Evidence-grounded customer journey

Campaign Delivery Optimizer Agent

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.

Get the one-pager and demo video Office hours All solutions

About this workshop

Workshop mission: Turn motivated, open-minded, non-technical sales professionals into AI superheroes who can match the practical output and problem-solving pace of technical peers who are not using AI, while staying evidence-grounded, governed, and honest about what the tools proved.

Boundary: synthetic qualitative evidence only—not a customer KPI, measured production result, live connection, or publication approval.

Found something inaccurate? Use Report an issue at that point. It opens a prefilled GitHub issue for review and does not submit anything automatically.

Self-paced local achievements

Workshop achievements

0 total points 0 in this workshop

0 of 0 Easy checkpoints complete

No badges yet

View achievements and local profile

Optional public verification

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

Open GitHub Copilot Chat

Start in GitHub Copilot Chat. No Frontier desktop app is required; the Easy Mode skill handles any additional setup.

Get ready

Open VS Code with the GitHub Copilot Chat extension installed.
Sign in to GitHub with an account that has Copilot access.
Open the Copilot Chat panel and select Agent mode.

Expected result

GitHub Copilot Chat is open in VS Code, signed in, and set to Agent mode.

I opened GitHub Copilot Chat in Agent mode.

What you will learn

Use the single Easy Mode skill.
Build and prove the portable agent.
Deploy the reviewed solution as an unpublished Draft.
Confirm the behavior yourself in Copilot Studio Preview.
Recognize the evidence that means the module is complete.

Before you begin

Use VS Code with GitHub Copilot Chat in Agent mode.
Sign in to GitHub with Copilot access.
Have access to a Copilot Studio environment.
The skill handles setup for you.
Do not publish. This module ends with a validated Draft.

Easy mode

Prepare your Copilot

Brief your Copilot with one line

One skill owns discovery, testing, Draft deployment, and Preview validation.

Do this

Open GitHub Copilot Chat in VS Code and select Agent mode.
Paste this one line and send it. Copilot reads the skill itself; nothing to download.

Send this message

Go and read https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/skills/aibast-easy-mode/SKILL.md and run the Campaign Delivery Optimizer workshop for me.

Expected result

Copilot says it has read the skill and is running the workshop. The skill owns the remaining setup and validation.

I sent the one line and Copilot started the workshop.

Prove the solution locally

Ask Easy Mode to build and test Campaign Delivery Optimizer

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.

Send this message

Give me Campaign Delivery Optimizer using Easy Mode and test it for me.

Expected result

Copilot reports a verified source and 3/3 locked local cases passed.

Copilot should end by suggesting the next message: Deploy it into Copilot Studio for me.

I saw every locked local case pass.

Create the reviewed Draft

Deploy the already-tested solution to Copilot Studio

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.

Send this message

Deploy it into Copilot Studio for me.

Expected result

Draft: Campaign Delivery Manual
Model: Claude Opus 5.5
Knowledge files: 2
Skills: 3
Status: Draft; published: false

The harness then validates the real Preview front door before returning its final verdict.

I saw the Draft identity and unpublished state.

Verify the real experience

Confirm the Draft in Copilot Studio Preview

The harness already runs these checks automatically. Repeat them here so you understand what was proven and can recognize a correct result yourself.

Open the validated Draft.
Select Preview.
Choose New chat before each case.
Paste the exact prompt.
Compare the answer with the required and forbidden markers.

Open the Copilot Studio Draft ↗

Expected result

Every case passes in a fresh Preview conversation, and the agent still appears as Draft.

CDO-01 · Ad Operations Manager

Confirm the expected evidence

Is the Harborlight Streaming campaign falling behind this week, and by how much?

Must include

Campaign Risk18% below plan235,000

Must not claim

I do not have accessI cannot help

Visible positive anchors: Campaign Risk; 235,000; 18% below plan. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

The Preview response matched this contract.

CDO-02 · Campaign Manager

Confirm the expected evidence

Where can we find extra reach this week to close the Harborlight gap?

Must include

Available ReachStreaming Home Screen Takeover42,000

Must not claim

I do not have accessI cannot help

Visible positive anchors: Streaming Home Screen Takeover; 42,000; Available Reach. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

The Preview response matched this contract.

CDO-03 · Ad Sales Lead

Confirm the expected evidence

Draft the make-good for Harborlight so Maya can review it. Don't send anything to the advertiser yet.

Must include

Approval RecommendationPending sales lead approvalDraft only

Must not claim

I do not have accessI cannot help

Visible positive anchors: Draft only; Pending sales lead approval; Approval Recommendation. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.

The Preview response matched this contract.

Recognize completion

Know what “done” looks like

The workshop is complete only when both the portable agent and the Copilot Studio front door prove the same behavior.

Local proof3/3 locked cases passed

Preview proof3/3 locked cases passed

Draft identityCampaign Delivery Manual

ModelClaude Opus 5.5

Inventory2 knowledge · 3 skills

Publication gateDraft · published false

Positive visual checkpoint. Source: 1424×863 JPEG. Download original.

Final expected verdict

The harness reports status: complete, exact case totals, the Draft identity, and published: false. The module ends here; it does not offer publication.

I confirmed the final Draft verdict.

Troubleshooting

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 3/3	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`.

Facilitator evidence and portable download

These links support audit, troubleshooting, and offline delivery. They are not learner steps.

Field guide Locked evidence Evidence report Download audit manifest Download portable bundle Download Copilot Studio solution Deployment settings Export details Download generic workshop agent Download SKILL.md

Manual mode · see how it was built

See how Campaign Delivery Optimizer Agent is built, one capability at a time.

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.

Synthetic disclosure: this is qualitative workflow evidence using packaged synthetic inputs. It is not a customer KPI or a live-system result.

Found something inaccurate? Use Report an issue on that step. It opens a prefilled GitHub issue for review and does not submit automatically.

Open standalone Manual-mode guide ↗ Download source bundle Download Copilot Studio solution Deployment settings Export details

0 of 16 complete

Manual-mode progress is saved on this device and contributes to the same achievement profile.

Build and verify

Create a blank Copilot Studio agent

Step 1 of 16

Action

Create a blank Copilot Studio agent

Expected resultA blank Copilot Studio agent is visible in the captured Draft workspace.

Positive visual checkpoint: Untitled Agent. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Name Campaign Delivery Manual

Step 2 of 16

Action

Campaign Delivery Manual

Name Campaign Delivery Manual

Expected resultThe page header shows the recorded manual build name: Campaign Delivery Manual.

Positive visual checkpoint: Campaign Delivery Manual. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Enter the reviewed global instructions

Step 3 of 16

Action

# Campaign Delivery Optimizer — Manual Global Instructions

You are a synthetic campaign delivery pilot for a media company's ad sales and ad operations teams. Explain the fixed weekly delivery snapshot and prepare reviewable recommendation drafts without booking inventory, changing a campaign, or sharing anything with an advertiser.

## Fixed synthetic snapshot

- Use only the uploaded Campaign Delivery Optimizer synthetic records, rules, and three
packaged skills.
- The media company and every advertiser campaign, reach figure, placement, inventory record, sales lead, and recommendation draft are invented.
- Do not browse, consult external sources, or add current-date, market, legal,
or customer facts. Never invent a record, value, deadline, decision, or
transaction.
- Never match a fictional organization, person, or record to a real one or
claim access to a live system.

## Natural-language routing

- Use **campaign risk check** for: someone asks whether a campaign is behind plan this week, how big the delivery gap is, or why it is at risk.
- Use **available reach** for: someone asks which placements have extra reach this week to close a campaign's delivery gap.
- Use **recommendation draft for approval** for: someone asks for the recommendation or make-good for a campaign, its approval status, or who approves it; returns a draft that is never shared.

## Human and side-effect gates

- Never book or release inventory, change a campaign, placement, or order, approve a recommendation, or share anything with an advertiser.
- Every decision stays with authorized ad sales leads and ad operations managers. Present drafts as drafts.
- Include only the evidence needed for the question.

## Evidence-first response contract

1. Lead with the specific figure, record, or draft status that answers the question.
2. Keep the agent's tables and figures exactly as returned; do not round or recompute.
3. State the recommended next step and who decides it.
4. Make the no-action boundary explicit; never speculate.
5. End substantive answers with: **Synthetic campaign delivery evidence only. No inventory was booked, no campaign was changed, and nothing was shared with an advertiser.**

## 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.

- `CDO-01` uses skill `campaign-risk`.
- `CDO-02` uses skill `available-reach`.
- `CDO-03` uses skill `approval-recommendation`.

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.

Enter the reviewed global instructions

Expected resultThe reviewed manual/GLOBAL-INSTRUCTIONS.md policy is visible or saved without unrecorded edits.

Positive visual checkpoint: Campaign Delivery Optimizer — Manual Global Inst. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Save the instruction policy

Step 4 of 16

Action

Save the instruction policy

Expected resultThe reviewed manual/GLOBAL-INSTRUCTIONS.md policy is visible or saved without unrecorded edits.

Positive visual checkpoint: Draft. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Remove default web search

Step 5 of 16

Action

Remove default web search

Expected resultThe captured inventory no longer lists the default web-search capability.

Positive visual checkpoint: Provide trusted context to guide decisions. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Add knowledge: aibast_campaign-delivery-optimizer-rules-and-guardrails.md

Step 6 of 16

Action

Add knowledge: aibast_campaign-delivery-optimizer-rules-and-guardrails.md

Expected 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.

Positive visual checkpoint: aibast_campaign-delivery-optimizer-rules-and-gua. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Add knowledge: aibast_campaign-delivery-optimizer-synthetic-records.md

Step 7 of 16

Action

Add knowledge: aibast_campaign-delivery-optimizer-synthetic-records.md

Positive visual checkpoint: aibast_campaign-delivery-optimizer-synthetic-rec. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Add skill: aibast_approval-recommendation_03

Step 8 of 16

Action

Add skill: aibast_approval-recommendation_03

Expected 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.

Positive visual checkpoint: approval-recommendation. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Add skill: aibast_available-reach_02

Step 9 of 16

Action

Add skill: aibast_available-reach_02

Positive visual checkpoint: available-reach. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Add skill: aibast_campaign-risk_01

Step 10 of 16

Action

Add skill: aibast_campaign-risk_01

Positive visual checkpoint: campaign-risk. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Review model, skills, knowledge, and safety boundaries

Step 11 of 16

Action

Review model, skills, knowledge, and safety boundaries

Expected resultThe screenshot visibly confirms Claude Opus 5.5, 3 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.

Positive visual checkpoint: Claude Opus 5.5; campaign-risk; available-reach; approval-recommendation; aibast_campaign-delivery-optimizer-synthetic-rec; aibast_campaign-delivery-optimizer-rules-and-gua. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Open a fresh Preview conversation

Step 12 of 16

Action

Open a fresh Preview conversation

Expected resultA fresh Preview surface or its recorded qualitative result is visible; only the evidence file defines a pass.

Positive visual checkpoint: Campaign Delivery Manual; New chat. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Pass CDO-01: Ad Operations Manager

Step 13 of 16

Action

Is the Harborlight Streaming campaign falling behind this week, and by how much?

Pass CDO-01: Ad Operations Manager

Expected resultThe captured Preview evidence records CDO-01 with the recorded identifiers Campaign Risk, 18% below plan, 235,000; do not infer results beyond it.

Before this case

Open Preview in a fresh conversation before running CDO-01. A previous response must not influence the evidence.

Pass CDO-01: Ad Operations Manager reviewed visual reference

Positive visual checkpoint: 18% below plan; 235,000; Campaign Risk. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Pass CDO-02: Campaign Manager

Step 14 of 16

Action

Where can we find extra reach this week to close the Harborlight gap?

Pass CDO-02: Campaign Manager

Expected resultThe captured Preview evidence records CDO-02 with the recorded identifiers Available Reach, Streaming Home Screen Takeover, 42,000; do not infer results beyond it.

Before this case

Open Preview in a fresh conversation before running CDO-02. A previous response must not influence the evidence.

Pass CDO-02: Campaign Manager reviewed visual reference

Positive visual checkpoint: Available Reach; Streaming Home Screen Takeover; 42,000. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Pass CDO-03: Ad Sales Lead

Step 15 of 16

Action

Draft the make-good for Harborlight so Maya can review it. Don't send anything to the advertiser yet.

Pass CDO-03: Ad Sales Lead

Expected resultThe captured Preview evidence records CDO-03 with the recorded identifiers Approval Recommendation, Pending sales lead approval, Draft only; do not infer results beyond it.

Before this case

Open Preview in a fresh conversation before running CDO-03. A previous response must not influence the evidence.

Pass CDO-03: Ad Sales Lead reviewed visual reference

Positive visual checkpoint: Draft only; Pending sales lead approval; Approval Recommendation. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Confirm Draft and stop before publish

Step 16 of 16

Action

Confirm Draft and stop before publish

Expected resultThe agent remains Draft and no Publish action is taken.

Positive visual checkpoint: Campaign Delivery Manual. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.

Manual-mode troubleshooting

A screenshot or browserfilm frame is missing

Stop. Do not invent, recreate, or substitute an image. Capture the real frame, update the browserfilm manifest, and regenerate without --allow-pending.

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 this manual duplicate in Draft unless publication is separately approved. Do not choose Publish as part of this tutorial.