A server setup that forwards incoming requests to another origin while keeping your public domain unchanged. Reverse proxies are used for migrations, custom routing, security policies, and integrating Framer with existing infrastructure. See How to self host using a reverse proxy.

Routing rules that internally map one URL path to another destination without changing the visible URL in the browser. Rewrites are useful for multi-site setups, legacy paths, and proxy-based integrations.

Structured Outputs enforce a specific response shape, often with schemas, so AI output can be parsed and consumed reliably by software.

Reasoning Effort is a controllable depth setting for model thinking, balancing answer quality, latency, and cost.

A Context Window is the maximum amount of tokens a model can process at once, including instructions, conversation history, and retrieved data.

Tool Calling is the capability for a model to decide when to call connected tools, then use tool results to complete a task.

Guardrails are technical and procedural constraints, such as filters and validators, that enforce safe and reliable AI behavior.

Related AI terms: Model Card and Content Credentials.

Evaluations (Evals) are benchmarked test suites used to track model behavior, regressions, and improvements against defined criteria.

Human-in-the-loop is an operating model where people validate, correct, or approve AI outputs before final execution.

Fine-tuning is supervised model adaptation on curated examples so behavior aligns more closely with domain-specific tasks.

Related AI terms: DreamBooth and Subject-Driven Generation.

Partner Models are external foundation models exposed through a single product interface. Product teams often combine them with Model Routing and governance artifacts like a Model Card.

A Model Card summarizes model behavior, scope, limitations, and known risks for operators and users. It supports safety controls such as Guardrails and helps teams reason about Hallucination risk.

An MCP host is the application that runs one or more MCP clients, manages connections, and makes responses from connected MCP servers available to the user or model.