📄️ AI Model Registry
It’s a central “catalog” of the AI models your can use in Rational AI. You add models once, and use them consistently (chat, agents, tools, workflows, etc.). It also lets you control which models are available, see key info (size, type, updates), and manage changes over time.
📄️ Fine-Tuning
Fine-tuning lets you customise an AI model with your own data so it performs better on the tasks that matter to you. You pick a base model and a training dataset, set a few training parameters, and launch a job that produces a tailored model. Use this section to start fine-tuning jobs and track the ones you've already run.
📄️ Datasets
Datasets are the curated collections of examples you use to fine-tune models in Rational AI. Each dataset stores its entries in a standard training format, keeps a full version history as you add more data, and can be downloaded or reused across fine-tuning jobs. Use this section to build, organise and maintain the training data that powers your custom models.
📄️ Extensions
Extensions are Model Context Protocol (MCP) servers that expand what your models can do in Rational AI. Each extension packages a set of capabilities—tools, prompts and resources—that agents can call during a conversation, such as fetching web pages, querying a database or searching the web. Use this section to install extensions from the registry, enable or disable them, configure their settings and review the tools they expose.
📄️ Sources
A source is a connection to an external system that supplies data to Rational AI, such as an Amazon S3 bucket or a Google Drive folder. Sources keep your content in sync on a schedule so the Knowledge module always works from up-to-date material. Use this section to add sources, configure how often they sync and monitor the result of each synchronisation.
📄️ Connectors
A connector stores the credentials and configuration needed to talk to an external provider—such as Google, AWS, OpenAI, Anthropic, OpenRouter, Brave Search or Azure. Once a connector is set up, it can be reused across the platform: by AI models (to reach a provider's API), by sources (to read your data) and by tools. Use this section to add connectors and review where each one is used.
📄️ Conversations
The Conversations settings control how Rational AI enriches and processes end-user conversations behind the scenes. From here you choose the default conversational model and configure three automatic analyses—title generation, topic detection and sentiment analysis—each of which can be enabled independently and assigned its own model and prompt. These settings apply across the platform unless a touchpoint overrides them.
📄️ Touchpoints
A touchpoint is a configured entry point through which users interact with an AI agent—for example, a chat assistant for a specific product or customer-care flow. Each touchpoint binds together a channel, a model and system prompt, the knowledge sources it can draw on and the tools it can call. Use this section to create touchpoints and tailor each one to a specific use case.