Progress will remain available on this page, but it will not persist after you leave. Easy Mode remains available.
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.
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.
1
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.
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Deploy the reviewed solution as an unpublished Draft.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Do not publish.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
2
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 M&A Target Sourcing 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.
3
Prove the solution locally
Ask Easy Mode to build and test M&A Target Sourcing
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 M&A Target Sourcing using Easy Mode and test it for me.
Expected result
Copilot reports a verified source and 6/6 locked local cases passed.
Copilot should end by suggesting the next message: Deploy it into Copilot Studio for me.
4
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: M&A Target Sourcing Manual
Model: Claude Opus 5
Knowledge files: 2
Skills: 6
Status: Draft; published: false
The harness then validates the real Preview front door before returning its final verdict.
5
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.
Every case passes in a fresh Preview conversation, and the agent still appears as Draft.
MATS-01 · Corporate Development Associate
Confirm the expected evidence
We want to buy a profitable compliance-workflow software company in Europe within our revenue band. Turn that into a screen we can run.
Must include
TH-2026-0145 of 8 passCindral Risk Labs
Must not claim
I do not have accessI cannot help
Visible positive anchors: TH-2026-014; 5 of 8 pass; Cindral Risk Labs. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.
MATS-02 · Corporate Development Associate
Confirm the expected evidence
Run the screen and rank the companies that pass.
Must include
Lumenrock Compliance Systems85.779.8
Must not claim
I do not have accessI cannot help
Visible positive anchors: Lumenrock Compliance Systems; 85.7; 79.8. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.
MATS-03 · Corporate Development Associate
Confirm the expected evidence
Give me the dossier on the top-ranked target, with its sources and diligence questions.
Must include
T-01-S122.0% marginDiligence questions
Must not claim
I do not have accessI cannot help
Visible positive anchors: 22.0% margin; T-01-S1; Diligence questions. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.
MATS-04 · Head of Corporate Development
Confirm the expected evidence
Does the ranking hold if we weight financial quality more heavily?
Must include
Financial-first84.5top 3 holds under all 3 weightings
Must not claim
I do not have accessI cannot help
Visible positive anchors: top 3 holds under all 3 weightings; Financial-first; 84.5. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.
MATS-05 · Research Analyst
Confirm the expected evidence
Where is our evidence thin or out of date?
Must include
RR-016 evidence gaps across 4 targetsnone has been sent
Must not claim
I do not have accessI cannot help
Visible positive anchors: RR-01; 6 evidence gaps across 4 targets. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.
MATS-06 · Head of Corporate Development
Confirm the expected evidence
Draft the screening memo for the investment committee.
Must include
ICM-2026-07-01$149MNot sent; no target contacted
Must not claim
I do not have accessI cannot help
Visible positive anchors: ICM-2026-07-01; $149M; Not sent; no target contacted. The screenshot supports the learner checkpoint; the full case pass remains the deterministic machine gate. Source: 1424×863 JPEG. Download original.
6
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 proof6/6 locked cases passedPreview proof6/6 locked cases passedDraft identityM&A Target Sourcing ManualModelClaude Opus 5Inventory2 knowledge · 6 skillsPublication gateDraft · published false
The harness reports status: complete, exact case totals, the Draft identity, and published: false. The module ends here; it does not offer publication.
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 6/6
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.
See how M&A Target Sourcing 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.
Manual-mode progress is saved on this device and contributes to the same achievement profile.
Build and verify
1
Create a blank Copilot Studio agent
Step 1 of 24
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.
2
Name M&A Target Sourcing Manual
Step 2 of 24
Action
M&A Target Sourcing Manual
Name M&A Target Sourcing Manual
Expected resultThe page header shows the recorded manual build name: M&A Target Sourcing Manual.
Positive visual checkpoint: M&A Target Sourcing Manual. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
3
Enter the reviewed global instructions
Step 3 of 24
Action
# M&A Target Sourcing Agent — Manual Global Instructions
You are an acquisition-screening pilot for corporate development teams. Explain the fixed synthetic snapshot and prepare
reviewable drafts without turning decision support into a decision.
## Fixed synthetic snapshot
- Use only the uploaded M&A Target Sourcing synthetic records, rules, and 6
packaged skills.
- Fabrikam Information Services and every record in the snapshot (eight fictional companies, one acquisition thesis, scoring weights, evidence sources and the memo draft) are fictional and
used only for demonstration. All names, identifiers, dates and amounts are invented.
- Do not browse, consult external sources, or add market, legal, regulatory, or
current-date facts. Never invent a record, figure, owner, deadline, or result.
- Never match a fictional record to a real organization or person, or claim access
to a live system.
## Natural-language routing
- Use **thesis to screening criteria** when someone describes an acquisition thesis and wants it turned into screening criteria and filters.
- Use **ranked target longlist** when someone wants the screen run and the passing companies ranked with a transparent weighted score.
- Use **cited target dossier** when someone wants one target's profile, synthetic financials, criteria scores, sources and diligence questions.
- Use **weighting challenge** when someone asks whether the ranking holds under different weightings, such as weighting financial quality more heavily.
- Use **evidence-gap review** when someone asks where the evidence behind the targets is thin, missing or out of date.
- Use **investment committee memo draft** when someone asks for the investment committee screening memo draft for the shortlist.
## Human and side-effect gates
- Never contact a target or its advisers; update a CRM or deal record; share or send a document; make or imply an investment decision; present synthetic financials as real market data.
- The corporate development lead must approve criteria, evidence, the shortlist and any first contact.
- Present drafts as drafts and say that nothing was sent, submitted, or changed.
## Evidence-first response contract
1. Lead with the answer: the figure, record, table, or draft status that was asked for.
2. Keep the snapshot's identifiers, figures and tables exactly as recorded.
3. State the human review or approval needed next.
4. Make the synthetic and read-only limits explicit; never speculate.
5. End substantive answers with: **Synthetic screening support only. No target was contacted, no record was changed, and no investment decision was made.**
<!-- 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.
- `MATS-01` uses skill `build-thesis`.
- `MATS-02` uses skill `screen-targets`.
- `MATS-03` uses skill `target-dossier`.
- `MATS-04` uses skill `challenge-ranking`.
- `MATS-05` uses skill `evidence-gaps`.
- `MATS-06` uses skill `ic-memo-draft`.
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 -->
Enter the reviewed global instructions
Expected resultThe reviewed manual/GLOBAL-INSTRUCTIONS.md policy is visible or saved without unrecorded edits.
Positive visual checkpoint: M&A Target Sourcing Agent — Manual Global Instru. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
4
Save the instruction policy
Step 4 of 24
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.
5
Remove default web search
Step 5 of 24
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.
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_ma-target-sourcing-rules-and-guardrails.m. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
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_ma-target-sourcing-synthetic-records.md. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
8
Add skill: aibast_build-thesis_01
Step 8 of 24
Action
Add skill: aibast_build-thesis_01
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: build-thesis. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
9
Add skill: aibast_challenge-ranking_04
Step 9 of 24
Action
Add skill: aibast_challenge-ranking_04
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: challenge-ranking. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
10
Add skill: aibast_evidence-gaps_05
Step 10 of 24
Action
Add skill: aibast_evidence-gaps_05
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: evidence-gaps. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
11
Add skill: aibast_ic-memo-draft_06
Step 11 of 24
Action
Add skill: aibast_ic-memo-draft_06
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: ic-memo-draft. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
12
Add skill: aibast_screen-targets_02
Step 12 of 24
Action
Add skill: aibast_screen-targets_02
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: screen-targets. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
13
Add skill: aibast_target-dossier_03
Step 13 of 24
Action
Add skill: aibast_target-dossier_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: target-dossier. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
14
Review model, skills, knowledge, and safety boundaries
Step 14 of 24
Action
Review model, skills, knowledge, and safety boundaries
Expected resultThe screenshot visibly confirms Claude Opus 5, 6 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Positive visual checkpoint: Claude Opus 5; target-dossier; screen-targets; ic-memo-draft; evidence-gaps; challenge-ranking; aibast_ma-target-sourcing-synthetic-records.md; aibast_ma-target-sourcing-rules-and-guardrails.m. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
15
Review the skill list (6 skills)
Step 15 of 24
Action
Review the skill list (6 skills)
Expected resultThe screenshot visibly confirms Claude Opus 5, 6 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Positive visual checkpoint: target-dossier; screen-targets; ic-memo-draft; evidence-gaps. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
16
Review the rest of the skill list
Step 16 of 24
Action
Review the rest of the skill list
Expected resultThe screenshot visibly confirms Claude Opus 5, 6 rendered skills, and no tools. Knowledge is verified separately in the two knowledge-upload checkpoints.
Positive visual checkpoint: screen-targets; ic-memo-draft; evidence-gaps; challenge-ranking; build-thesis. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
17
Open a fresh Preview conversation
Step 17 of 24
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: M&A Target Sourcing Manual. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
18
Pass MATS-01: Corporate Development Associate
Step 18 of 24
Action
We want to buy a profitable compliance-workflow software company in Europe within our revenue band. Turn that into a screen we can run.
Pass MATS-01: Corporate Development Associate
Expected resultThe captured Preview evidence records MATS-01 with the recorded identifiers TH-2026-014, 5 of 8 pass, Cindral Risk Labs; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running MATS-01. A previous response must not influence the evidence.
Positive visual checkpoint: TH-2026-014; 5 of 8 pass; Cindral Risk Labs. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
19
Pass MATS-02: Corporate Development Associate
Step 19 of 24
Action
Run the screen and rank the companies that pass.
Pass MATS-02: Corporate Development Associate
Expected resultThe captured Preview evidence records MATS-02 with the recorded identifiers Lumenrock Compliance Systems, 85.7, 79.8; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running MATS-02. A previous response must not influence the evidence.
Positive visual checkpoint: Lumenrock Compliance Systems; 85.7; 79.8. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
20
Pass MATS-03: Corporate Development Associate
Step 20 of 24
Action
Give me the dossier on the top-ranked target, with its sources and diligence questions.
Pass MATS-03: Corporate Development Associate
Expected resultThe captured Preview evidence records MATS-03 with the recorded identifiers T-01-S1, 22.0% margin, Diligence questions; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running MATS-03. A previous response must not influence the evidence.
Positive visual checkpoint: 22.0% margin; T-01-S1; Diligence questions. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
21
Pass MATS-04: Head of Corporate Development
Step 21 of 24
Action
Does the ranking hold if we weight financial quality more heavily?
Pass MATS-04: Head of Corporate Development
Expected resultThe captured Preview evidence records MATS-04 with the recorded identifiers Financial-first, 84.5, top 3 holds under all 3 weightings; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running MATS-04. A previous response must not influence the evidence.
Positive visual checkpoint: top 3 holds under all 3 weightings; Financial-first; 84.5. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
22
Pass MATS-05: Research Analyst
Step 22 of 24
Action
Where is our evidence thin or out of date?
Pass MATS-05: Research Analyst
Expected resultThe captured Preview evidence records MATS-05 with the recorded identifiers RR-01, 6 evidence gaps across 4 targets, none has been sent; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running MATS-05. A previous response must not influence the evidence.
Positive visual checkpoint: 6 evidence gaps across 4 targets; RR-01. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
23
Pass MATS-06: Head of Corporate Development
Step 23 of 24
Action
Draft the screening memo for the investment committee.
Pass MATS-06: Head of Corporate Development
Expected resultThe captured Preview evidence records MATS-06 with the recorded identifiers ICM-2026-07-01, $149M, Not sent; no target contacted; do not infer results beyond it.
Before this case
Open Preview in a fresh conversation before running MATS-06. A previous response must not influence the evidence.
Positive visual checkpoint: ICM-2026-07-01; $149M; Not sent; no target contacted. Source capture: 1424×863 JPEG. The full pass remains the deterministic machine gate. Download original.
24
Confirm Draft and stop before publish
Step 24 of 24
Action
Confirm Draft and stop before publish
Expected resultThe agent remains Draft and no Publish action is taken.
Positive visual checkpoint: M&A Target Sourcing 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.