The config pack

This is the payload: every file the harness ships, as one downloadable starter repo or file by file, verbatim. These are inert text — placeholders are marked, and the org URL in the MCP config must be replaced before anything acts.

Get the pack

Download the starter (.zip)

contoso-financial/ · 32 files · as of July 6, 2026

  1. Unzip and open the folder.

    Windows: Expand-Archive demo-harness-starter.zip; code contoso-financial

    macOS/Linux: unzip demo-harness-starter.zip && code contoso-financial

  2. Put it under version control: git init && git add -A && git commit -m "engagement starter"
  3. Replace the placeholder org URL in .vscode/mcp.json — the Dataverse server does nothing until you do.
  4. In chat, run /new-engagement to personalize the instruction files for a real customer.

Prefer single files? Every file in the tree below has copy and download buttons.

contoso-financial/.github/copilot-instructions.md

The engagement constitution — always-on instructions.

# The Demo Harness — drewbreyer.com/harness — starter file, as of 2026-07-06

# Contoso Financial — engagement instructions (always on)

You are working inside a single customer engagement repo. Your job is to help
produce a pipeline of artifacts — account research, discovery findings, a data
model, sample data, demo agents, a rehearsed script, and a leave-behind — for a
Dynamics 365 / Copilot Studio demo. Read the numbered folders in order.

## The artifact pipeline
00-intake -> 01-research -> 02-discovery -> 03-model -> 04-data -> 05-agents ->
06-rehearsal -> 07-leave-behind. Each folder is the input to the next. Do not
skip ahead; a later artifact that does not trace to an earlier one is a bug.

## Citation discipline
Every claim in a research artifact carries a source URL. Prefer primary sources.
Flag anything single-sourced. If a claim cannot be sourced, soften it to
pattern-generic language or drop it. No uncited claims ship.

## Fiction / real boundary
Contoso Financial is a fictional demo subject. Customer data of record never
enters this repo. Only public research, your own notes, and fiction-safe
summaries live here. The system of record keeps the rest.

## Tool separation
Agents are scoped on purpose. Research agents may read the web and Learn; they
may not write to any environment. Only the operator loads or queries the
Dataverse environment. The fabricator writes data files but never loads them.
Respect the scope declared in each agent file; do not widen it.

## Determinism
Anything generated — sample data above all — is seeded. Same seed, same output.
The environment must be rebuildable from the spec in an afternoon.

## Tone for customer-facing artifacts
Plain and precise. No superlatives, no "powerful" or "seamless", no exclamation
marks. Name preview features as previews. Say what a thing does, then stop.