Advisors
Weekly report
A dated report for each week, built from your own numbers with no model in the loop, readable on screen, by email, and on paper.

What this is
Weekly report is a dated report built
once a week for every project it runs for: one hero number, the prompts that
moved, where you stand against competitors, and a short list of what to do
next, assembled automatically rather than something you have to go generate
yourself (api/services/weekly_report.py#generate_weekly_report). It is
gated on your plan; see Pricing. A project on a plan the report is not
included in sees a locked screen instead, with no report and no history to
browse (api/routers/insights.py#get_latest_insight).
No model in the loop
The generator never calls a language model, and the report it stores
names no model (api/services/weekly_report.py#generate_weekly_report).
The scorecard, the engine and competitor rows and the prompts that moved
all come from one reader, api/services/weekly_readings.py#read_week,
which reads each metric with the Explorer's own definitions for the
report's week and the week before
(api/services/explorer/compare.py#compare), so those figures count
answers the way the Explorer does. The AI referral
traffic and Search Console sections come from those features' own readers
(api/services/weekly_report.py#_assemble_revenue, #_assemble_quick_wins).
Plain Python then formats the results: build_headline writes the
one-sentence summary, and the email's tiles show the same figures, both to
one decimal with a trailing ".0" dropped ("rose 0.4 points to 23.4%", "rose
1 point to 61%"), the precision the report's hero shows
(api/services/weekly_report.py#build_headline, #_pct).
An engine counts as measured in a week only when it ran (an answer, or a
Google run that showed no AI answer) on at least 80% of the week's answered
days, the days on which any engine has an answer (6 of 7 when every day was
answered) (api/services/collection_health.py#WINDOW_PRESENCE_MIN_PERCENT). When some engine that answered in either
week was not measured in both (the Google engines, ChatGPT or Gemini
(app) in the week after launch, or an engine switched off during the week),
the scorecard's changes, the prompts that gained or slipped and each
brand's change, and so the competitors that surged, are compared over the
engines measured in both weeks only, while each value itself still counts
every engine (api/services/collection_health.py#engine_windows,
api/services/explorer/compare.py#compare). An engine's own row compares
that engine with itself, so it needs no such rule
(api/services/weekly_readings.py#engine_rows). A summary that reports a
brand visibility change adds "Change compares engines measured in both
weeks." (a summary with no visibility comparison does not, even when its
prompt or competitor counts compare only the shared engines; a week where
visibility held steady still counts as a comparison and gets the note)
(api/services/weekly_report.py#build_headline).
The week, and when it runs
A report's week is always the last complete Monday-to-Sunday week in UTC:
week_start is a Monday and week_end is six days later, the Sunday before
the run (api/services/weekly_report.py#week_bounds). The week is chosen by
snapping back to that Monday, not by counting seven days back from the run
date, so a run delayed past its Monday still produces the week the on-time
run would have produced rather than a shifted seven-day window. The
scorecard, the engine and competitor rows and the prompts that moved
measure that same week against the week just before it
(api/services/weekly_readings.py#read_week,
api/services/explorer/compare.py#window_pair), and so does the AI
referral traffic (api/services/weekly_report.py#_assemble_revenue). The
Search Console queries are the exception: they cover the seven days up to
the day the report is generated
(api/routers/integrations.py#gsc_search_performance).
There is exactly one path that builds a report: a systemd timer fires every
Monday at 06:30 UTC, which enqueues one generation job for every paid,
active project without a report for that week yet, and each job runs the
generator for its one project
(discoveredby-cli@enqueue-weekly-report.timer,
api/tasks.py#_enqueue_weekly_report_for_eligible_projects,
#generate_weekly_report_task). There is no on-demand trigger: nothing in
the app, and nothing in the internal admin panel, builds a report outside
that weekly run. A project with no completed answer inside that week is
skipped rather than shown an empty or partial week
(api/services/weekly_report.py#_enough_data,
api/services/weekly_readings.py#has_answers).
What's on the screen
The hero is brand visibility when the report carries a real reading for it,
and falls back to citation rate otherwise, each with its own one-line
definition and a note of how it moved from the week before
(frontend/src/routes/(app)/insights/+page.svelte#heroValue). Beneath it
sits a tile for each of the report's other readings, named for what that
report measured, and one for prompts tracked; the hero's own reading is
not repeated (frontend/src/routes/(app)/insights/+page.svelte#tiles,
frontend/src/lib/insights.js#scorecardTiles). A current report's
readings are Brand visibility, Share of voice, Position, Citation rate and
Citation share, so with brand visibility as the hero its tiles are Share of
voice, Position, Citation rate and Citation share. An older report, written
before the report read its numbers through the Explorer, has Brand
visibility, Citation rate, Share of all citations and Avg citation
position; the last two are named for what those reports counted, your
share of every citation the engines recorded and where your best citation
landed in a typical answer (api/services/weekly_report.py#scorecard_readings).
A change is in points, except a position's, which reads as positions
better or worse, because a lower position is better. A tile with no change to
show carries its one-line definition instead
(frontend/src/lib/components/Stat.svelte#moved), unless it is empty and
has a note of its own: an empty Position tile says "Your brand was not
named this week." only when brand visibility measured exactly 0, and an
empty Avg citation position tile says none of your pages were quoted that
week
(frontend/src/lib/insights.js#tileEmptyNote).
Whether a reading counts as measured depends on which generator wrote the
report. Reports written from 2026-09-19 record a reading with no data
behind it as empty, so a 0% on one of them is a real measurement of
zero. Older reports stored that same "no data" case as zero, which is
indistinguishable from a measured zero, so a reading there is only trusted
when the value, the previous week or the change is nonzero; otherwise the
tile reads – and the hero says the week was not measured. This is why an
older report can omit brand visibility entirely. One rule covers this
screen, the printable page, the weekly email and shared client links, so
they cannot disagree about the same week
(api/services/weekly_report.py#METRICS_VERSION, #reading_is_measured,
frontend/src/lib/insights.js#readingValue).
A change is left blank rather than shown as 0 when there is no comparable
week before it, since a zero there would claim the metric held steady
against a week that was never measured
(api/services/explorer/compare.py#Reading, #change).
A "Do this next" checklist holds the five highest-impact citation gap
opportunities on file for your project
(api/services/weekly_report.py#select_recommendations). Each item's prompt
chips show the prompt's current text, read from the project when the report
is opened, so a report written before the chips carried text gets it too; a
prompt that has since been removed reads "Prompt no longer in this project"
and does not link (api/routers/insights.py#_prompt_labels). Editors and company members
can check one off as done; a viewer sees each check circle disabled, with a
role notice above the list explaining why, rather than a click that would
be rejected
(api/routers/insights.py#toggle_recommendation,
frontend/src/routes/(app)/insights/+page.svelte#writable). What gets checked off
carries forward: next week's report shows how many of that list got done
(api/services/weekly_report.py#progress_from_prior). Further down: the
prompts that gained or lost ground
(frontend/src/routes/(app)/insights/+page.svelte#rising, #declining),
how you compare engine by engine and against your tracked competitors, each
with its own message when there is nothing to compare yet
(#engines, #hasEngineData, #competitors).
The prompts that moved are the ones whose brand visibility changed most
from the week before, at most five in all, split into gaining and losing
ground. A prompt is compared only when it has a reading in both weeks, so a
prompt that did not run in one of them is not a mover, and a change of
exactly zero is left out (api/services/weekly_readings.py#movers). Each
names the engine on which that prompt's visibility was highest that week,
when any engine named you (api/services/weekly_readings.py#_best_engines).
In an older report the prompts that moved were citation-rate changes, and
the screen labels them so (frontend/src/lib/insights.js#moverLabels).
An engine's row shows its brand visibility that week, with how often its
answers linked to you beside it (under it on a phone); an engine's
collection channels are pooled into one row, the way the filter bar's
engine filter pools them
(api/services/weekly_readings.py#engine_rows,
frontend/src/lib/insights.js#engineRows). An engine that completed none
of your prompts that week is left out rather than shown at zero (a Google
engine that showed no AI answer on any run that week included, since a run
with no AI answer is not a completed answer). An engine whose answers were
not analysed for brand names has no visibility reading: it shows – and
no bar, rather than 0%. When no engine's visibility could be read, the
section says brand names were not analysed yet, and still draws every
engine's row when any engine linked to you, so no citation rate is hidden;
it says no engine picked you up only when every engine's visibility was a
measured 0 and none linked to you; and a week
where no engine ran says that no answers were collected
(frontend/src/lib/insights.js#engineView). An engine's week-over-week
change is shown only when that engine also has a reading the week before
(api/services/weekly_readings.py#engine_rows).
An older report's engine rows are citation rates, not visibility, and the
section's caption says which it shows (frontend/src/lib/insights.js#engineRows).
The oldest reports, generated before an engine that did not run was left
out, stored a row for every engine, at 0% when it did not run, and could measure a
change from that 0%, so on such a report a 0% row cannot be told apart from
an engine that never ran and no engine change can be trusted. The screen
and the printable page therefore leave out those reports' 0% engine rows,
the screen shows none of their engine changes, and both say why in a
one-line note (api/services/weekly_report.py#METRICS_VERSION,
frontend/src/lib/insights.js#engineRows). Those reports also used a
different per-engine definition: they divided only by the days your domain
was cited, where the citation-rate reports after them divided by every day
the engine ran. A drop from one of them to a later week can therefore be
the definition changing rather than a real fall, and the same note says so.
Against competitors lists you and every active tracked competitor by brand
visibility, each with its change, and beneath each its share of voice and
Citation share when either was measured
(api/services/weekly_readings.py#brand_rows,
frontend/src/lib/insights.js#brandRows). It appears when the report
holds a tracked competitor, and otherwise invites you to add one
(frontend/src/routes/(app)/insights/+page.svelte#rivalsTracked). A
brand's change is left blank when it has no reading the week before, and
such a competitor is not counted as surging in the headline, which counts a
competitor as surging when its visibility rose at least 5 points
(api/services/weekly_report.py#generate_weekly_report, #SURGE_THRESHOLD).
In an older report the bars are citation rates, yours counted over answers
and each competitor's over prompt runs, and a note under them says the bars
are not strictly comparable (frontend/src/lib/insights.js#brandRows).
Then, only when there is something to show, AI
referral traffic from Google Analytics
(frontend/src/routes/(app)/insights/+page.svelte#revenue),
striking-distance Search Console queries (#quickWins), a sentiment
breakdown (#sentiment, #hasSentiment), and a receipt of articles
published, pages optimized, and prompts added that week
(#receipt, #shipped).
The AI referral traffic section shows sessions, conversions and conversion
value, the value in the currency your GA4 property reports and with no
currency symbol when that is unknown. A report records a change in any of
the three only when Google Analytics imported data for each of the two
weeks, the report's week and the one before it, on at least 80% as many days
as for the other, the rule AI traffic and Site traffic use
(api/services/integrations/google/gsc_search_metrics.py#is_comparable).
Otherwise it records no change and says there are no weekly changes, rather
than showing an import gap as a gain or a fall
(api/services/weekly_report.py#revenue_band).
Reports generated before this rule show no change in conversion value, a
change in sessions or conversions only when they stored a week before with
traffic in it, and the value with no currency symbol
(frontend/src/lib/insights.js#revenueReadings). In the Search Console
section, a click-through rate or position Search Console did not report reads
"CTR unknown" or "position unknown", never 0%
(frontend/src/lib/insights.js#reportQuickWins).
If the report cannot be loaded, the screen shows an error with Retry rather than saying the first report has not arrived yet.
Screen, email, and paper
The same report reaches you three ways. On screen, at the Weekly report
page linked above. By email, sent the moment a report first finishes
generating, to each active member of the project's company, when the
project's email preferences and the company's weekly-report entitlement
allow it,
built from the same stored numbers and summary sentence
(api/tasks.py#_email_weekly_report,
api/services/email.py#send_weekly_report_email). And on paper: a
"Printable" link opens a second page built for print, reading the same
stored numbers and hiding the app's own navigation chrome behind a print
stylesheet. It is a one-page digest rather than the whole screen: the hero,
which prints citation rate with brand visibility above it when the report
carries a real reading for that
(frontend/src/routes/(app)/insights/report/+page.svelte#hasBrandVisibility),
where you stand engine by engine, what shipped that week if anything did,
and up to three moves from that week's "Do this next" list, under a heading
that names how many it shows ("Two moves next week" when the list has two)
(frontend/src/lib/insights.js#movesHeading). It is drawn in the project's
report accent colour, or coral (#F2685C) when none is set
(frontend/src/lib/report-accent.js#REPORT_ACCENT_DEFAULT). The tiles, the
prompts that moved, the competitor comparison, the AI referral traffic and
Search Console sections, and the sentiment breakdown stay on screen. There
is no PDF file the product builds: the page's Print or save as PDF
button opens your browser's own print dialog, the same as printing any
other web page. On a plan without weekly reports the page says printable
reports come with a paid plan; a failed read shows an error with Retry;
and a project with no report yet says there is no report to print, so the
three are never confused.
Client sharing
Company members and editors can choose Client links to preview and share a fixed digest of a generated week. Links work without sign-in, expire after 1, 7 or 30 days, and can be revoked. The client page contains a smaller set of fields than this screen. Review the exact preview before creating a link. See Client report links for contents, permissions, measurement caveats and access checks.
History
Past weeks are one click away once more than one exists: a dropdown lists
every week with a generated report
(frontend/src/routes/(app)/insights/+page.svelte#availableWeeks), and
picking one fetches that specific week without changing anything else on
screen (api/routers/insights.py#get_insight_for_week). A project not on a
plan the report is included in cannot reach a past week either, the same
gate as the latest one.
Across client projects
Open the Client reports tab under Reports in the sidebar to review the same completed week across your active projects, with separate readings and access states. Choosing Open report switches to that project and exact week. A requested week that is no longer available shows an error instead of substituting the latest report. See Client reports.
Related
- Metrics defined: the formulas behind brand visibility, citation rate, and the other figures on the scorecard
- Citation gaps: how the opportunities behind "Do this next" are found and scored
- Brands and sub-brands: where you add, pause and remove the competitors this report's "against competitors" section compares you with
- Search performance: where this report's striking-distance queries come from
Last verified 2026-10-15