Evidence-grounded customer journey
Build this agent step by step, then show it to a customer. Easy mode lets AI do the clicks; Manual mode shows every step yourself.
Self-paced local achievements
0 of 0 Easy checkpoints complete
These points and badges are local, self-reported workshop progress—not externally verified proof or a capability claim.
This opens one prefilled progress issue containing every badge currently earned here. Nothing syncs until you submit it. Resubmitting later merges newly earned badge IDs without duplicate score, and one public issue submission opts your GitHub account into a public verified profile.
Workshop setup
Start in GitHub Copilot Chat. No Frontier desktop app is required; the Easy Mode skill handles any additional setup.
GitHub Copilot Chat is open in VS Code, signed in, and set to Agent mode.
Prepare your Copilot
One skill owns discovery, testing, Draft deployment, and Preview validation.
Go and read https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/skills/aibast-easy-mode/SKILL.md and run the Wealth Insights Generator workshop for me.
Copilot says it has read the skill and is running the workshop. The skill owns the remaining setup and validation.
Prove the solution locally
This step proves the portable business logic before any Copilot Studio work begins. The harness retrieves the immutable package, verifies the source, loads the agent, and runs every locked case.
Give me Wealth Insights Generator using Easy Mode and test it for me.
Copilot reports a verified source and 9/9 locked local cases passed.
Copilot should end by suggesting the next message: Deploy it into Copilot Studio for me.
Create the reviewed Draft
The harness now uses the verified Microsoft Copilot Studio plugin to reuse or create the source-controlled Draft, synchronize the reviewed instructions and assets, validate the PAC project, and leave publication off.
Deploy it into Copilot Studio for me.
Wealth Insights ManualClaude Opus 529falseThe harness then validates the real Preview front door before returning its final verdict.
Verify the real experience
The harness already runs these checks automatically. Repeat them here so you understand what was proven and can recognize a correct result yourself.
Every case passes in a fresh Preview conversation, and the agent still appears as Draft.
WIG-01 · Advisory Director
Give me the fixed market snapshot for the morning huddle and label whether it is current data.
WIG-02 · Wealth Advisor
Which household has the largest held-away opportunity and what life event needs validation?
WIG-03 · Relationship Manager
Which clients have high-priority planning signals for advisor review?
WIG-04 · Portfolio Strategist
Which synthetic client is below its benchmark, and what does the attribution label say?
WIG-05 · Wealth Advisor
Prepare my review brief for the Kensington household without turning it into advice or outreach.
WIG-06 · Wealth Advisor
Generate wealth insights for my top clients and identify opportunities to deepen relationships.
WIG-07 · Wealth Advisor
What planning gaps does the Morrison Family have?
WIG-08 · Relationship Manager
How should I approach the Morrison relationship expansion?
WIG-09 · Advisory Director
Give me the complete wealth insights summary with the immediate actions.
Recognize completion
The workshop is complete only when both the portable agent and the Copilot Studio front door prove the same behavior.
The harness reports status: complete, exact case totals, the Draft identity, and published: false. The module ends here; it does not offer publication.
| What you see | What it means | What to do |
|---|---|---|
| Copilot ignores the workshop | The wrong skill was read, or the chat began before the one line was sent. | Start a new Agent-mode chat and send the one line first. |
| Local validation is not 9/9 | The portable source, package, or locked behavior does not match. | Stop. Do not deploy. Let the harness report the exact failed case and marker. |
| No active Copilot Studio environment | PAC has no selected environment. | Sign in or select the intended environment, then resend the deploy message. |
| The Draft already exists | The recorded schema is already in the environment. | The harness should clone and reconnect automatically. Treat an attendee choice prompt as a harness defect. |
| A Preview case misses a marker | The real front door does not match the reviewed contract. | Keep the case failed. Inspect instructions and assets; do not retry until it happens to pass. |
| The agent is Published | The workshop crossed its safety boundary. | Stop immediately. The module must end at Draft with published: false. |
These links support audit, troubleshooting, and offline delivery. They are not learner steps.
Manual mode · see how it was built
Optional. Easy mode already did all of this for you from one skill file. This path replays every action the AI took, one real browser frame per step, so you can understand the agent before you adapt it. No PAC CLI, YAML import, or plugin architect; stop at Draft.
Manual-mode progress is saved on this device and contributes to the same achievement profile.
Step 1 of 30
Step 2 of 30
Wealth Insights Manual
Step 3 of 30
# 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 -->
Step 4 of 30
Step 5 of 30
Step 6 of 30
Step 7 of 30
Step 8 of 30
Step 9 of 30
Step 10 of 30
Step 11 of 30
Step 12 of 30
Step 13 of 30
Step 14 of 30
Step 15 of 30
Step 16 of 30
Step 17 of 30
Step 18 of 30
Step 19 of 30
Step 20 of 30
Step 21 of 30
Give me the fixed market snapshot for the morning huddle and label whether it is current data.
Open Preview in a fresh conversation before running WIG-01. A previous response must not influence the evidence.
Step 22 of 30
Which household has the largest held-away opportunity and what life event needs validation?
Open Preview in a fresh conversation before running WIG-02. A previous response must not influence the evidence.
Step 23 of 30
Which clients have high-priority planning signals for advisor review?
Open Preview in a fresh conversation before running WIG-03. A previous response must not influence the evidence.
Step 24 of 30
Which synthetic client is below its benchmark, and what does the attribution label say?
Open Preview in a fresh conversation before running WIG-04. A previous response must not influence the evidence.
Step 25 of 30
Prepare my review brief for the Kensington household without turning it into advice or outreach.
Open Preview in a fresh conversation before running WIG-05. A previous response must not influence the evidence.
Step 26 of 30
Generate wealth insights for my top clients and identify opportunities to deepen relationships.
Open Preview in a fresh conversation before running WIG-06. A previous response must not influence the evidence.
Step 27 of 30
What planning gaps does the Morrison Family have?
Open Preview in a fresh conversation before running WIG-07. A previous response must not influence the evidence.
Step 28 of 30
How should I approach the Morrison relationship expansion?
Open Preview in a fresh conversation before running WIG-08. A previous response must not influence the evidence.
Step 29 of 30
Give me the complete wealth insights summary with the immediate actions.
Open Preview in a fresh conversation before running WIG-09. A previous response must not influence the evidence.
Step 30 of 30
Stop. Do not invent, recreate, or substitute an image. Capture the real frame, update the browserfilm manifest, and regenerate without --allow-pending.
Wait for ingestion to finish before Preview. A partial answer is not evidence.
Use the linked raw SKILL.md. Fix the reviewed source deliberately; do not silently skip the action.
Record the substitution and stop the parity claim until Easy and Manual use the same reviewed model.
Mark the recorded case failed, inspect instructions and inventory, then replay the exact prompt in a fresh conversation.
No. Keep this manual duplicate in Draft unless publication is separately approved. Do not choose Publish as part of this tutorial.
