Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    GEO-Pulse: AI Search Visibility & Citation Share Tracker

    1

    Track how ChatGPT, Perplexity and Google AI Overviews cite your brand vs competitors over time—with 0% URL hallucination and no $800/mo CRM lock-in.

    $39

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    GEO-Pulse: AI Search Visibility & Citation Share Tracker

    GEO-Pulse: AI Search Visibility & Citation Share Tracker

    Example session with this skill installed

    Score November's 40 buyer-intent search responses across ChatGPT, Perplexity and AI Overviews against October's snapshot and build our QBR report.

    • Read your context and instructions
    • Compiled the geo-pulse

    GEO Visibility Index 34/100 (+6 MoM vs VeloData 46 and CloudPulse 20), 2 hallucinated URLs quarantined from scoring, 0% share gap identified on 'pricing alternatives' prompts, 120 verified BigQuery JSONL rows, and prioritized FAQ/JSON-LD remediation actions.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    High-intent B2B buyers shortlist vendors inside ChatGPT, Perplexity and AI Overviews before clicking a website, yet enterprise AEO trackers sit behind $800–$3,600/month suites and naive prompt scripts credit fabricated URLs.

    What your AI assistant does with it

    • Raw-payload URL verification: Cross-checks every cited link against raw search grounding payloads on strict domain boundaries—quarantining hallucinated URLs.
    • 0–100 GEO Visibility Index: Scores mention prominence, verified domain citations and recommendation polarity across four buyer-intent funnel stages.
    • Month-over-month share diffs: Compares snapshots against prior runs to spotlight lost citations, rival surges and negative-caveat warnings.
    • BigQuery JSONL & agency QBRs: Enforces pre-run query cost caps and outputs BigQuery time-series JSONL, DDL, Excel XML and client-ready HTML QBR decks.

    How a run works

    1. Configure your brand domains, rival domains and 25–100 buyer-intent prompts
    2. Run --plan-only to verify query count against your pre-run API spend cap
    3. Score captured ChatGPT, Perplexity and AI Overview responses against grounding logs
    4. Deliver the monthly QBR report, BigQuery JSONL row set and schema/content fixes

    Built for: VP Marketing & Growth leads, SEO / GEO agency owners, B2B content & PMM teams.

    Included: Skill instructions with pre-run API budget & grounding gates, geo_pulse_tracker.py: citation verifier, 0–100 GEO scorer & MoM delta engine, BigQuery JSONL + DDL, Excel SpreadsheetML workbook & offline HTML QBR report, Unbiased prompt-cohort design & JSON-LD remediation guide, Multi-engine citation & hallucination-quarantine evaluation case.

    Part of the B2B Operations & FinOps suite by Production AI Agents. Every calculation runs locally in standard-library Python (Decimal math, zero hidden network calls) and pauses at a human STOP AND VERIFY gate before any external write or sign-off.

    Scores captured search/LLM response payloads deterministically; live answer capture uses your connected search/LLM API or MCP within your budget cap. Always review generated calculations, drafts and SQL/API payloads before executing external actions.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Requires

    Python 3.10+
    Python

    Permissions

    File Scopes

    Prompt
    cohort
    JSON
    and
    captured
    AI
    search/grounding
    JSONL
    logs
    (read);
    BigQuery
    DDL
    SQL
    Excel
    XML
    QBR
    HTML/Markdown
    (write)

    geo_pulse_tracker.py scores captured response payloads deterministically offline and enforces a pre-run cost cap before any live search capture.

    Listedtoday

    What's inside

    Frequently Asked Questions

    geo_pulse_tracker.py cross-verifies every URL mentioned in model prose against the raw search/grounding citation array using strict RFC-compliant domain-boundary matching—quarantining ungrounded URLs.

    No. GEO-Pulse runs standalone with your own prompt cohort JSON and stores longitudinal history in plain local files or your own BigQuery dataset.

    GEO-Pulse separates mention frequency from recommendation polarity and triggers a 'High Visibility / Negative Caveat' alert whenever negative caveats exceed 25%.