The problem
The service lives in twenty documents and five organisations.
Nobody agrees what good looks like, so debates go round in circles.
Blueprints take weeks, and the gaps are hidden.
04
Your service, mapped and scored against what good looks like.
Service Designer turns policies, process maps and call scripts into a blueprint, journey and flow, then scores the service against Lou Downe's 15 principles of good service.
Or get all nine agents in the UCD Team bundle.
The service lives in twenty documents and five organisations.
Nobody agrees what good looks like, so debates go round in circles.
Blueprints take weeks, and the gaps are hidden.
Extracts actors, channels, touchpoints and backstage steps with sources
Drafts an ecosystem map, service blueprint, journey map and service flow
Scores all 15 good-service principles on a 0–4 scale, with evidence
Names a fix and an owner for every weak principle
Builds boards in Miro, Mural or FigJam after your yes
Get this on Gumroad and download the zip.
Unzip it into a project folder and open it in your AI tool.
Say `map the service in <documents or description>`.
It works one stage at a time and stops for your yes.
Stakeholder and touchpoint extraction
Ecosystem map, Service blueprint, Journey map and service flow
Good service scorecard, Canvas write
Lou Downe's 15 principles of good service, scored 0–4.
Every claim cites its source. Nothing is written to your tools without your approval.
Service owners, delivery managers and product owners who have lots of documents and no service designer to hand.
An AI tool that reads project instructions: Claude Code, Cursor, or a tool that reads AGENTS.md. Claude Projects and custom bots work too, with copy-and-paste outputs.
Your own AI subscription or API key. Nothing to host.
Optional connections: Miro MCP, Mural MCP, FigJam via Figma MCP.
| File | What it does |
|---|---|
00-root-instructions.md | Who the agent is, the rules, the gates |
01-extract.md | Stage 1: Extract |
02-map.md | Stage 2: Map |
03-score.md | Stage 3: Score |
04-tools.md | Connections and permissions |
05-manifest.md | Which skill uses which tool |
06-adapters.md | How to load it in your tool |
LICENCE.md | What you may and may not do |
README.md | Start here: set-up in two minutes |
guardrails.md | Risks, controls and sign-off |
memory.md | What is kept and where |
adapters/AGENTS.md | Adapter for your AI tool |
adapters/CLAUDE.md | Adapter for your AI tool |
adapters/chat-system-prompt.md | Adapter for your AI tool |
adapters/service-designer.mdc | Adapter for your AI tool |
evals/eval-suite.md | Tests and pass marks |
rules/good-services-15.md | Standard the agent checks against |
samples/01-carers-allowance.md | Synthetic sample input |
samples/02-licence-70.md | Synthetic sample input |
samples/03-school-place.md | Synthetic sample input |
Designed before it was built
This agent was designed with the five-question method: purpose, boundaries, what it touches, when a person steps in, and how you know it works. [Read the design](./anatomy).
Designed by Vijay Kandhalu.