Create a blank Copilot Studio agent
Step 1 of 32
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 Care Gap Closure 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 Care Gap Closure Manual
Step 2 of 32
Action
Name Care Gap Closure ManualCare Gap Closure Manual
Expected resultThe page header shows the recorded manual build name: Care Gap Closure Manual.
Enter the reviewed global instructions
Step 3 of 32
Action
Enter the reviewed global instructions# Role You are Care Gap Closure Agent, a synthetic, read-only healthcare evidence assistant for Quality Manager, Care Coordinator, Clinical Operations Lead. Use only the two packaged manual knowledge files. # Privacy and clinical boundary - All people, identifiers, organizations, dates, measures, policies, records, and workflow states are fictional. - Never request, retain, infer, or expose live patient information. Use minimum-necessary synthetic fields. - Never provide diagnosis or treatment advice. - Never make eligibility, measure-compliance, medical-necessity, or authorization outcomes beyond clearly labeled source evidence. - Never schedule, contact, send, submit, publish, place, cancel, or change any appointment, referral, order, authorization, message, outreach, task, or record. - A qualified clinical, utilization, quality, or operational reviewer must verify every substantive answer. # Natural-language routing - Route requests about **source-evidence gap analysis** to `gap_analysis`. Summarizes aggregate synthetic source counts and limitations without deciding measure eligibility. - Route requests about **aggregate cohort review** to `cohort_review`. Organizes operational evidence-review cohorts without clinical risk scoring. - Route requests about **unsent outreach draft** to `outreach_draft`. Drafts privacy-aware language but does not contact anyone. - Route requests about **qualitative quality dashboard** to `quality_dashboard`. Shows source-completeness signals for quality and clinical validation. Do not require users to know operation names. Ask one concise clarification only when the intent cannot be mapped safely. # Decision rules 1. Never identify a person as eligible, overdue, high risk, or noncompliant from agent output alone. 2. Never send outreach, schedule care, or change a quality or clinical record. 3. Validate exclusions, consent, contact preferences, accessibility, and minimum-necessary content. 4. Quality and clinical reviewers approve downstream action. 5. For CG-01, compare all three measures using source population minus source-recorded closed. Do not inherit a measure filter from another case: SYN-COL has 182 records, SYN-BCS has 108, and SYN-CDC has 53 requiring evidence review. # Response style Lead with the read-only finding, cite the synthetic identifier and source limitation, use compact Markdown, and end every substantive response with: `> Synthetic healthcare evidence only; no diagnosis, treatment, eligibility, authorization, scheduling, outreach, submission, or record change. Human review required.` # Production seams Potential Microsoft connection seams are Dynamics 365 care-coordination workflow, Microsoft Teams review and approval. They are future governed integrations only; this package has no live connection or write permission. <!-- 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. - `CG-01` uses skill `care-gap-closure-gap-analysis`. - `CG-02` uses skill `care-gap-closure-cohort-review`. - `CG-03` uses skill `care-gap-closure-outreach-draft`. - `CG-04` uses skill `care-gap-closure-quality-dashboard`. - `CG-05` uses skill `hedis-status`. - `CG-06` uses skill `top-gaps`. - `CG-07` uses skill `risk-stratification`. - `CG-08` uses skill `outreach-strategy`. - `CG-09` uses skill `campaign-projection`. - `CG-10` uses skill `monitoring-plan`. 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 32
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 32
Action
Remove default web searchExpected resultThe captured inventory no longer lists the default web-search capability.
Add knowledge: aibast_care-gap-closure-review-rules.md
Step 6 of 32
Action
Add knowledge: aibast_care-gap-closure-review-rules.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_care-gap-closure-synthetic-records.md
Step 7 of 32
Action
Add knowledge: aibast_care-gap-closure-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-projection_09
Step 8 of 32
Action
Add skill: aibast_campaign-projection_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_cohort-review_02
Step 9 of 32
Action
Add skill: aibast_cohort-review_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_gap-analysis_01
Step 10 of 32
Action
Add skill: aibast_gap-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_hedis-status_05
Step 11 of 32
Action
Add skill: aibast_hedis-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_monitoring-plan_10
Step 12 of 32
Action
Add skill: aibast_monitoring-plan_10Expected 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_outreach-draft_03
Step 13 of 32
Action
Add skill: aibast_outreach-draft_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_outreach-strategy_08
Step 14 of 32
Action
Add skill: aibast_outreach-strategy_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_quality-dashboard_04
Step 15 of 32
Action
Add skill: aibast_quality-dashboard_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_risk-stratification_07
Step 16 of 32
Action
Add skill: aibast_risk-stratification_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_top-gaps_06
Step 17 of 32
Action
Add skill: aibast_top-gaps_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 18 of 32
Action
Review model, skills, knowledge, and safety boundariesExpected resultThe screenshot visibly confirms Claude Opus 5, 10 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the skill list (10 skills)
Step 19 of 32
Action
Review the skill list (10 skills)Expected resultThe screenshot visibly confirms Claude Opus 5, 10 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Review the rest of the skill list
Step 20 of 32
Action
Review the rest of the skill listExpected resultThe screenshot visibly confirms Claude Opus 5, 10 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Open a fresh Preview conversation
Step 21 of 32
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 CG-01: Quality Manager
Step 22 of 32
Action
Pass CG-01: Quality ManagerWhich synthetic quality measure has the largest evidence-review queue?
Expected resultThe captured Preview evidence records CG-01 with the recorded identifiers SYN-COL — 182 records, Records requiring evidence review; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-01. A previous response must not influence the evidence.
Pass CG-02: Care Coordinator
Step 23 of 32
Action
Pass CG-02: Care CoordinatorOrganize the synthetic evidence-review cohorts without clinical risk scoring.
Expected resultThe captured Preview evidence records CG-02 with the recorded identifiers Multiple Source Gaps, operational triage only; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-02. A previous response must not influence the evidence.
Pass CG-03: Care Coordinator
Step 24 of 32
Action
Pass CG-03: Care CoordinatorDraft outreach for the synthetic screening measure, but do not send it or state that anyone is eligible.
Expected resultThe captured Preview evidence records CG-03 with the recorded identifiers No message is sent, Do not state; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-03. A previous response must not influence the evidence.
Pass CG-04: Clinical Operations Lead
Step 25 of 32
Action
Pass CG-04: Clinical Operations LeadShow the qualitative source-completeness dashboard and its limitations.
Expected resultThe captured Preview evidence records CG-04 with the recorded identifiers SYN-BCS, source-recorded closed; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-04. A previous response must not influence the evidence.
Pass CG-05: Quality Manager
Step 26 of 32
Action
Pass CG-05: Quality ManagerI need to prioritize care gaps for our Medicare Advantage population before the HEDIS reporting deadline. What's our current status?
Expected resultThe captured Preview evidence records CG-05 with the recorded identifiers HEDIS Performance Summary, 1,142 (40.1%), $428,900; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-05. A previous response must not influence the evidence.
Pass CG-06: Quality Manager
Step 27 of 32
Action
Pass CG-06: Quality ManagerShow me the top care gaps and which ones are most actionable.
Expected resultThe captured Preview evidence records CG-06 with the recorded identifiers Top 5 Care Gap Measures, $189,450, Best Opportunity; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-06. A previous response must not influence the evidence.
Pass CG-07: Care Coordinator
Step 28 of 32
Action
Pass CG-07: Care CoordinatorShow me the diabetes cohort analysis with risk tiers and engagement barriers.
Expected resultThe captured Preview evidence records CG-07 with the recorded identifiers A1C >9.0 (Critical), Transportation: 34% (132 patients), 4.2 chronic conditions; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-07. A previous response must not influence the evidence.
Pass CG-08: Care Coordinator
Step 29 of 32
Action
Pass CG-08: Care CoordinatorDesign a barrier-specific outreach strategy for the diabetes gap patients.
Expected resultThe captured Preview evidence records CG-08 with the recorded identifiers Outreach Strategy Draft, 294 SMS, 94 RN callbacks; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-08. A previous response must not influence the evidence.
Pass CG-09: Clinical Operations Lead
Step 30 of 32
Action
Pass CG-09: Clinical Operations LeadShow me the campaign deployment plan and projected impact.
Expected resultThe captured Preview evidence records CG-09 with the recorded identifiers 42% expected, $128,700 of $189,450, 47 to reserve; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-09. A previous response must not influence the evidence.
Pass CG-10: Clinical Operations Lead
Step 31 of 32
Action
Pass CG-10: Clinical Operations LeadConfigure monitoring for the campaign and alert me if performance drops.
Expected resultThe captured Preview evidence records CG-10 with the recorded identifiers Daily 8 AM summary via Teams, Close rate drops below 60%, Monitoring and Alert Configuration; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running CG-10. A previous response must not influence the evidence.
Confirm Draft and stop before publish
Step 32 of 32
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.