Pierview

AI-extracted facts about competitors from LLM visibility responses. For each tracked competitor, returns positive and negative facts extracted from LLM responses along with a sentiment score.

get_competitor_facts

For each competitor, which LLMs mention them and at what percentage over recent results.

get_competitor_llm_breakdown

Which competitors gained or lost mention share over two consecutive windows — optionally scoped to a single prompt. Use this after spotting a mention-rate drop to find out whether a specific competitor displaced the brand (their mention count/rank improved as the brand's fell) or the change wasn't a competitor takeover at all. Pass promptId to scope to one prompt (recommended after get_prompt_llm_breakdown narrows down a specific prompt+LLM); omit it for an org-wide view across all tracked prompts. Sorted by mention-count delta descending (biggest gainers first) — check the bottom of the list for the biggest decliners.

get_competitor_share_shift

Google Analytics 4 traffic for a date range against the equal-length window immediately before it: total users, new users, sessions, engaged sessions and views for both windows, plus the top countries with each one's share of users. Reads only the organization's connected GA4 property and errors when there is none. For traffic measured by Pierview's own tracking pixel (referrers, UTM campaigns, bot filtering, live users) use get_traffic_analytics instead; the two sources count differently and their numbers will not match. Use query_ga4 when the analysis needs a dimension this summary does not carry.

get_ga4_traffic

Dashboard key metrics for the user's brand (same as Key Metrics cards): mention_rate (share of responses mentioning the brand), average_ranking (lower is better), share_of_voice among competitors. Pass startDate and endDate (YYYY-MM-DD) to specify a custom date range — the previous period of equal length is computed automatically for comparison. If neither is provided, defaults to the past 14 days (two weeks). Includes current vs previous window values. If values are null, read the note field.

get_key_metrics

Filter traffic analytics to show only visits from AI/LLM platforms (ChatGPT, Claude, Perplexity, etc.). Includes both referrer domains and UTM sources. Shows which AI assistants are sending traffic to the user's website. platforms is the per-AI-platform breakdown shown on the Traffic Analysis page, and totalLlmVisits counts a visit once even when it matches by both referrer and UTM source. Pass startDate and endDate (YYYY-MM-DD) to select a specific time range. If neither is provided, defaults to the past 14 days (two weeks).

get_llm_referral_traffic

Recent visibility prompts where competitors appeared but the user’s brand did not.

get_missed_prompts

Per-LLM mention rate for ONE specific prompt, over two consecutive windows. Use this after get_prompt_mention_rates flags a prompt with a notable change, to find out whether the change is broad (every model moved similarly) or concentrated in one or two specific LLMs (e.g. Gemini collapsed while others held steady). Returns current and previous response/mention counts and rates per LLM, sorted by absolute change descending (biggest-moving LLM first).

get_prompt_llm_breakdown

Per-prompt mention rate (share of responses mentioning the user's brand) for each tracked prompt, over two consecutive 14-day windows. For each prompt's estimated monthly search volume, call list_prompts and join on prompt_id. Returns current and previous mention rate as 0–1 fractions plus response counts per window. Results sorted by absolute change descending. For monthly reports: filter to prompts with response_count ≥ 5 in at least one window; highlight prompts with ≥5 percentage point change.

get_prompt_mention_rates

Google Search Console performance for the organization's connected property over a date range, compared against the equal-length window immediately before it. Returns site totals (clicks, impressions, CTR, average position) for both windows, the branded vs non-branded query split, the top query and page gainers and losers with before/after clicks, impressions and average position, queries newly picking up impressions, and a written diagnosis naming the most likely cause of the change (including any Google ranking update that landed inside the window). Use this for the standard 'how is organic search doing' question; use query_search_console when the analysis needs a specific dimension, filter or slice this section does not cover.

get_search_console_performance

Traffic measured by Pierview's own tracking pixel, not Google Analytics (same data as Dashboard, Traffic Analysis). Returns total visits, unique visitors, live users, top referrers, top landing pages, traffic sources breakdown, device breakdown, session metrics (avg duration, bounce rate), bot vs human traffic analysis, UTM campaign analytics (top campaigns, sources and mediums), per-AI-platform traffic with the landing pages it arrives on, daily traffic time series, and recent individual visits. Use this for referrer, UTM campaign, bot-filtering and live-user questions, which only the pixel measures. For Google Analytics figures (users, sessions, engagement, channels) use get_ga4_traffic or query_ga4 instead; the two sources count differently and their numbers will not match. topLandingPages excludes bot-flagged visits, while the visit and visitor totals include them, so read botAnalytics before comparing the two. Pass startDate and endDate (YYYY-MM-DD) to select a specific time range. If neither is provided, defaults to the past 14 days (two weeks).

get_traffic_analytics

Quick summary of Pierview tracking pixel traffic, not Google Analytics: total visits, unique visitors, live users, top 5 referrers, and device breakdown. Use this for a quick overview; use get_traffic_analytics for the full pixel breakdown, or get_ga4_traffic for Google Analytics figures. Pass startDate and endDate (YYYY-MM-DD) to select a specific time range. If neither is provided, defaults to the past 14 days (two weeks).

get_traffic_summary

Daily visibility (mention rate) time series per competitor for the organization. Returns at most 12 x-axis points and top 5 competitors. Use the granularity parameter to control aggregation; if omitted, the best fit is chosen automatically (daily → weekly → monthly).

get_visibility_timeseries

List full-site AI SEO crawls for the organization, most recent first. Each crawl audits an entire domain. Returns crawl IDs, domain, status (running/completed), and score breakdowns. Use this to find crawl IDs before asking about specific results.

list_ai_seo_crawls

List organizations the user can access (organization id, name, workspace, role). Call first when the user may have multiple orgs.

list_organizations

List the organization's tracked prompts (the Prompts page) with their persona and estimated monthly prompt volume, plus the organization's personas. volume is the same figure the dashboard's Prompt Volume column shows: an estimate of monthly AI search volume from the prompt's keywords, rounded, and null where the dashboard shows no figure. Sorted by volume descending, like the dashboard's By Volume view. Use promptId values with update_prompt, delete_prompt, get_prompt_llm_breakdown and get_competitor_share_shift.

list_prompts

Run a custom Google Analytics 4 report against the organization's connected property. Name the metrics and the dimensions to break them down by, optionally filter and order, and read back one row per dimension combination. Common metrics: totalUsers, newUsers, activeUsers, sessions, engagedSessions, screenPageViews, averageSessionDuration, bounceRate, engagementRate, conversions, eventCount. Common dimensions: date, country, deviceCategory, pagePath, landingPage, sessionSource, sessionMedium, sessionSourceMedium, sessionDefaultChannelGroup, eventName, browser. Use this for questions the traffic summary cannot answer: landing pages by channel, organic sessions over time, conversions by source. Invalid metric or dimension names are reported back by Google, so a rejected report can be corrected and retried. For month-over-month reporting, call once per window and compare the results yourself, raising limit above the number of rows you intend to report on so a page truncated out of one window is not read as having lost all its traffic. Note that user-scoped metrics such as totalUsers deduplicate within a window, so two windows' figures cannot be added together into a combined total.

query_ga4

Run a custom Google Search Console query against the organization's connected property. Pick the dimensions to group by (query, page, country, device, date, searchAppearance) and optionally filter them, then read back clicks, impressions, CTR and average position per row. Use this for slices the standard section does not cover: a single page's queries (filter dimension 'page'), mobile versus desktop, one country, a daily time series, or every query containing a term. For month-over-month reporting, call once per month and compare the results yourself; when doing that, raise rowLimit well above the number of rows you intend to report on, because rows come back clicks-first and a query or page truncated out of one month's results would otherwise look like it gained or lost everything. Omit dimensions entirely to get one site-wide totals row, which is the right source for headline clicks and impressions: summing the returned rows understates both, since Search Console withholds rows below its privacy threshold. A row absent from one month has no average position there, so treat a position of 0 as no data rather than a top ranking. Filters are combined with AND. Data lags roughly 2-3 days.

query_search_console

Update the organization's brand kit / brand guidelines. Only the fields you provide are changed — omitted fields keep their current value. Use this to write structured brand guidance (e.g. distilled from documents or notes the user shares) into brandDescription, brandVoice, authorPersona, or writingRules. productLines, when provided, fully replaces the existing product lines list.

update_brand_kit

Edit a tracked prompt's text and/or persona. Changing the text works like the dashboard: the old prompt is retired with its history and a new prompt with a new promptId starts collecting results, so metrics for the new text start from zero. Pass personaId null to unassign the persona.

update_prompt