When building an AI agent or setting up a Project Folder, Dynamic Context allows you to retrieve content from an API and inject it into the system prompt. This can be used to add live information to the AI or implement Retrieval-Augmented Generation (RAG) from your own data sources (e.g., vector store database).

Use cases

• Connect to a vector store database and make use of the lastUserMessage parameter to inject useful/relevant content into the AI agent/Project.
• Inject “Latest newsletter post” to your AI agent/Project context.
• Add “Latest 10 tweets from my account” to the AI agent/Project.

How it works

For AI Agent:

• Go to AI Agents → Create or edit an AI Agent → Set up a Dynamic Context via API.

For Project Folders:

• Create a new folder in the left sidebar → Click on Project Settings → Set up Dynamic Context

Here’s how it works:

• When the user chats with the AI Agent/starts a conversation within Project Folders, the API endpoint will be called.
• The response of the API endpoint will be added to the AI Agent’s system prompt or the Project Folder Context and Instructions.
• The AI agent / AI model within Projects will use this additional context to answer the user's questions better.

Compared to adding Knowledge Base

Compared to the knowledge base (TypingMind Custom), the Dynamic Context will inject the content directly into the AI Agent/Project Context. This means the AI will not need to perform a lookup in order to get the desired content.

• Pros: The AI has access to the context at all times in full and no delay.
• Cons: More context length will be used.