Publish Content to your own
Private GPT and AI Models

Deploy your content safely and quickly to private, secure Large Language Models (LLMs) and inference-based AI models running on your local network (or in the cloud).

Enhance your content with critical metadata, classifiers, heuristic relational weights and tags that are inferenced seamlessly from Generative AI, Image and Optical Character Recognition, Textual Analysis and more.

Continuously train your Private GPT and ML Models with generated datasets and calibration. Schedule your releases for batch deployment of content and models for QA, Staging and Production.

  • Secure Data on your Infrastructure

    Run everything within your own containers. Your data never leaves your network.

  • Private GPT and AI Models

    Spin up new Private GPT and Machine Learning models to provide smart API support for your customer engagement apps.

  • Trained on your Content

    Generate datasets, tests and validations using AutoML to train Private GPT and ML models as experts on your content and messaging.

  • Content Production Workflow

    The Editorial team works alongside AI "Sidekick" assistants to create, enhance, approve, train and deploy critical content changes in real-time.

  • Enterprise Security

    Safeguard your content with Access Policies. Assert regulatory compliance via the audit trail, lifecycle policies and event handlers.

Gitana Content Platform

Private and Secure

Private and Secure

Prevent your intellectual property from leaking into the public domain. Run your Gitana and private AI model containers locally (via Kubernetes) to keep everything on your internal network.

High Quality

High Quality Data

Enhance your competitive advantage. Increase the signal of your data. Sidekick Copilots work alongside your editorial team to seamlessly sharpen your data with classification, relational modeling and Generative AI.

Real-Time Deployment

Real-Time Publishing

Schedule and release critical content to your Private GPT and AI models. Real-time publishing lets you approve, train, deploy and rollback updates in real-time.


Enterprise Scale

Scale across your business with access policies, workflow, SSO, version control, full-text search, SQL-like query, GraphQL traversal and a Git-like versioned data engine with branches, auditing and best of breed, Enterprise Content Management.

Curation and Deployment


Bulk import your desktop files, SQL data, product inventory information (PIM) or highly structured relational data.


Create, Manage and Approve structured content within the graph using our simple, form-based editorial user interface.


Enhance your content with AI services that manage your graph, curating metadata and pruning the data set for continuous learning.


Approve and publish content across projects and to multiple environments (development, QA, live).


Scriptable generation of AutoML data sets, tests and validations to train your Private GPT / AI Model.

Continuous Learning

Measure model behavior and conversion targets, leveraging feedback to improve / re-calibrate the graph.

Highlighted Features

Integrated AI tools to assist the editor

Automated assistants (Sidekicks) free up your team to be more efficient and more creative.

  • Automated Workloads

    Sidekicks provide assistance at performing a lot of the repetitive tasks and heavy lifting. Once assigned a task, they perform the work in isolated branches and then present that work to you for further editing and approval.

  • Conversational Insights (with Citations)

    Converse with your sidekicks about the content that you're working on. Ask questions and glean insights on specific content instances, sets of content, folders or even your entire branch of content. Sidekick provides citations to indicate from where within your content the answer was sourced.

  • Content Generation

    Sidekicks utilize AI, including Generative AI and ChatGPT, to generate new and interesting content based on what you provide. They summarize documents, generate questions and answers, produce key insights, extract terms and bullet points and much more.

Sidekick answers a question about the contents of a document
Sidekick answers a question about the contents of a document

Boost your Content with Integrated AI Services

Model your content to integrate seamlessly with backend AI services that automatically populate and maintain metadata about your content.


Automatic assignment of content to taxonomy classifiers as your content is modified and undergoes analysis and extraction by AI services including text analysis, image recognition, optical character recognition and more. Define your taxonomy hierarchy and auto-sync assignments as detection occurs in the background.

  • Taxonomy

    Support for multiple versioned taxonomy hierarchies. Develop hierarchies and apply them to multiple projects, repositories and branches.

  • Classification

    Support for nested classifiers with inheritance and behaviors. Easily tag content with classifiers using drag and drop via the taxonomy tree.

  • Import

    Import Taxonomy Hierarchies for various industries (including Medical, Pharmaceutical, Automotive and more) into your data engine using one of our pre-built import providers.

Generative AI

Generate new content, summaries and insights using GPT-3 and GPT-4 powered models by OpenAI ChatGPT, Google Bard and other Generative AI backend providers.

  • Write new content

    Automatically write new content based on an existing selection of text, sizing it for a specific number of words or length and targeting it to a specific audience and voice (such as "professionals" or "parents").

  • Insights

    Given a selection of content, automatically generate summaries, keywords, key points, questions and answers, bullet lists of topics and more. Derive the theme of selected material and correlate with other documents in your branch.

  • Converse with your Content

    Generative AI capabilities work with your content to source insights and write against the knowledge and structure contained in your content model. All interactions are scoped to your current branch, your current document or a current selection of multiple documents. Chat history is maintained to allow for natural language interaction.

Image Recognition

Automatically identify faces, landmarks, text terms and labels, sentiment and content moderation concerns within your image content. Your content is immediately indexed for full-text search and structured query, letting you utilize these extract elements for quick content lookup and discovery.

  • Recognition

    Define which content types are automatically processed through image recognition. Extracted elements are stored as JSON on your content, letting you get at the data from within your application or user interface.

  • Visual Identification

    Extracted elements are highlighted within the editorial interface using overlays. These visual overlays serve to quickly identify the location and relevancy of tags and labels as they apply to bounded regions of the image.

  • Classification

    Image Recognition hooks into the Classification engine, allowing for extracted labels and tags to be utilized in computing the taxonomy of the content bearing the image.

Optical Character Recognition

Automatic detection and extraction of text, terms and categories from images, scanned and hand-written documents. Drop content into Gitana from a scanner or email integration to automatically extract text and index documents for full-text search.

  • Text Extraction

    Hand-written and scanned elements are submitted for visual analysis and text extraction, pulling out all textual elements for use by the editorial curation team.

  • Full-Text Search

    All extracted text is immediately indexed for full-text search, letting editors and managers (and your own live applications) instantly search and find documents.

  • Document Behavior

    Wire up rules that automatically execute based on extracted content, including approval workflows, web hooks and data sanitizing server-side scripts!

Text Analysis

Automatic analysis of text from content properties and attachments to detect labels, landmarks and other entities. Provides determination of sentiment and detection of moderation concerns (bad language, sexual content and more).

  • Text Analysis

    Text is extracted from your content, including properties and attachments. For any new or updated text, analysis is performed and the results are applied to the JSON of your document, enabling immediate indexing and availability for full-text search, query, GraphQL and traversal.

  • AI Services

    Plug in to pre-built integrations to AWS Comprehend and OpenAI GPT-powered NLP comprehension.

  • Classification

    Image Recognition hooks into the Classification engine, allowing for extracted labels and tags to be utilized in computing the taxonomy of the content bearing the image.

Text to Speech

Generate high quality audio with voice sampling from text attachments, properties or ad-hoc fragments of text.

  • Speech Generation

    Produce high quality voice renditions of textual elements. Configure each generative call to utilize the configuration options and vocal samples for the selected platform.

  • AI Services

    Plug in to pre-built integrations to AWS Polly, Google Text-to-Speech Services and Azure Text-to-Speech Services.

  • Workflow-based Approval

    Route audio renditions and source text through workflow for review and approval prior to deployment to a live web site, endpoint or indexing engine.


Automatic processing of audio streams into text-based representations. As you make changes to your audio files, transcriptions are automatically updated and kept in sync.

  • Audio Formats

    Support for a diversity of audio formats. Audio is processed on the fly and text transcriptions are produced and applied to your content instance as JSON.

  • AI Services

    Plug in to pre-built integrations to AWS Transcribe, Microsoft Azure Transcription Services and the OpenAI Whisper API.

  • Workflow-based Approval

    Route transcriptions and source documents through workflow for review and approval prior to deployment to a live web site, endpoint or indexing engine.


Automatically internationalization (I18N) of documents via AI-assisted generation of translations into one or more target locales. As you make changes to your master document, the translations are automatically kept in sync.

  • Master Document

    Well-suited for use-cases in the European Union, Canada and other regulatory environments where multiple documents (including translations) must move together through a workflow approval process.

  • Natural Language Processing

    Plug in to pre-built integrations to AWS Translation Services, Google Translation Services, Microsoft Azure Translation Services and OpenAI GPT-powered Translation Services.

  • Workflow-based Approval

    Route translations and master document changes through workflow for review and approval prior to deployment to a live web site, endpoint or indexing engine.

Scheduled Publishing

Snap together your editorial contributions into a scheduled Release. Lock in a date and Gitana will automatically detect any potential conflicts with other scheduled Releases ahead and after your own. We make it easy to reconcile those conflicts so that your published content is always consistent.

  • Scheduled Releases

    A scheduled release describes a future, locked in state of your content. Simply lock it in, walk away and rest assured that your content will go live on time.

  • Hot Fixes

    Even with a locked-in schedule, you will at times need to quickly push a hot fix. Gitana lets you slot in a hot fix and discover any potential conflicting properties or content items that might be impacted in future releases after the hot fix.

  • The Big Event

    When a scheduled Release goes live, it merges and triggers a series of events. These include sending emails, trigger Slack notifications and publishing to remote endpoints such as CDNs, S3 or other Gitana installations around the world.

Schedule current releases of your content for future dates
Schedule current releases of your content for future dates

Train your AI Models

Generate data sets and stream them into a pipeline to seamlessly train your AI models as experts in your business, your content and your brand.

Trained AI models optimize the customer experience by providing personalized and goal-optimized inference services.

Here are a few examples of AI models that support inference at the edge.

Predictive Recommendations
Predictive Recommendations

Predict what your customers will want to see next. Show what's most relevant based on where they are in their journey, based on contextual navigation, from pre-purchase to post-purchase.


Using real-time customer data and training guidance, create dynamic and custom navigation experiences, delivering pages and components that are most relevant for each unique customer.

Chat Bots / Assistants

Provide better answers for your customers as they interact with ChatBots, assistants and other natural language processing interfaces. Improve accuracy as these models parse, interpret and respond to customer questions.

Personalized Search
Personalized Search

Find it Faster. Using intent-based detection, users search not only on words but also on the intent in their language and behavior to yield instantly relevant results.

Intelligent Tagging

Automatic application of tags to content based on the text, context and intention of the document. Tags allow for automatic management of grouping and relatedness between documents.

Taxonomy / Classification
Taxonomy / Classification

Classify your content according to Taxonomy structures and rules. Group, tag, apply hierachical relationships and apply aspects to inject metadata and behaviors onto your content.

Content Generation
Content Generation (Preview)

Spin up private and secure Large Language Models (LLMs) to provide content generation, summarization, extraction and synopsis using Generative AI. Train and fine tune the LLM on your content, your brand and your messages.

>Questions and Answers
Questions and Answers

When a user types in a question, utilize auto-completion and contextual awareness to instantly serve up one or more responses they need. Provide better customer support with the right answers in fewer clicks.

Ready to Get Started?

Get started with the only Content Platform that publishes your content in real-time to your web sites, apps and Private GPT and AI models.

Request Information