Glossary

    AI & SaaS
    glossary.

    Short, accurate definitions of the terms that come up when building AI products and SaaS platforms.

    AI Agent
    Software that uses a large language model to choose steps and tools to complete a task, such as looking up data, calling an API and drafting a response.
    Related service →
    RAG (Retrieval-Augmented Generation)
    A technique where an AI system retrieves relevant passages from a document collection and uses them to generate a grounded answer, often with citations.
    Related service →
    LLM (Large Language Model)
    A neural network trained on large amounts of text that can generate and analyze language. Examples include GPT, Claude, Gemini and Llama.
    Related service →
    Vector Database
    A database that stores embeddings and finds the most similar items to a query by distance. PostgreSQL with the pgvector extension is a common choice.
    Related service →
    Embeddings
    Lists of numbers that represent the meaning of text or images, so that similar content has similar vectors. Used for semantic search and RAG.
    Related service →
    Tool Calling / Function Calling
    A model capability where the LLM returns a structured request to run a named function with arguments; the application runs it and returns the result to the model.
    Related service →
    Structured Outputs
    Constraining a model's response to a defined schema (for example JSON with specific fields) so the application can safely parse and store it.
    Related service →
    AI SaaS
    A software-as-a-service product whose core value is delivered by AI features, combined with standard SaaS parts: accounts, billing, dashboards and admin.
    Related service →
    Multi-Tenant SaaS
    An architecture where one application serves many customer organizations (tenants) while keeping each tenant's data isolated.
    Related service →
    FastAPI
    A Python web framework for building typed, asynchronous APIs with automatic OpenAPI documentation.
    Related service →
    Django
    A mature Python web framework with a built-in ORM, authentication and admin interface.
    Related service →
    API
    An application programming interface: a defined set of requests one program can make to another, commonly over HTTP as REST or GraphQL.
    Related service →
    Webhook
    An HTTP request a service sends to your application when an event happens, such as Stripe notifying you that a payment succeeded.
    Related service →
    RBAC (Role-Based Access Control)
    A permission model where users are assigned roles and each role grants a set of allowed actions.
    Related service →
    Stripe Connect
    Stripe's product for marketplaces and platforms that need to onboard sellers and route payouts to them while taking a platform fee.
    Related service →
    Supabase
    An open-source backend platform built on PostgreSQL that provides a database, authentication, storage and realtime features.
    Related service →
    Row-Level Security (RLS)
    A PostgreSQL feature that filters which rows each user can read or change using policies enforced by the database itself.
    Related service →