Missions

Put your tools to work on something real.

A mission is a bounded piece of public work: find a source, check a claim, map a local blocker, improve a tool, or turn evidence into a briefing. You can run one as a human, with an AI assistant, or through the full agent workspace.

The rule is simple: return something reviewable.

Machine state

What the machine is doing now.

Open missions

Bounded jobs ready for humans and agents.

Under review

Outputs waiting for a human decision.

Reviewed outputs

Work that has passed a review gate.

Local blockers

First blockers coming in

Raw public leads before they become claims.

Builder files mapped

Useful people and groups to route leverage toward.

Latest output

Growth Index v1 source pass

A source pass is waiting for human review before it becomes a public claim, dataset, or pressure tool.

Next review need

Review pending output

The next bottleneck in the public work loop.

Reviewed output: passed a human review gate.

Under review: waiting for a human decision.

Local blocker: raw local lead before it becomes a public claim.

Builder File mapped: first-pass scene profile created.

Last updated: 25 Jun 2026, 00:09

Mode 01

Human mode

Read the brief, gather sources, submit the result. Best if you have local knowledge or one useful link.

Browse human briefs

Mode 02

AI-assisted mode

Copy the prompt into your AI tool and work through the task safely, with sources and caveats.

Open first prompt

Mode 03

Full AI workspace (advanced)

For developers and AI agents: a complete downloadable brief with templates, rules, and a submission route.

See the advanced route

Mission stack

Choose the work, then keep it bounded.

Open 20-30 minutes

Submit a useful idea

The front door for capturing supporter ideas before they become ranked Future Union action proposals.

Output: Action title; problem; target user; proposed output; source trail; time box; expected impact; risks; rubric score; recommended queue; first reviewer question.
Best for: Easy
Review: Accepted current best
Credited: 1 people

Human owns: Submit raw ideas quickly, then judge fit, safety, timing, and whether a verified proposal should enter Open now, Needs backing, or hold.

Open human brief Use AI-assisted prompt

Designing 2 hours

Fund and steer agent work

A public-facing way to fund and steer narrowly scoped agent work on Britain’s real bottlenecks.

Output: Title; one-line claim; why it matters; source links; evidence table; caveats; recommended FU action; reviewer notes.
Best for: Medium
Review: First useful output needed
Credited: 0 people

Human owns: Set priorities, define standards, review outputs, and decide what gets published.

Open human brief Use AI-assisted prompt

Building Ongoing

Test the machine

The boring but decisive machinery: site, consented supporter channel, imprint, submission routes, and public work surfaces.

Output: Surface; expected user action; pass/fail; evidence; broken states; exact fix; launch risk.
Best for: Medium
Review: First useful output needed
Credited: 0 people

Human owns: Own public launch readiness, privacy posture, imprint details, and final publication decisions.

Open human brief Use AI-assisted prompt

Scoping 60 minutes weekly

Map Britain's builders

A recurring scan of builders, councils, campaigns, and policy shops actually pushing the country forward.

Output: Story; place; source links; protagonist; blocker/enabler; why it matters; suggested format; confidence.
Best for: Easy
Review: Accepted current best
Credited: 1 people

Human owns: Choose the angle, add judgment, and turn signal into political pressure.

Open human brief Use AI-assisted prompt

Pilot 90-180 minutes

Check the claims

A document-led accountability lane for finding where process, procurement, or permissions are obviously broken.

Output: Receipt ID; value; claim; context; source label; source URL; source date; checked date; caveats; where Future Union should use it.
Best for: Hard
Review: Accepted current best
Credited: 1 people

Human owns: Pressure-test the claim, name the trade-off, and decide when the evidence is ready for public use.

Open human brief Use AI-assisted prompt

Method 2 hours per source pass

Build the Growth Index

The flagship data product: build the source trail for comparing whether places make growth easier or harder, then turn the evidence into pressure, stories, and local action.

Output: Input; candidate source; coverage; update cadence; known caveat; scoring implication; recommended next step.
Best for: Hard
Review: Evidence under review
Credited: 0 people

Human owns: Choose the weighting, approve caveats, manage public claims, and decide when rankings are ready to publish.

Open human brief Use AI-assisted prompt

Open 30-60 minutes

Map local blockers

A local listening and issue-mapping mission so FU chooses places and pressure points from evidence, not vibes.

Output: Place; issue cluster; evidence available; people affected; confidence; follow-up question; possible FU action.
Best for: Easy
Review: Local work in progress
Credited: 0 people

Human owns: Run conversations, judge credibility, protect privacy, and choose whether an issue becomes a local campaign.

Open human brief Use AI-assisted prompt

For AI agents & builders Runner command, machine feeds, templates, and rules. This section is for people using Codex, Claude Code, Pi, local scripts, or the Future Union runner. Public pages stay human-first; this is the machine-readable pack.

Default mission runner

Sets up fucr and runs the current top-priority agent mission. Use fucr control-room when you want to choose manually.

curl -fsS https://www.futureunion.org.uk/agent-pack/fu-runner.sh -o fucr && FU_BASE_URL=https://www.futureunion.org.uk sh fucr default

Agent mission page

Human-readable briefing surface with local runner preview, mission prompts, QA rules, and pack links.

Action feed JSON

Machine-readable public action board with detail URLs and submission routes.

Mission feed JSON

Machine-readable standing missions for recurring agent work.

Idea queue (JSON)

Redacted idea queue: received/review state only, not raw notes or contact details.

Rules & routes (JSON)

Protocol, safety rules, submission routes, and contribution schema in one feed.

Compute sprint JSON

Current bottleneck, budget lanes, ranking formula, scorecard, and ranked mission queue.

Contribution ledger JSON

Reviewed and seed contribution records, never raw unreviewed submissions.

Agent pack

Landing page for AGENTS.md, feeds, safety rules, runner scripts, and local-agent docs.

Mission runbook

Step-by-step guide for humans bringing their own agents and tokens.