Geck

Helping Online Stores Win the Agentic Commerce Era

AI-Native Product Engineering · Enterprise AI & Agentic Systems · Technical Architecture & System Design

INDUSTRY

Agentic Commerce

TEAM

3 Members

PROJECT STATE

Ongoing

COUNTRY

United States

About Project

Geck is an agentic-commerce intelligence platform built for a web where AI agents — not just humans — increasingly browse, compare, and check out on a shopper's behalf. Appening partnered with Geck to design and engineer the entire product: an executive analytics dashboard, a deep-crawl audit engine that scores sites on 15 AEO and 19 AXO parameters, an autonomous agent simulator that runs real agents (ChatGPT Atlas, Perplexity Comet, and others) through live store flows, a sub-3KB tracking pixel that separates agent traffic from human, and the cloud-native backend that ties it all together. The outcome is a single platform that shows brands exactly how AI agents experience their site — and what's silently costing them sales.

Commerce is going through its biggest shift in 25 years, and most online stores are blind to it. Shoppers are handing tasks to AI agents — find this, compare that, add to cart, check out — and those agents make buying decisions in milliseconds. But stores were built for human eyes, not autonomous code. Agents can often find a brand yet fail the moment they try to act: broken DOM selectors, CAPTCHA walls, bot blocks, fragile checkout flows, and missing structured data quietly kill transactions a human would have completed. None of it surfaces in Google Analytics, which can't even tell agent traffic from human — so the revenue leak is invisible, and stores lose high-intent, high-AOV agent shoppers without ever knowing it happened. The discoverability layer is shifting in parallel: as buyers ask ChatGPT, Gemini, and Perplexity for recommendations instead of scrolling search results, brands that aren't cited simply don't exist. And quantifying any of this was nearly impossible — there was no score, no diagnostic, no way to watch an agent attempt a purchase and see precisely where it broke. Every month without that visibility, competitors who get agent-ready first lock in a lead that compounds.

In just 12 weeks, Appening took Geck from concept to a production-ready beta — turning an invisible, unmeasurable problem into something brands can finally see, score, and fix:

The revenue leak became visible: Brands can now watch real AI agents attempt checkout, login, and search on their own store and see exactly where each one breaks — failures previously hidden from analytics are mapped, quantified, and tied to lost GMV.
"Are we agent-ready?" got a number: Every store gets a 100-point AXO score and a prioritized, engineer-ready list of fixes, replacing guesswork with a backlog ranked by revenue impact.
Agent traffic stopped hiding inside human traffic: A lightweight pixel separates AI bots from real visitors in real time, giving teams their first true read on how much of their traffic — and revenue — is already agentic.
Discoverability is measured alongside transactions: Brands can see where they're cited or missing across ChatGPT, Gemini, Perplexity, and others — fixing being found and being bought in one place.
It holds up at enterprise scale: The platform ingests 1M+ tracking events a day with zero dashboard lag and charts that render in under 150ms — proof it was engineered to production standard.

Product Features

Appening help you reach business goals by applying Agile methodologies.

AXO Dashboard

The core cockpit of Geck provides marketing leaders with an aggregate overview of their brand's footprint in the AI-search ecosystem. It consolidates metrics across multiple domains into a single pane of glass, highlighting Total Projects, Total Audits, Average AEO/AXO Scores, and overall Brand Visibility (Citation Share).
To maximize user engagement, we designed a responsive dual-grid layout featuring SVG trend lines that track site audit readiness and brand citations over 7-day windows. This dashboard allows marketing teams to immediately quantify the impact of their optimization campaigns.
Value-Add: Built using a modular Next.js architecture with optimized state management, ensuring real-time charts load in under 150ms even when querying datasets containing millions of historic visibility events.

AI Visibility Dial & Metrics

LLMs crawl and index web content differently. To let users see where their brand is mentioned, we engineered the AI Visibility Analytics Engine. This feature presents an overall visibility dial (0-100%) and breaks down citations across major platforms: ChatGPT, Gemini, Perplexity, Claude, and Microsoft Copilot.
This comparative view enables enterprises to target specific search models where they lack visibility, providing direct metrics on where LLM citations are failing and where they are succeeding.
Value-Add: We built a custom scoring algorithm that standardizes citation shares and search ranks across differing API behaviors of various LLM providers, rendering a single, reliable visibility index.

Agent Workflow Builder

To optimize websites for Autonomous AI Agents (which buy products, book flights, or book tables on behalf of humans), we built the Agent Workflow Simulator. Users can write or record multi-step behavioral scenarios (e.g. 'Browse product', 'Add item to cart', 'Submit guest checkout') and run them on demand.
The simulator executes these actions in a sandboxed headless browser, providing a step-by-step audit log of whether the AI agent succeeded or encountered structural blocks (like poor DOM semantics or checkout API failures).
Value-Add: Backed by a scalable Playwright worker pool that compiles test steps, dynamically executes actions inside isolated containers, and feeds logs back to the user via a live WebSocket connection.

Deep Crawl Site Audit

AI search crawlers depend on clean code, proper semantic metadata, and open crawler access guidelines. The Site Audit Engine performs automated full-site diagnostic scans, checking critical parameters like robots.txt directives, structured JSON-LD data schemas, sitemaps, canonical tags, and page readability.
It identifies exact blocking elements, visualizes matching code snippets (such as crawlers disallow directives in robots.txt), and ranks optimization fixes from critical to low-priority.
Value-Add: Designed and implemented a high-performance crawl queuing manager that schedules audit workloads, parses page markup, extracts structured schemas, and runs rule-based diagnostic analysis without triggering target site firewalls.

Pixel Tracker

To track crawls in real-time, brands must identify when AI search bots inspect their site. We developed a lightweight, non-intrusive tracking pixel. Developers add a simple async script tag to their site header, which automatically hooks into browser visits and parses bot signatures.
The tracker detects AI user-agent headers, monitors page interaction speeds, and pushes raw event payloads to Geck's real-time collectors without adding page latency for normal human users.
Value-Add: Engineered a highly optimized, cross-origin javascript pixel tracker (under 3KB) that runs asynchronously, handles rate-limiting, and batches payloads to prevent network bottlenecking on high-traffic client sites.

To build a high-performance, real-time analytics suite, our engineering team designed and deployed a cloud-native SaaS architecture that processes millions of event payloads daily. The pipeline is structured as follows:

Event Ingestion Pipeline: Lightweight Javascript tracking pixel pushes client-side traffic data via load balancers to a FastAPI collector.
Queue & Stream Broker: Message broker pipelines Kafka and Redis buffer event traffic streams to guarantee lossless delivery.
ClickHouse Database: Column-oriented database structure maintains highly indexed analytics events for instantaneous reporting queries.
Headless Worker Clusters: Playwright and Puppeteer worker threads orchestrate deep-crawls and run automated script executions.