LLM Pulse

Delete a tag/collection from a project. The tag is removed irreversibly, but its prompts remain and only the grouping disappears. Requires the exact collection id. The in-app chat requests confirmation before execution.

delete_collection

Delete a competitor from a project. This irreversible action removes the competitor immediately, frees a competitor slot, and purges its mentions, citations, sentiment, and share-of-voice history in a background job. Requires the exact competitor id. The in-app chat requests confirmation before execution.

delete_competitor

Delete a prompt from a project. This irreversible action removes the prompt immediately, frees a prompt slot, and purges its executions, mentions, citations, sentiment, and related GEO Writer tasks in a background job. Requires the exact prompt id. The in-app chat requests confirmation before execution.

delete_prompt

Delete a webhook subscription by ID. The target URL stops receiving events immediately. Available on Scale and above plans.

delete_webhook_subscription

Finalize a project draft: create the project from a completed wizard draft. The operation revalidates every plan gate and quota. It is idempotent, and an already-finalized draft returns its existing project.

finalize_project_draft

Get the AI Model Insights position distribution for the project brand and an optional competitor. brand_kind=non_brand matches the in-app default and excludes brand-focused prompts. When brand2 is omitted (or equals brand1) it defaults to the largest other competitor by mentions. Weekly and monthly buckets cover full calendar periods, including the complete first period containing the range start.

get_ai_model_position_distribution

Get an AI model summary: a per-AI-model breakdown of mentions, citations, sentiment, and weighted visibility for the brand and competitors. All models are returned in one response. brand_kind=non_brand matches the in-app AI Model Insights default and excludes brand-focused prompts. mentions_market_share is the independent mention rate of each actor within a model, so values can overlap and do not form a 100% share partition.

get_ai_model_summary

Get aggregate Google AI Overview result availability over time plus per-prompt breakdowns.

get_ai_overview_results

Get AI traffic for a project: the human visits arriving from AI assistants (ChatGPT, Perplexity, Gemini, Claude, Copilot, Grok, Mistral, Meta AI, DeepSeek), measured from the connected web analytics provider (Google Analytics 4, Adobe Analytics, PostHog, Plausible or Piano). Returns per-day users, sessions and conversions grouped by AI source, plus totals and conversion rate. Requires a connected web analytics provider. Available on Scale and above plans.

get_ai_traffic

Get the account plan, usage, remaining quotas (prompts, projects, competitors, tasks) and API rate limits for the authenticated account. plan is the internal key and plan_name its display name (e.g. Scale++). The response includes the remaining capacity for quota-consuming creation and analysis actions. An unlimited quota returns limit and remaining as null with unlimited=true. The subscription block is only present for callers who may access Billing & Plans.

get_account_usage

Get agent traffic: aggregated AI bot traffic for a project from Cloudflare or uploaded server logs. Returns per-day request counts grouped by bot or by company. Available on Scale and above plans.

get_agent_traffic

Get detailed information about a single AI answer/response including full response text, mentions, citations, sentiments, and sources.

get_answer

Get sanitized cached page content plus page-cache metadata and mention snippets for one cited URL. Text longer than 15,000 characters is truncated (content.text_truncated=true, full length in content.text_total_chars); use max_chars to shrink the slice and offset to page through the rest.

get_cited_url_content

Get cited URL details: URL-level citation intelligence for one cited URL, including page-cache metadata and mention evidence.

get_cited_url_details

Get competitor details: matching names, mobile app IDs, and icon URLs.

get_competitor_details

Get a GEO Writer (formerly Content Intelligence) task by ID, including status and result data when completed.

get_intelligence_task

Get mentions by citing domain: for responses where a given source domain is cited, the share of those responses that mention the brand vs each competitor (brand + competitors sum to 100% per domain). Accepts a list of domains so the whole matrix is one call. Answers questions like "when gmac.com is cited, which brands get mentioned?".

get_mentions_by_citing_domain

Get project details: matching names, industry, business model, primary products, target audience, prompt counts per brand focus (brand / brand_other / non_brand), and data_coverage for the AI models, countries, and languages that have data.

get_project_details

Get a project wizard draft: state, current step, accumulated data. include_suggestions returns cached suggestions for the current step (never triggers AI).

get_project_draft

Get a prompt summary: per-prompt aggregated metrics (responses, mentions, citations, mention_rate, citation_rate, avg_mention_position, avg_position) with pagination and sorting. mention_rate (also accepted as visibility) is the percentage of responses mentioning the brand. Returns brand-only metrics broken down by individual prompt. Supports breakdown=model to get per-prompt per-model metrics. Field notes: visibility and mention_rate are the same value (historical alias, both kept for compatibility); avg_mention_position is the average rank of the brand among the brands named WITHIN the answers that mention it, and it is the position behind ai_visibility_score; avg_position is a different thing, the average rank of the brand cited URL among the URLs an answer cited (background citations excluded).

get_prompt_summary

Get full details for one recommendation run, including items, source references, and report data. Each item carries source_refs codes (e.g. P1, C2); resolve them against the report_data indices (prompts_index, citations_index, own_content_index), which are always included once per response.

get_recommendation

Get the scores of one reputation report as flat rows: one row per (analyst model, brand, dimension, attribute) with its 0-100 score and the reasoning the model gave. The report id comes from the project reputation-report history. Scores remain separate for each analyst model, and the model filter selects a single analyst view. Requires reputation monitoring to be enabled on the account.

get_reputation_report

Get top Google Search Console landing pages for a project over a date range, ranked by impressions, clicks, CTR, or average position, with pagination. Supports filters, non-web search types, and data_state=all for recent incomplete days. Page rows can differ from property-wide headline totals. Requires a Search Console connection.

get_search_console_pages

Get top Google Search Console search queries for a project over a date range, ranked by impressions, clicks, CTR, or average position, with pagination. Supports filters, non-web search types, and data_state=all for recent incomplete days. Query rows undercount anonymized queries and can differ from property-wide headline totals. Requires a Search Console connection.

get_search_console_queries

Get Share of Voice (SoV): the relative share of mentions between the project and its competitors over time. Returns current shares by actor plus periods with the mention sample size (n), a partial flag, a confidence level (none, low under 30 mentions, medium under 100, high) and margin_of_error in percentage points; sample is the period the current shares were computed on. view=compact drops the over_time, breakdown and others representations; view=over_time, current or breakdown returns only that one. group_by=model returns the comparison per AI model. brand_kind=non_brand excludes brand-focused prompts for a fair competitor comparison.

get_sov

Get one custom AI study: its brief, the subjects it compares, the dimensions it scores them on, and its report history. The `reports` array contains the ids and status metadata for the study score reports. Requires reputation monitoring to be enabled on the account.

get_study

Get the scores of one custom-study report as flat rows: one row per (analyst model, subject, dimension, attribute) with its 0-100 score and the reasoning the model gave. The report id belongs to the selected study report history. Scores remain separate for each analyst model. Requires reputation monitoring to be enabled on the account.

get_study_report

Get summary statistics for metrics over a time period. Returns one row per metric and actor with total, min, max, and last values. Count totals are summed; percentages and rates are averaged across periods. group_by returns one summary per AI model or collection. brand_kind=non_brand excludes brand-focused prompts for a fair competitor comparison.

get_summary

Get one technical GEO report by type and id, including its current status and full result_data when completed. agent_readiness identifies the AI/Agent Readiness report. A response containing poll_after_seconds indicates that the existing report is still running.

get_technical_geo_report

Get time series metrics data for a project. Supports mentions, citations, mention_rate (also accepted as visibility), citation_rate, responses, ai_visibility_score (position-weighted visibility and unbounded), avg_position, net_sentiment, and sentiment breakdowns. Competitor series accept competitor record ids. Week and month granularity clip the first bucket to the requested window. brand_kind=non_brand excludes brand-focused prompts for a fair competitor comparison.

get_timeseries

Get top performing source domains for a project. Returns domains ranked by citing responses. avg_visibility (alias avg_mention_rate) is the percentage of all responses in the window that cite the domain at least once, bounded from 0 to 100. This metric describes the domain, not the brand, and does not include brand share conditioned on that domain.

get_top_sources

Get sample webhook payloads for an event type, built from the project's most recent real data or a static sample when no data exists. The response shows the exact signed-delivery payload shape. Available on Scale and above plans.

get_webhook_sample

Launch AI-powered recommendation generation for a project. This action spends the shared weekly recommendation-item budget unless the account has unlimited recommendations or the caller is an admin. It starts a background job that typically runs for 1-3 minutes. The in-app chat requests confirmation before execution. Recommendation status moves from pending to processing to completed.

launch_recommendations

List ads: the paid placements AI answers returned for your tracked prompts. view=advertisers (default) returns one row per advertising domain with its placement count, how many prompts it appeared on, and its average and best position; view=ads returns the individual placements with title, snippet, position and the prompt that triggered them. Every response also carries a totals block (placements, advertisers, your placements and share, average position) matching the KPI cards in the app. Position 1 is the best slot, so a LOWER average position is better. Available on Scale and above plans.

list_ads

List agent bots: the catalog of known AI bots, including crawlers, assistants, and search fetchers, with their parent companies. Returns each bot's slug, display name, company, category, and description. The slugs and company names are valid bot-traffic filter values.

list_agent_bots

List all citations (brand + competitor) for a project with actor_type field. Returns paginated results combining project and competitor citations. The competitors filter narrows which competitor rows are included, but project rows are ALWAYS included. position 0 means unranked/background (real positions are 1-indexed).

list_all_citations

List all mentions (brand + competitor) for a project with actor_type field. Returns paginated results combining project and competitor mentions. The competitors filter narrows which competitor rows are included, but project rows are ALWAYS included.

list_all_mentions

List the timeline annotations of a project, newest first. Includes manual annotations, project automations, GEO test markers, and platform-wide events. origin identifies the source and editable indicates whether the authenticated user can modify the row. Supports date-window and category filters. Available on every plan.

list_annotations

List AI answers with their content, prompt text, model, and basic metrics. Results are paginated and response text is truncated to 1,500 characters per row by default. full_text=true raises the per-row limit to 10,000 characters. query performs full-text search, makes total the exact number of matching responses, and returns a short snippet around each match.

list_answers

List URL citations of the project brand only, without competitor rows and effectively one citation per answering response. position 0 means unranked/background; ranked positions are 1-indexed. Returns paginated results with citation id, name, domain, prompt_id, prompt_execution_id, url, position, and created_at.

list_citations