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.
Download the starter (.zip)
contoso-financial/ · 32 files · as of July 6, 2026
-
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
-
Put it under version control:
git init && git add -A && git commit -m "engagement starter" -
Replace the placeholder org URL in
.vscode/mcp.json— the Dataverse server does nothing until you do. -
In chat, run
/new-engagementto personalize the instruction files for a real customer.
Prefer single files? Every file in the tree below has copy and download buttons.
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.