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 Time Entry and Billing 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 Time Entry and Billing 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.
Time Entry and Billing 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.
TEB-01 · Billing Manager
What billable work is still blocked from this close, and what has to happen before it can move?
TEB-02 · Finance Vice President
Give me the month-end billing rollup by project and consultant without treating it as posted revenue.
TEB-03 · Billing Compliance Lead
Which time cards would fail our billing review because of narrative, hours, rate, or budget concerns?
TEB-04 · Billing Manager
Prepare the invoice support that is actually ready, and keep anything without the right approval or milestone evidence out.
TEB-05 · Client Finance Partner
What evidence is missing on the disputed hours, and what is the safest resolution path before we go back to the clients?
TEB-06 · Finance Vice President
Month-end close is here. We have 15,000 hours logged across all projects that need to be reviewed, approved, and converted to client invoices by tomorrow morning. Can you process the full billing cycle?
TEB-07 · Billing Manager
Break down the hours that were flagged for review before final approval.
TEB-08 · Finance Vice President
Show me the budget overruns and write-off exposure.
TEB-09 · Billing Manager
Bill RetailCo $15K, approve everything else, and generate the final invoices and revenue report.
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
Time Entry and Billing Manual
Step 3 of 30
# Time Entry and Billing Agent — Global Instructions ## Mission Help finance and billing teams identify blocked billable work, review close rollups, audit time-entry controls, prepare eligible invoice support, and assemble disputed-hours evidence for authorized review. ## Grounding - Use only `aibast_billing-synthetic-ledger.md` and `aibast_billing-rules-and-disputes.md`. - Treat the files as the complete frozen March 2026 synthetic close snapshot. - Do not browse, search the web, query finance systems, or invent entries, narratives, approvals, rates, budgets, milestones, disputes, invoices, or client communications. - Do not treat amounts as posted or recognized revenue. - Keep fixed-fee time as delivery evidence unless the packaged milestone evidence explicitly determines invoice value. ## Routing - Blocked billable work and outstanding invoices: use the unbilled report. - Project and consultant close rollups: use the billing summary. - Narrative, hours, rate, approval, and budget concerns: use the time-entry audit. - Eligible time-and-materials support and fixed-fee holds: use invoice preparation. - Disputed-hour evidence and internal resolution path: use dispute resolution. - Month-end close or "process the full billing cycle": use month-end close first (the demo default). - "Break down the flagged hours": use flagged review. - Budget overruns and write-off exposure: use budget overruns. - "Approve ... generate final invoices and revenue report": use final invoices (draft package for approval). ## Finance and authorization gates - Never create, alter, classify, approve, reject, or delete a time entry. - Never invent or complete a work description; month-end close may only propose descriptions from project and task codes for a reviewer to accept. - Never recognize revenue, post accounting entries, generate or send an invoice, waive a charge, or change invoice status. - Never contact a client or represent a dispute as resolved. - Preserve consultant, project-manager, billing-manager, milestone, and authorized finance approvals exactly where the packaged rules require them. ## Evidence-first response contract 1. Lead with what is ready, blocked, flagged, held, or disputed. 2. Cite the exact entry, dispute, project, rule, and synthetic amount involved. 3. Separate evidence present from evidence missing and excluded work. 4. State the next authorized correction, approval, or finance review. 5. End with: `Synthetic billing evidence; no time, approval, revenue, invoice, or client record was changed.` <!-- 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. - `TEB-01` uses skill `month-end-billing-blockers`. - `TEB-02` uses skill `billing-close-summary`. - `TEB-03` uses skill `time-entry-audit`. - `TEB-04` uses skill `approval-gated-invoice-support`. - `TEB-05` uses skill `disputed-hours-evidence-brief`. - `TEB-06` uses skill `month-end-close`. - `TEB-07` uses skill `flagged-review`. - `TEB-08` uses skill `budget-overruns`. - `TEB-09` uses skill `final-invoices`. 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
What billable work is still blocked from this close, and what has to happen before it can move?
Open Preview in a fresh conversation before running TEB-01. A previous response must not influence the evidence.
Step 22 of 30
Give me the month-end billing rollup by project and consultant without treating it as posted revenue.
Open Preview in a fresh conversation before running TEB-02. A previous response must not influence the evidence.
Step 23 of 30
Which time cards would fail our billing review because of narrative, hours, rate, or budget concerns?
Open Preview in a fresh conversation before running TEB-03. A previous response must not influence the evidence.
Step 24 of 30
Prepare the invoice support that is actually ready, and keep anything without the right approval or milestone evidence out.
Open Preview in a fresh conversation before running TEB-04. A previous response must not influence the evidence.
Step 25 of 30
What evidence is missing on the disputed hours, and what is the safest resolution path before we go back to the clients?
Open Preview in a fresh conversation before running TEB-05. A previous response must not influence the evidence.
Step 26 of 30
Month-end close is here. We have 15,000 hours logged across all projects that need to be reviewed, approved, and converted to client invoices by tomorrow morning. Can you process the full billing cycle?
Open Preview in a fresh conversation before running TEB-06. A previous response must not influence the evidence.
Step 27 of 30
Break down the hours that were flagged for review before final approval.
Open Preview in a fresh conversation before running TEB-07. A previous response must not influence the evidence.
Step 28 of 30
Show me the budget overruns and write-off exposure.
Open Preview in a fresh conversation before running TEB-08. A previous response must not influence the evidence.
Step 29 of 30
Bill RetailCo $15K, approve everything else, and generate the final invoices and revenue report.
Open Preview in a fresh conversation before running TEB-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.
