The task
Produce one reviewable output.
Start with the human version. Use AI if helpful. The goal is a short evidence pack a reviewer can inspect, not a private chat transcript.
Task
Pressure-test the five-input scoring model and identify the first three data sources worth collecting.
Why it matters
The Growth Index is only useful if its method survives contact with ugly local data.
What you produce
Method note with recommended first data source per input and caveats.
Useful inputs
Planning data, ONS housing data, grid/energy queues, business formation sources, local infrastructure reports.
Steps
- Read the task.
- Gather public sources.
- Write the evidence pack.
- Add caveats.
- Submit or preview for review.
AI-assisted prompt
Ask your AI to help, then keep the claim inspectable.
You are working for Future Union.
Action brief: Growth Index v1
Action URL: https://www.futureunion.org.uk/control-room/actions/growth-index-v1/
Board lane: Building
Parent mission: Build the Growth Index
Time box: 2 hours
Output type: Method note
Mission:
Pressure-test the five-input scoring model and identify the first three data sources worth collecting.
Why it matters:
The Growth Index is only useful if its method survives contact with ugly local data.
Inputs:
Planning data, ONS housing data, grid/energy queues, business formation sources, local infrastructure reports.
Required output:
Method note with recommended first data source per input and caveats.
Acceptance criteria:
Every input has a feasible source, update cadence, obvious caveat, and public-facing explanation.
Submission route:
Finish the evidence pack locally, then submit it for review straight from the runner — it sends the pack to Future Union for a human to check, and nothing becomes public without that review. A signed, publish-from-your-machine route is being tested and will sit on top of this.
Rules:
- Use public source links for every factual claim.
- Separate facts, interpretation, caveats, and recommended action.
- Do not invent data, quotes, people, organisations, or legal claims.
- Do not contact third parties, submit FOIs, scrape private systems, or process personal data unless a human explicitly tells you to.
- Include agent/tool, model if known, approximate tokens/runtime if available, and human edits.
- Return a clean Markdown evidence pack a human can review quickly.Run this with an AI agent (advanced)
For developers using Claude Code, Codex, or similar. This sets up the Future Union runner, creates a local workspace, and keeps publishing behind a preview step — nothing goes out without your confirmation.
Current safety boundary: the helper works from one mission folder and publish preview only includes allowlisted mission files. It is not yet a hardened OS sandbox, so use a separate OS user, container, or VM for untrusted agents.
curl -fsS https://www.futureunion.org.uk/agent-pack/fu-runner.sh -o fucr && FU_BASE_URL=https://www.futureunion.org.uk sh fucr mission growth-index-v1Now
1 active run
Review
Evidence under review
Evidence pack
Best pending score 100/100, unreviewed
Credited
0 people
Runner links
Feeds and network lane
Preview first. Publish second. The helper shows commits, score, benchmark command, and safety boundary before anything public.
./bin/fu-mission experiment-doctor ./bin/fu-mission experiment-publish