Start free
    Menu
    How it worksIntegrationsCustomersPricingSign in

    documentation

    documentation.

    Set Cogny up, connect your stack, and run it from Claude, ChatGPT, Cursor or Codex over MCP. Integration guides, references and architecture.

    Press / to search.

    15

    Getting Started & Setup

    How to set up Cogny Cloud for success: what to connect, what to tell the agent, and how to run the weekly loop

    1. 01Set Up Cogny Cloud for SuccessThe complete guide to getting value from Cogny Cloud: what Cogny is, the one-hour setup, what to expect in weeks one to four, and the weekly routine that makes it compound.
    2. 02Before Your Onboarding: Checklist and WizardWhat to decide and gather before the Cloud onboarding call, who should attend, and what the Cloud setup wizard does in its two steps.
    3. 03Connect Your Data SourcesWhich integrations to connect first and why, how OAuth and API-key connections work, the GA4 and Search Console links into BigQuery, tool permissions, and the traps that cost a week.
    4. 04Context and Growth StrategyThe context layers the agent reads before every report and ticket: the generated industry, company and competitor documents, the growth strategy, the context tree, and what to put where.
    5. 05Core MetricsDefine the two to five numbers you run the business on, so every report and ticket is judged against them, and unlock the Core Metrics Drivers report.
    6. 06Reports and TemplatesHow scheduled reports work, which templates to enable first for your kind of business, cadence and adaptive scheduling, custom instructions, email delivery, and what reports cost.
    7. 07Tickets and ApprovalsHow the ticket board works, the three decisions on every ticket, why the first twenty deserve real review, how feedback teaches the agent, and how to turn on auto-execution safely.
    8. 08Automations and Content LoopsBeyond weekly reports: Autonomous Operator jobs that act through tools you greenlit, Content from data loops that turn a source into published pieces, and Scripts for deterministic sync work.
    9. 09Connect Your Own App to Cogny AutomationsExpose your app's data and actions as an MCP endpoint, register it with Cogny, and run a scheduled agent against it. The full loop a coding agent can do end to end with the Cogny CLI.
    10. 10Coding Agent, GitHub and Cogny SitesConnect your repository so tickets ship as pull requests with preview deployments and visual proof, what to expect from the coding agent, and how to handle sites on a locked CMS.
    11. 11Use Cogny from Your Own AgentConnect Claude, ChatGPT, Codex, Cursor, Lovable or the Cogny CLI to your workspace over MCP, when to use your own agent instead of the in-app chat, and what it costs.
    12. 12Credits and PlansWhat the plans include, what consumes credits and what does not, rough costs per action, what happens at zero, and how to keep a Cloud workspace inside its monthly allowance.
    13. 13Buying Guide for AgentsWhat an AI assistant needs to know before its user subscribes to Cogny: what each plan includes, what the tools can change, who approves a write, the limits, billing and data protection.
    14. 14Team, Governance and PrivacyRoles and invitations, the weekly operating cadence that keeps the loop running, human-in-the-loop support, Cogny Shield for personal data, audit trails, and workspace deletion.
    15. 15Cogny Cloud FAQThe questions customers ask most before and after setting up Cogny Cloud, answered plainly: trials, credits, what it does and does not do, time required, CMS support, privacy and results.
    02

    Connecting Integrations

    The integration catalog, per-platform setup guides, and connectors that need extra steps

    1. 01Integration Catalog and Setup GuidesEverything Cogny connects to, grouped by category, with the setup guide for each platform and the connectors that need extra steps.
    2. 02Connect Discord to Cogny — bot setup, intents, and invite URLEnd-to-end Discord MCP setup: create the application, copy the token, install the bot with the right scope and permissions, and enable the two privileged intents the read tools need.
    04

    Features

    How the product works under the hood

    1. 01Webhooks: Send Cogny Events to Slack, Zapier or Your Own ServerConfigure an outbound webhook, pick from eight events, verify the X-Cogny-Signature header and handle retries. Included on Cogny Cloud and AppSumo Tier 3 and Tier 4.
    2. How Growth Tickets WorkHow Cogny turns report insights into prioritised, executable tickets: what the ticket agent reads, how it scores and de-duplicates, how execution and analysis close the loop, and what always stays with a human.
    3. How AI Reports WorkHow a Cogny report is produced: the template and context that shape it, the bounded analysis loop over your warehouse and integrations, the data-quality checks, the output structure, scheduling and delivery.
    4. How ICP Analysis WorksHow Cogny builds, validates and uses your ideal customer profile: generated from context and real buyer data, editable, exported as platform targeting, and checked against actual conversions by the Audience Intelligence report.
    02

    MCP & Agents

    Use Cogny from Claude, ChatGPT, Cursor or any MCP client

    1. 01Install Cogny in Your AI AgentPaste one line into Claude Code, Codex, Cursor or another coding agent and it sets Cogny up itself. What the agent does, what it changes on your machine, how to do it by hand, and how to undo it.
    2. Cogny MCP ServerConnect Claude to your marketing data. Query BigQuery, browse reports, manage growth tickets, and build organizational context — all through natural conversation.
    10

    Platform References

    Reference material for the platforms Cogny reads from: GA4, Google Ads, GTM, Meta, schema.org, UTMs and more

    1. Conversion Tracking Debugger ReferenceComplete debugging guide for conversion tracking across GTM, GA4, Google Ads, and Meta Pixel. Covers discrepancy diagnosis, BigQuery validation queries, Consent Mode v2, Enhanced Conversions, server-side tagging, and step-by-step troubleshooting flowcharts.
    2. Core Web Vitals ReferenceComplete technical reference for Core Web Vitals (LCP, INP, CLS): thresholds, common causes, fixes, measurement tools, CrUX BigQuery queries, web-vitals library usage, and SEO impact.
    3. GA4 BigQuery Export Schema ReferenceComplete reference guide to the Google Analytics 4 BigQuery export schema, including table structure, nested fields, common queries, and data processing best practices.
    4. GA4 Event Implementation ReferenceComplete reference for implementing Google Analytics 4 events: automatically collected, enhanced measurement, recommended, and custom events with exact parameter lists, code examples, and validation techniques.
    5. Google Ads Query Language (GAQL) ReferenceComplete GAQL reference covering syntax, resource types, fields, operators, date macros, and ready-to-use query patterns for campaign performance, search terms, Quality Score, geographic targeting, and more.
    6. Google Ads Scripts ReferenceComplete reference guide to Google Ads Scripts: JavaScript automation within Google Ads, AdsApp object model, selectors and iterators, GAQL queries, common script patterns with working code, Google Sheets integration, MCC scripts, and best practices.
    7. GTM Event Tracking & Setup ReferenceComplete reference guide to Google Tag Manager event tracking, including dataLayer fundamentals, trigger and variable types, GA4 tag configuration, debug mode, and implementation best practices.
    8. Meta Conversions API (CAPI) Setup ReferenceComplete technical reference for Meta Conversions API: architecture, event types, customer information parameters, implementation methods, deduplication, testing, and Aggregated Event Measurement.
    9. Schema.org Structured Data ReferenceComplete reference for Schema.org structured data markup: JSON-LD examples for every major schema type, rich results eligibility, testing tools, and implementation patterns for static sites, Next.js, React, and WordPress.
    10. UTM Parameter Strategy & Builder ReferenceComplete guide to UTM parameter strategy, naming conventions, GA4 channel grouping rules, auto-tagging behavior, common mistakes, and BigQuery validation queries for marketing attribution.
    01

    Trust

    AI transparency, literacy and how to read what the agent says

    1. AI Transparency & Literacy at CognyHow Cogny uses AI, what the EU AI Act means for our customers, how we label AI-generated output, and the basics every user should know to use AI-assisted marketing responsibly.