Volume vs Breadth Signaling
Clustering and deduplication for high-volume submissions
Submissions are grouped by similarity so a reviewer reads each distinct argument once, with nothing removed from the record.
The console surfaces arguments for a person to weigh. It never scores, ranks for decision, or drops a submission. A three-submission cluster with new data can outweigh a 1,842-submission template; that judgment stays human.
Provenance and attribution for mass submissions
A campaign appears on the record as one attributed entry with its size and organizer disclosed, rather than as thousands of separate-looking submissions.
The record shows what it can verify: size, organizer, and route. It also states what it cannot verify. No entry is labeled machine-written, because that call cannot be made reliably.
Opinion mapping by consensus and clustering
Statements are ranked by how widely they are shared across groups, so a position that bridges divides outranks one a single faction repeats.
This statement has support across all three clusters.
The map structures deliberation among clusters rather than ranking statements for a decision. Its job is to answer “how widely is this shared?” — a question raw vote counts cannot answer.
Weighting distinct voices
Raw submissions, distinct arguments, and verified distinct submitters are reported together, so breadth reads as independent sources rather than as volume.
Breadth means distinct positions from independent sources. 4,213 submissions making 27 arguments from 1,388 people is a legible fact here. Presented as one number, it would have read as a city in near-total opposition.
Submitter nudges on template matches
A submitter using a campaign template is told, without being blocked, that their own experience adds weight.
Your submission on the foreshore plan
This matches a template shared by a campaign. Adding a detail from your own experience is optional.
The submit action never moves, dims, or gains steps because a template was detected: the nudge only adds information for the submitter to weigh.
Alternative weighting mechanisms
Concentrating votes on a single position costs more the further it goes, and the screen shows how the final weighting is computed.
Each extra vote on the same option costs more: 1 credit for one vote, 4 for two, 9 for three, 16 for four. Spending more on one option records stronger support for it. Your votes are counted exactly as cast, with no adjustment afterward.
Costs rise with the square of the votes (1 credit, then 4, then 9), so a participant can back one thing strongly or several things weakly, never everything strongly. The running cost of the next vote is shown on each row, because a participant who can’t see how they are counted is being asked to take the result on trust.
Submission processing that resists prompt injection
Submissions are treated as data the agent may read but never obey, with a person owning every consequential step.
The embedded instruction had no effect. The submission still counts, and a person decides how to treat it.
Prompt injection can’t be fully filtered, so the pipeline limits the damage instead: untrusted data, no agent authority, a human on the consequential step, and a log. A flag routes a submission to a person, never out of the record — unusual phrasing from a second-language writer trips the same signal.
Verified agent admission
A signed request is admitted with its operator named, and an unverifiable one is routed to a path held at parity rather than turned away.
A public, read-only endpoint asks nothing extra of either route, and both draw the same rate limit. The bar rises only where the stakes do.
Declared agent welcome
The channel itself states what agent traffic is welcome and for what purposes, in plain language and in a form an agent can read.
Agent access policy
AP-2026-014City Digital Services’s statement of what software agents may do on this channel. Readable by people and by agents.
Any agent may read the public pages here.
An agent may lodge on a person’s behalf; the admission check confirms whose agent is asking. A submission that arrives outside these preferences is still a submission, and is still considered.
Content on this channel is not offered for model training.
What this page says is what the channel enforces. Blocks are logged and reviewed against this policy.
The declaration states the channel’s policy and confirms nothing about which agent sent a request — that check belongs to admission, the paired surface. Publishing it takes back a policy surface otherwise exercised by edge-infrastructure defaults.
No surfaces match this filter.