# What is tagIt? tagIt is an AI platform for building and improving **AI journeys**. Most teams can get a chatbot on the screen. The harder part is making that experience feel intentional, governed, and adaptive over time. That is where tagIt fits. tagIt helps teams: * design how an AI experience should behave * embed that experience in a product or host application * learn from conversations and user behavior * turn those signals into insight and engagement policy * use that policy to improve future interactions In short, tagIt helps teams move beyond one-off chat and build AI experiences that can evolve. ## How teams get started If you want to use tagIt in your own product or organization, start by contacting ****. If you want help shaping a broader AI initiative, [**Enhanced Relevance**](https://enhancedrelevance.com), powered by tagIt, can help teams define the right use cases, pilot them safely, and deploy them into real products and workflows. ## The three parts of tagIt ### AI Orchestrator AI Orchestrator is the runtime layer that conducts the journey. It helps teams define and run: * contexts * use cases/agents * model selection * tool and MCP integrations * policies and runtime controls A **context** is the top-level container for a brand, product, campaign, site, app, or agent family. It provides the shared environment and governance for the use cases/agents inside it. This is the layer that decides how an AI interaction should execute for a given scenario. ### AI Canvas AI Canvas is the experience layer. It gives teams the ability to embed a polished AI surface into a product, site, or application. This is where users actually engage with the journey through the AI client and interface patterns that bring the experience to life. ### AI Presence AI Presence is the intelligence layer. It turns conversations into intent, memory, and insight. Instead of treating every interaction like a fresh start, tagIt helps teams understand what a user is signaling over time and use that understanding to shape future engagement. This is what allows the journey to become more context-aware, not just more conversational. ## How tagIt works At a high level, tagIt connects orchestration and insight in one loop: 1. A team designs an AI journey using contexts, use cases, models, and tools. 2. The experience is embedded into a product or workflow. 3. Users interact with that experience. 4. tagIt captures relevant conversation and behavioral signals. 5. AI Presence classifies those signals into intent and relationship memory. 6. That insight becomes engagement policy that can inform future orchestration. The result is an AI system that does not just answer. It learns how to engage more effectively over time. ## Who tagIt is for tagIt is built for teams shipping AI experiences, including: * product teams designing AI journeys * platform teams governing orchestration and runtime behavior * teams embedding AI into host applications, apps, and customer workflows * teams that want insight into what conversations actually mean, not just what was said ## Why tagIt is different Many tools solve one piece of the problem. Some help you build a chatbot. Some help you orchestrate model calls. Some help you analyze conversations after the fact. tagIt connects those layers. It combines: * orchestration * embedded AI experiences * presence intelligence That means teams can design the journey, deliver the experience, and learn from it in one connected system. ## In one sentence tagIt makes AI journeys easy by combining orchestration, embedded AI experiences, and presence intelligence that turns conversations into intent, memory, and action. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://tagit.gitbook.io/tagit/getting-started/what-is-tagit.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.