Items, sources and citations
An item is the atom of a snapshot: one regulatory development, placed at one jurisdiction × area coordinate, described and classified. Everything the dashboard shows you is built from items — a heatmap cell is a stack of them, a timeline entry is one of them with a date, a briefing priority is a claim about several of them. This page covers what an item carries, and then the part that deserves the most careful reading: how the product tells you how well it knows what it is telling you.
The anatomy of an item
Open any item — from a heatmap cell, the timeline, or the map — and the detail card shows the same fields:
| Field | What it carries |
|---|---|
| Title | The development, named — usually the instrument or proposal itself |
| Jurisdiction · Regulator | Where it comes from, and which authority owns it |
| Area | The policy domain it is filed under (including your custom areas) |
| Status | Where the measure is in its lifecycle — see below |
| Likelihood | How firm the development is — see below |
| Impact | How much it matters — High · Medium · Low, angled by your entity type |
| Expected date | When it is expected to bite; items may also carry effective dates or compliance deadlines. Undated items show TBD rather than an invented date |
| Summary | A short editorial account, carrying citation numbers |
| Evidence chip and tally | What the item’s claims rest on — see below |
| Primary document ↗ | The primary regulator’s page that verified the most of the item’s claims, when there is one |
Two of these fields are ladders worth internalising, because the filter bar treats them as the primary lenses on every reading:
Status tracks a measure’s lifecycle: Proposed → Consultation → Final Rule → Implementation Phase → Effective. It answers “how far along is this?” — a Consultation wants a response; an Implementation Phase rule wants a project plan; an Effective rule is a live obligation.
Likelihood — Confirmed · Likely · Possible — answers a different question: “how certain is it that this lands as described?” A Confirmed item has a fixed footing (rules adopted, date set); a Possible item is direction-of-travel. Items for which no likelihood could be established are treated as Uncertain in the filters rather than being silently promoted. Status and likelihood are deliberately independent axes: a Proposed measure can be Confirmed-likely to proceed, and a Final Rule can still carry Possible timing.
Impact and likelihood combine in one visible place: the Overview heatmap. Each cell prints a pressure score out of 10 that weighs impact by likelihood, so a confirmed high-impact item heats a cell far more than a speculative one. The grid is a severity-times-certainty reading, not a raw item count — the count survives in the cell’s tooltip.
What each claim rests on
The Analyst chooses its own sources as it researches. After the briefing is written, a dedicated citation audit takes every cited sentence — in the executive narrative, the enforcement priorities and each item’s summary — splits it into its claims, and checks each factual claim against the pages the scan read or found in its searches. We do not ask the Analyst to rate its own sources; we report what the pages say.
1. The result of each claim
Each factual claim gets one of three results, and the sentence’s analysis gets a fourth label:
- Verified — a page states the claim. The popover quotes the page’s own words.
- Source located. Check wording — a page is about the claim but does not state all of it. Read the page before relying on the detail.
- No source found — none of the pages the scan read states or covers the claim. A result, not a failure.
- Analysis — the briefing’s own reading of the facts: what they mean, require or signal. Not checked against a page, by design.
The small number on a sentence opens all of this: each claim, its result, the quoted words and the page. A sentence with no sourced claim carries no number.
2. Who the page is — page tier
Every page carries a tier from our list of regulators, supranational bodies and their domains: Primary regulator, Supranational or Secondary. The tier describes the page, not the claim — a verified claim on a law firm’s write-up is still verified; the tier tells you whose words they are.
3. What the item rests on — evidence chip and Primary document
On the item, the two combine. The evidence chip names the strongest tier among the pages that verified one of its claims — Verified on primary regulator pages, Verified on supranational pages, Verified on secondary sources only, or Not verified. A page that only located a claim does not count. Beside it, a tally (5 claims · 4 verified · 1 located). And Primary document ↗ links the primary regulator’s page that verified the most of the item’s claims — or, when no primary regulator’s page verified one, the card says so rather than linking a page nothing was checked against.
The audit also reports its own coverage. A cited sentence it could not check keeps the Analyst’s own source, drawn with a dashed underline and a note. The status chip stays quiet for a small gap (Citation audit complete · 1 of 84 unchecked) and turns amber — Citation audit partial — when a whole section, or more than one cited sentence in ten, could not be checked. Neither means the scan failed, nor that any finding is incorrect.
The Sources tab totals all of this: how many claims are sourced across every surface, the share of verified claims resting on primary regulator pages, and — under Evidence for each claim — every page each item’s claims were checked on. Snapshots from before the evidence-based audit keep their earlier signals (a sourcing-confidence chip, a ✓/≈/? cross-reference badge and View source →), which are no longer produced for new scans.
Reading one item end to end
Take a concrete reading. An item titled after an EU fund-liquidity proposal shows Consultation status, Likely, High impact, expected 15-10-2026, a Verified on primary regulator pages chip and 4 claims · 3 verified · 1 located. Its summary’s second sentence carries a citation number; opening it shows the claim Verified with the regulator’s own words quoted from an esma.europa.eu page tagged Primary regulator, and a second claim Source located. Check wording on a law firm’s note. What you now know: the measure is mid-lifecycle with a response window; the analysis regards it as probably landing; three of its four claims are stated by pages the scan read, at least one of them the regulator’s own; and one detail needs a read of its page. What you still do not know — and what no result claims — is that the regulator’s page is itself complete or current. The audit narrows the trust gap; it does not close it.
The product ships with the same caution on every dashboard: AI-assisted analysis — always verify findings against primary sources before acting. The citation audit exists to make that verification fast — the citation numbers and Primary document ↗ take you straight to the documents — not to substitute for it.
Why items are built this way
The design bets on a specific failure mode: in regulatory work, a wrong-but-confident summary is worse than a hedged one. Hence the per-claim results (so one weak claim never hides behind an average), the honest absences (TBD dates, No source found, unchecked sentences marked as such), and the one-click path from any claim to its document. Items are also the substrate of change tracking — an item is bound to a tracked instrument, and it is instruments whose confirmed, dated events the Change Monitor reports between snapshots. Provenance discipline at the item level is what makes the change headline trustworthy one level up.
Where to go next
- The Sources tab — the trust surfaces in the product.
- What “changed” means — how item provenance becomes change evidence.
- Snapshots — the item fields on the wire for API callers.