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 Cart Abandonment Recovery 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 Cart Abandonment Manual
Step 2 of 26
Action
Name Cart Abandonment ManualCart Abandonment Manual
Expected resultThe page header shows the recorded manual build name: Cart Abandonment Manual.
Enter the reviewed global instructions
Step 3 of 26
Action
Enter the reviewed global instructions# Cart Abandonment Recovery Agent — Manual Global Instructions Use only the uploaded anonymous synthetic carts, aggregate metrics, safety rules, and operation skills. Do not identify or contact a shopper. Produce analysis, campaign drafts, incentive scenarios, and measurement summaries only. Never send or schedule outreach, create or apply an offer, retarget a person, change a cart, reserve stock, or complete a purchase. State assumptions, consent and approval gates, and that no external side effect occurred. A request to launch campaigns returns the draft recovery program ready for approval; it is launched from the marketing platform by an authorized person, never by this agent. <!-- 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. - `CAR-01` uses skill `anonymous-cart-abandonment-analysis`. - `CAR-02` uses skill `consent-aware-recovery-campaign-draft`. - `CAR-03` uses skill `margin-aware-incentive-scenarios`. - `CAR-04` uses skill `synthetic-recovery-conversion-tracking`. - `CAR-05` uses skill `recovery-strategies`. - `CAR-06` uses skill `recovery-forecast`. - `CAR-07` uses skill `optimization-recommendations`. 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_cart-recovery-rules-and-safety.md
Step 6 of 26
Action
Add knowledge: aibast_cart-recovery-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_cart-recovery-synthetic-records.md
Step 7 of 26
Action
Add knowledge: aibast_cart-recovery-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_abandonment-analysis_01
Step 8 of 26
Action
Add skill: aibast_abandonment-analysis_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_conversion-tracking_04
Step 9 of 26
Action
Add skill: aibast_conversion-tracking_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_incentive-optimization_03
Step 10 of 26
Action
Add skill: aibast_incentive-optimization_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_optimization-recommendations_07
Step 11 of 26
Action
Add skill: aibast_optimization-recommendations_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_recovery-campaign_02
Step 12 of 26
Action
Add skill: aibast_recovery-campaign_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_recovery-forecast_06
Step 13 of 26
Action
Add skill: aibast_recovery-forecast_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_recovery-strategies_05
Step 14 of 26
Action
Add skill: aibast_recovery-strategies_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.
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 CAR-01: Marketing Manager
Step 19 of 26
Action
Pass CAR-01: Marketing ManagerAs Marketing Manager, show where the anonymous synthetic cart journey is breaking down and what needs review.
Expected resultThe captured Preview evidence records CAR-01 with the recorded identifiers Prepared for:** Marketing Manager, Synthetic Cart Abandonment Analysis, no shopper is contacted; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-01. A previous response must not influence the evidence.
Pass CAR-02: Digital Marketing Lead
Step 20 of 26
Action
Pass CAR-02: Digital Marketing LeadAs Digital Marketing Lead, outline a consent-aware draft sequence without sending or scheduling anything.
Expected resultThe captured Preview evidence records CAR-02 with the recorded identifiers Prepared for:** Digital Marketing Lead, Draft Recovery Campaign Dashboard, not deployed; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-02. A previous response must not influence the evidence.
Pass CAR-03: Growth Manager
Step 21 of 26
Action
Pass CAR-03: Growth ManagerAs Growth Manager, compare margin-aware value scenarios and keep every concept behind approval.
Expected resultThe captured Preview evidence records CAR-03 with the recorded identifiers Prepared for:** Growth Manager, Draft Incentive Scenario Comparison, Scenario for approval; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-03. A previous response must not influence the evidence.
Pass CAR-04: Growth Manager
Step 22 of 26
Action
Pass CAR-04: Growth ManagerAs Growth Manager, summarize the fixed recovery metrics and separate benchmarks from planning estimates.
Expected resultThe captured Preview evidence records CAR-04 with the recorded identifiers Synthetic Conversion Tracking, Recovery Rate, no cart or purchase is changed; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-04. A previous response must not influence the evidence.
Pass CAR-05: Marketing Manager
Step 23 of 26
Action
Pass CAR-05: Marketing ManagerAs Marketing Manager, what personalized offers should we make to win back our top abandoned-cart shoppers?
Expected resultThe captured Preview evidence records CAR-05 with the recorded identifiers Personalized Recovery Strategies, Sarah M., Point Expiry (12,000); do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-05. A previous response must not influence the evidence.
Pass CAR-06: Growth Manager
Step 24 of 26
Action
Pass CAR-06: Growth ManagerAs Growth Manager, how much revenue should we expect to win back over the next two days, and how does that compare to the industry?
Expected resultThe captured Preview evidence records CAR-06 with the recorded identifiers Recovery Forecast (48 hours), $37,940, +$56K/month; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-06. A previous response must not influence the evidence.
Pass CAR-07: Growth Manager
Step 25 of 26
Action
Pass CAR-07: Growth ManagerAs Growth Manager, what else could we change to lift our recovery rate further?
Expected resultThe captured Preview evidence records CAR-07 with the recorded identifiers Recovery Optimization Recommendations, Exit intent popup, Quick Win; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CAR-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.