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: energy-regulatory-reporting-synthetic-records.md
Step 7 of 24
Action
Add knowledge: energy-regulatory-reporting-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_audit-readiness_04
Step 8 of 24
Action
Add skill: aibast_audit-readiness_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_data-validation_02
Step 9 of 24
Action
Add skill: aibast_data-validation_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_emissions-summary_05
Step 10 of 24
Action
Add skill: aibast_emissions-summary_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_prepare-submission_06
Step 11 of 24
Action
Add skill: aibast_prepare-submission_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_report-status_01
Step 12 of 24
Action
Add skill: aibast_report-status_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_submission-tracker_03
Step 13 of 24
Action
Add skill: aibast_submission-tracker_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.
Review model, skills, knowledge, and safety boundaries
Step 14 of 24
Action
Review model, skills, knowledge, and safety boundariesExpected resultThe screenshot visibly confirms Claude Opus 5, 6 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the skill list (6 skills)
Step 15 of 24
Action
Review the skill list (6 skills)Expected resultThe screenshot visibly confirms Claude Opus 5, 6 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the rest of the skill list
Step 16 of 24
Action
Review the rest of the skill listExpected resultThe screenshot visibly confirms Claude Opus 5, 6 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Open a fresh Preview conversation
Step 17 of 24
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 ENERGY_REGULATORY_REPORTING-01: Regulatory Reporting Lead
Step 18 of 24
Action
Pass ENERGY_REGULATORY_REPORTING-01: Regulatory Reporting LeadWhich filing is overdue and who owns it?
Expected resultThe captured Preview evidence records ENERGY_REGULATORY_REPORTING-01 with the recorded identifiers PHMSA Annual Pipeline Safety Report, OVERDUE, Pipeline Operations; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running ENERGY_REGULATORY_REPORTING-01. A previous response must not influence the evidence.
Pass ENERGY_REGULATORY_REPORTING-02: Data Analyst
Step 19 of 24
Action
Pass ENERGY_REGULATORY_REPORTING-02: Data AnalystWhich report data is incomplete or below quality threshold?
Expected resultThe captured Preview evidence records ENERGY_REGULATORY_REPORTING-02 with the recorded identifiers Data collection incomplete, Data quality score below threshold, authorized report owner; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running ENERGY_REGULATORY_REPORTING-02. A previous response must not influence the evidence.
Pass ENERGY_REGULATORY_REPORTING-03: Compliance Manager
Step 20 of 24
Action
Pass ENERGY_REGULATORY_REPORTING-03: Compliance ManagerShow filing state and confirm you did not transmit anything.
Expected resultThe captured Preview evidence records ENERGY_REGULATORY_REPORTING-03 with the recorded identifiers PHMSA Annual Pipeline Safety Report, OVERDUE, No regulator filing; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running ENERGY_REGULATORY_REPORTING-03. A previous response must not influence the evidence.
Pass ENERGY_REGULATORY_REPORTING-04: Internal Auditor
Step 21 of 24
Action
Pass ENERGY_REGULATORY_REPORTING-04: Internal AuditorWhat high-severity reporting evidence is still open?
Expected resultThe captured Preview evidence records ENERGY_REGULATORY_REPORTING-04 with the recorded identifiers Pipeline mileage discrepancy, HIGH, cannot predict an audit outcome; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running ENERGY_REGULATORY_REPORTING-04. A previous response must not influence the evidence.
Pass ENERGY_REGULATORY_REPORTING-05: Environmental Manager
Step 22 of 24
Action
Pass ENERGY_REGULATORY_REPORTING-05: Environmental ManagerI need to prepare our quarterly EPA emissions report. Can you pull the data?
Expected resultThe captured Preview evidence records ENERGY_REGULATORY_REPORTING-05 with the recorded identifiers 14 facilities, 8.24M tons, down 7.3%; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running ENERGY_REGULATORY_REPORTING-05. A previous response must not influence the evidence.
Pass ENERGY_REGULATORY_REPORTING-06: Regulatory Affairs Director
Step 23 of 24
Action
Pass ENERGY_REGULATORY_REPORTING-06: Regulatory Affairs DirectorGenerate the EPA submission file for the quarter and show me any compliance risks.
Expected resultThe captured Preview evidence records ENERGY_REGULATORY_REPORTING-06 with the recorded identifiers EPA_Q1_Emissions_Report.xml, 6 sections incomplete, No regulator filing; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running ENERGY_REGULATORY_REPORTING-06. A previous response must not influence the evidence.
Confirm Draft and stop before publish
Step 24 of 24
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.