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 Personalized Marketing 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 Personalized Marketing Manual
Step 2 of 26
Action
Name Personalized Marketing ManualPersonalized Marketing Manual
Expected resultThe page header shows the recorded manual build name: Personalized Marketing Manual.
Enter the reviewed global instructions
Step 3 of 26
Action
Enter the reviewed global instructions# Personalized Marketing Agent — Manual Global Instructions Use only the uploaded synthetic aggregate records, safety rules, and operation skills. Never infer sensitive traits or imply access to a live customer system. Produce audience analysis, campaign concepts, content drafts, and measurement scenarios only. Do not contact anyone, send or schedule a message, create or apply an offer, launch a campaign, issue a reward, or complete a purchase. Lead with evidence, distinguish synthetic facts from recommendations, name the human approval gate, and state that no external side effect occurred. The fixed scenario is the holiday email promotion: 240,000 customers in five segments ($8.4M addressable), a five-wave plan led by VIP Shoppers ($8.12M expected from a $47K investment), three VIP A/B variants, a draft VIP launch tomorrow 8:00 AM PST with a 72-hour workflow, and VIP revenue scenarios of $1.42M / $1.78M / $2.11M. Route segment analysis to `privacy-safe-customer-segmentation`, campaign recommendations to `review-only-campaign-design`, VIP creative and A/B variants to `consent-aware-content-personalization`, scheduling and the automation workflow to `campaign-workflow`, the revenue projection to `revenue-projection`, the executive brief to `executive-brief`, and past test results to `synthetic-marketing-performance-analysis`. Schedules and briefs are drafts for approval. <!-- 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. - `PM-01` uses skill `privacy-safe-customer-segmentation`. - `PM-02` uses skill `review-only-campaign-design`. - `PM-03` uses skill `consent-aware-content-personalization`. - `PM-04` uses skill `synthetic-marketing-performance-analysis`. - `PM-05` uses skill `campaign-workflow`. - `PM-06` uses skill `revenue-projection`. - `PM-07` uses skill `executive-brief`. 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: aibast_personalized-marketing-rules-and-safety.md
Step 6 of 26
Action
Add knowledge: aibast_personalized-marketing-rules-and-safety.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: aibast_personalized-marketing-synthetic-records.md
Step 7 of 26
Action
Add knowledge: aibast_personalized-marketing-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_campaign-design_02
Step 8 of 26
Action
Add skill: aibast_campaign-design_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_campaign-workflow_05
Step 9 of 26
Action
Add skill: aibast_campaign-workflow_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_content-personalization_03
Step 10 of 26
Action
Add skill: aibast_content-personalization_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_customer-segmentation_01
Step 11 of 26
Action
Add skill: aibast_customer-segmentation_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_executive-brief_07
Step 12 of 26
Action
Add skill: aibast_executive-brief_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.
Add skill: aibast_performance-analysis_04
Step 13 of 26
Action
Add skill: aibast_performance-analysis_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_revenue-projection_06
Step 14 of 26
Action
Add skill: aibast_revenue-projection_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.
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 PM-01: Marketing Director
Step 19 of 26
Action
Pass PM-01: Marketing DirectorAs Marketing Director, summarize the aggregate customer groups without demographic traits and identify portfolio review priorities.
Expected resultThe captured Preview evidence records PM-01 with the recorded identifiers Prepared for:** Marketing Director, Total Addressable Customers, no audience is profiled with sensitive attributes; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-01. A previous response must not influence the evidence.
Pass PM-02: Campaign Manager
Step 20 of 26
Action
Pass PM-02: Campaign ManagerAs Campaign Manager, show me the personalized multi-wave campaign recommendations for the holiday promotion and the approval gates.
Expected resultThe captured Preview evidence records PM-02 with the recorded identifiers Prepared for:** Campaign Manager, Draft Campaign Design Portfolio, Total Campaign Projection; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-02. A previous response must not influence the evidence.
Pass PM-03: Campaign Manager
Step 21 of 26
Action
Pass PM-03: Campaign ManagerAs Campaign Manager, generate the VIP campaign with personalized content and A/B test variants.
Expected resultThe captured Preview evidence records PM-03 with the recorded identifiers Draft Content Personalization Matrix, VIP Shoppers, A/B Test Setup; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-03. A previous response must not influence the evidence.
Pass PM-04: Marketing Director
Step 22 of 26
Action
Pass PM-04: Marketing DirectorAs Marketing Director, compare the synthetic tests and call out measurement limitations before any decision.
Expected resultThe captured Preview evidence records PM-04 with the recorded identifiers Marketing Performance Analysis, A/B Test Results, Synthetic aggregate planning data; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-04. A previous response must not influence the evidence.
Pass PM-05: Campaign Manager
Step 23 of 26
Action
Pass PM-05: Campaign ManagerAs Campaign Manager, plan the VIP wave launch for tomorrow morning and show me the automation workflow for approval.
Expected resultThe captured Preview evidence records PM-05 with the recorded identifiers Draft VIP Launch Schedule, Hour 48, Nothing is scheduled or sent; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-05. A previous response must not influence the evidence.
Pass PM-06: Marketing Director
Step 24 of 26
Action
Pass PM-06: Marketing DirectorAs Marketing Director, break down the revenue projection scenarios for the VIP wave.
Expected resultThe captured Preview evidence records PM-06 with the recorded identifiers VIP Revenue Projection Model, Conservative (Baseline), ROI Range; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-06. A previous response must not influence the evidence.
Pass PM-07: Marketing Director
Step 25 of 26
Action
Pass PM-07: Marketing DirectorAs Marketing Director, create the executive brief summarizing our holiday campaign strategy.
Expected resultThe captured Preview evidence records PM-07 with the recorded identifiers Executive Campaign Brief, Program Economics, has not been sent; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running PM-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.