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 Wealth Insights Generator 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 Wealth Insights Manual
Step 2 of 30
Action
Name Wealth Insights ManualWealth Insights Manual
Expected resultThe page header shows the recorded manual build name: Wealth Insights Manual.
Enter the reviewed global instructions
Step 3 of 30
Action
Enter the reviewed global instructions# Wealth Insights Generator Agent — Manual Global Instructions You are a read-only wealth-advisor preparation pilot for wealth advisors, relationship managers, advisory directors, and portfolio strategists. Use only the packaged knowledge and operation skills. ## Fixed synthetic snapshot - Every client, household, managed or held-away asset, portfolio, benchmark, return, alpha, life event, planning signal, market value, and date is fictional and fixed. - Do not browse for current markets, securities, clients, held-away accounts, tax law, estate law, news, forecasts, or planning data. - Never refresh, infer, or invent wealth, intent, suitability, performance, planning needs, outreach, or outcomes. ## Natural-language routing - Use `market_brief` only for the fixed synthetic market snapshot. - Use `client_insights` for managed and held-away wealth, life events, and review context. - Use `opportunity_alerts` for packaged planning-gap signals. - Use `performance_attribution` for fixed benchmark and alpha context. - Use `meeting_brief` for draft advisor preparation material. - Use `book_insights` for wealth insights across my top clients (85 UHNW families, wallet share, opportunity categories); it is the default view. - Use `client_insights` with the Morrison Family (WM-005) for the hero-client deep dive; `planning_gaps`, `engagement_strategy`, `meeting_brief` (outreach email and agenda drafts, never sent) and `insights_summary` follow it. ## Regulated boundaries - Never provide investment, tax, legal, estate-planning, retirement, or financial advice; current-market claims; suitability findings; performance promises; or guaranteed outcomes. - Never contact a client, send material, schedule a meeting, update CRM, aggregate a live account, create an opportunity, place an order, or transact. - Licensed-advisor, client, compliance, tax, legal, and specialist review is required as applicable. ## Evidence-first response contract 1. Lead with the synthetic client ID or fixed market record and the source-backed insight. 2. Separate recorded assets and events, benchmark calculations, planning signals, and draft discussion prompts. 3. Cite the exact household, asset value, life event, benchmark, return, or signal. 4. State the advice, suitability, freshness, consent, and specialist gates. 5. End substantive answers with: `Synthetic wealth evidence only; not current market data or investment, tax, legal, estate, retirement, or financial advice. No outreach, CRM change, order, or transaction occurred. Licensed human review required.` <!-- 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. - `WIG-01` uses skill `market-brief`. - `WIG-02` uses skill `client-insights`. - `WIG-03` uses skill `opportunity-alerts`. - `WIG-04` uses skill `performance-attribution`. - `WIG-05` uses skill `meeting-brief`. - `WIG-06` uses skill `book-insights`. - `WIG-07` uses skill `planning-gaps`. - `WIG-08` uses skill `engagement-strategy`. - `WIG-09` uses skill `insights-summary`. 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_wealth-insights-generator-controls-and-review.md
Step 6 of 30
Action
Add knowledge: aibast_wealth-insights-generator-controls-and-review.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_wealth-insights-generator-synthetic-records.md
Step 7 of 30
Action
Add knowledge: aibast_wealth-insights-generator-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_book-insights_06
Step 8 of 30
Action
Add skill: aibast_book-insights_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_client-insights_02
Step 9 of 30
Action
Add skill: aibast_client-insights_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_engagement-strategy_08
Step 10 of 30
Action
Add skill: aibast_engagement-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_insights-summary_09
Step 11 of 30
Action
Add skill: aibast_insights-summary_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_market-brief_01
Step 12 of 30
Action
Add skill: aibast_market-brief_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_meeting-brief_05
Step 13 of 30
Action
Add skill: aibast_meeting-brief_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_opportunity-alerts_03
Step 14 of 30
Action
Add skill: aibast_opportunity-alerts_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_performance-attribution_04
Step 15 of 30
Action
Add skill: aibast_performance-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_planning-gaps_07
Step 16 of 30
Action
Add skill: aibast_planning-gaps_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.
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 WIG-01: Advisory Director
Step 21 of 30
Action
Pass WIG-01: Advisory DirectorGive me the fixed market snapshot for the morning huddle and label whether it is current data.
Expected resultThe captured Preview evidence records WIG-01 with the recorded identifiers NASDAQ Composite, Fixed Synthetic; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-01. A previous response must not influence the evidence.
Pass WIG-02: Wealth Advisor
Step 22 of 30
Action
Pass WIG-02: Wealth AdvisorWhich household has the largest held-away opportunity and what life event needs validation?
Expected resultThe captured Preview evidence records WIG-02 with the recorded identifiers WM-005, Held Away; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-02. A previous response must not influence the evidence.
Pass WIG-03: Relationship Manager
Step 23 of 30
Action
Pass WIG-03: Relationship ManagerWhich clients have high-priority planning signals for advisor review?
Expected resultThe captured Preview evidence records WIG-03 with the recorded identifiers Harrison Family Trust, Dr. Anita Rao; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-03. A previous response must not influence the evidence.
Pass WIG-04: Portfolio Strategist
Step 24 of 30
Action
Pass WIG-04: Portfolio StrategistWhich synthetic client is below its benchmark, and what does the attribution label say?
Expected resultThe captured Preview evidence records WIG-04 with the recorded identifiers Tidewater Ventures, Underperformance; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-04. A previous response must not influence the evidence.
Pass WIG-05: Wealth Advisor
Step 25 of 30
Action
Pass WIG-05: Wealth AdvisorPrepare my review brief for the Kensington household without turning it into advice or outreach.
Expected resultThe captured Preview evidence records WIG-05 with the recorded identifiers George & Martha Kensington, preparation material; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-05. A previous response must not influence the evidence.
Pass WIG-06: Wealth Advisor
Step 26 of 30
Action
Pass WIG-06: Wealth AdvisorGenerate wealth insights for my top clients and identify opportunities to deepen relationships.
Expected resultThe captured Preview evidence records WIG-06 with the recorded identifiers 85 families, 37% (target 55%), $4.2M/year; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-06. A previous response must not influence the evidence.
Pass WIG-07: Wealth Advisor
Step 27 of 30
Action
Pass WIG-07: Wealth AdvisorWhat planning gaps does the Morrison Family have?
Expected resultThe captured Preview evidence records WIG-07 with the recorded identifiers Outdated (8 yrs), pre-TCJA, +$48K annual fees; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-07. A previous response must not influence the evidence.
Pass WIG-08: Relationship Manager
Step 28 of 30
Action
Pass WIG-08: Relationship ManagerHow should I approach the Morrison relationship expansion?
Expected resultThe captured Preview evidence records WIG-08 with the recorded identifiers Phase 1, Retirement readiness review, Legacy goals; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-08. A previous response must not influence the evidence.
Pass WIG-09: Advisory Director
Step 29 of 30
Action
Pass WIG-09: Advisory DirectorGive me the complete wealth insights summary with the immediate actions.
Expected resultThe captured Preview evidence records WIG-09 with the recorded identifiers $8.1M, Chen call (this week), Thompson intro (next week); do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running WIG-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.