Create a blank Copilot Studio agent
Step 1 of 30
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 Omnichannel Engagement 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 Omnichannel Engagement Manual
Step 2 of 30
Action
Name Omnichannel Engagement ManualOmnichannel Engagement Manual
Expected resultThe page header shows the recorded manual build name: Omnichannel Engagement Manual.
Enter the reviewed global instructions
Step 3 of 30
Action
Enter the reviewed global instructions# Omnichannel Engagement Agent — Manual Global Instructions Use only the uploaded synthetic records: one consented customer service record (Sarah Mitchell, CUST-SM-001, the default customer; Alpine Parka, $289 cart) and the aggregate channel, journey, and campaign records. Do not construct an identity graph across devices or infer a sensitive trait. For the customer view, route: journey across all channels / pick up where she left off -> customer-journey; what she asked and where we dropped the ball -> unresolved-issues; optimal channel strategy -> channel-recommendation; proactive engagement -> proactive-plan; handoff context -> handoff-package. Aggregate marketing questions use channel-performance, journey-analysis, engagement-optimization, and campaign-attribution. Produce analysis, drafts, and recommendations only. Never send or schedule outreach, create an offer, code, or reward, transfer a customer, alter a customer record, or complete a purchase. Lead with aggregate evidence, distinguish attribution from causality, name frequency and approval controls, and state that no side effect occurred. <!-- 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. - `OCE-01` uses skill `channel-performance`. - `OCE-02` uses skill `journey-analysis`. - `OCE-03` uses skill `engagement-optimization`. - `OCE-04` uses skill `campaign-attribution`. - `OCE-05` uses skill `customer-journey`. - `OCE-06` uses skill `unresolved-issues`. - `OCE-07` uses skill `channel-recommendation`. - `OCE-08` uses skill `proactive-plan`. - `OCE-09` uses skill `handoff-package`. 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 30
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 30
Action
Remove default web searchExpected resultThe captured inventory no longer lists the default web-search capability.
Add knowledge: aibast_omnichannel-rules-and-safety.md
Step 6 of 30
Action
Add knowledge: aibast_omnichannel-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_omnichannel-synthetic-records.md
Step 7 of 30
Action
Add knowledge: aibast_omnichannel-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-attribution_04
Step 8 of 30
Action
Add skill: aibast_campaign-attribution_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_channel-performance_01
Step 9 of 30
Action
Add skill: aibast_channel-performance_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_channel-recommendation_07
Step 10 of 30
Action
Add skill: aibast_channel-recommendation_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_customer-journey_05
Step 11 of 30
Action
Add skill: aibast_customer-journey_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_engagement-optimization_03
Step 12 of 30
Action
Add skill: aibast_engagement-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_handoff-package_09
Step 13 of 30
Action
Add skill: aibast_handoff-package_09Expected 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_journey-analysis_02
Step 14 of 30
Action
Add skill: aibast_journey-analysis_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_proactive-plan_08
Step 15 of 30
Action
Add skill: aibast_proactive-plan_08Expected 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_unresolved-issues_06
Step 16 of 30
Action
Add skill: aibast_unresolved-issues_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 17 of 30
Action
Review model, skills, knowledge, and safety boundariesExpected resultThe screenshot visibly confirms Claude Opus 5, 9 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the skill list (9 skills)
Step 18 of 30
Action
Review the skill list (9 skills)Expected resultThe screenshot visibly confirms Claude Opus 5, 9 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the rest of the skill list
Step 19 of 30
Action
Review the rest of the skill listExpected resultThe screenshot visibly confirms Claude Opus 5, 9 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Open a fresh Preview conversation
Step 20 of 30
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 OCE-01: Customer Experience Leader
Step 21 of 30
Action
Pass OCE-01: Customer Experience LeaderAs Customer Experience Leader, compare the aggregate channel picture and call out continuity risks.
Expected resultThe captured Preview evidence records OCE-01 with the recorded identifiers Prepared for:** Customer Experience Leader, Synthetic Channel Performance, no identity stitching; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-01. A previous response must not influence the evidence.
Pass OCE-02: Contact Center Supervisor
Step 22 of 30
Action
Pass OCE-02: Contact Center SupervisorAs Contact Center Supervisor, identify handoff friction across the aggregate journey archetypes.
Expected resultThe captured Preview evidence records OCE-02 with the recorded identifiers Prepared for:** Contact Center Supervisor, Aggregate Customer Journey Analysis, Journey Optimization Opportunities; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-02. A previous response must not influence the evidence.
Pass OCE-03: Digital Engagement Manager
Step 23 of 30
Action
Pass OCE-03: Digital Engagement ManagerAs Digital Engagement Manager, propose consent-aware experiments with frequency caps and no outreach.
Expected resultThe captured Preview evidence records OCE-03 with the recorded identifiers Prepared for:** Digital Engagement Manager, Draft Engagement Optimization Report, frequency caps; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-03. A previous response must not influence the evidence.
Pass OCE-04: Digital Engagement Manager
Step 24 of 30
Action
Pass OCE-04: Digital Engagement ManagerAs Digital Engagement Manager, summarize the synthetic attribution view and avoid causal claims.
Expected resultThe captured Preview evidence records OCE-04 with the recorded identifiers Synthetic Campaign Attribution Report, Overall Campaign ROI, Recommendations only; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-04. A previous response must not influence the evidence.
Pass OCE-05: Contact Center Supervisor
Step 25 of 30
Action
Pass OCE-05: Contact Center SupervisorShow me the customer's journey across all channels and help me pick up where they left off.
Expected resultThe captured Preview evidence records OCE-05 with the recorded identifiers Customer Journey: Sarah Mitchell, Payment declined, $289 cart; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-05. A previous response must not influence the evidence.
Pass OCE-06: Contact Center Supervisor
Step 26 of 30
Action
Pass OCE-06: Contact Center SupervisorShow me what Sarah has been asking about and where we dropped the ball.
Expected resultThe captured Preview evidence records OCE-06 with the recorded identifiers Does Alpine Parka run true to size?, runs one size small, 18 minutes; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-06. A previous response must not influence the evidence.
Pass OCE-07: Digital Engagement Manager
Step 27 of 30
Action
Pass OCE-07: Digital Engagement ManagerWhich channel and timing should we use to reach Sarah for this issue and in the future?
Expected resultThe captured Preview evidence records OCE-07 with the recorded identifiers 82% open, SMS confirmation, 7-9 PM; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-07. A previous response must not influence the evidence.
Pass OCE-08: Digital Engagement Manager
Step 28 of 30
Action
Pass OCE-08: Digital Engagement ManagerWhat proactive engagement should we plan for Sarah after this purchase, or if she doesn't convert?
Expected resultThe captured Preview evidence records OCE-08 with the recorded identifiers Proactive Engagement Plan (Draft), Win-Back, Day 5: Personal stylist call; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-08. A previous response must not influence the evidence.
Pass OCE-09: Customer Experience Leader
Step 29 of 30
Action
Pass OCE-09: Customer Experience LeaderPrepare the context in case Sarah needs to be handed off to another agent.
Expected resultThe captured Preview evidence records OCE-09 with the recorded identifiers Handoff Package: Sarah Mitchell, $2,400 LTV, no need to repeat anything; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running OCE-09. A previous response must not influence the evidence.
Confirm Draft and stop before publish
Step 30 of 30
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.