HyperText Transfer Protocol Secure—encrypted web communication that protects data between browsers and servers. HTTPS is now essential for security, SEO rankings, and enabling modern browser features. Framer provides free SSL certificates for automatic HTTPS on all sites.

Internet Protocol address—a numerical label identifying devices on a network, like 192.168.1.1 or a longer IPv6 format. IP addresses enable communication between devices and can provide geographic location data for analytics. CDNs route traffic based on IP to serve content from nearby servers.

System for Cross-domain Identity Management, a standard protocol for automating user provisioning and deprovisioning between identity providers and SaaS products. SCIM helps keep account access in sync with organizational directories.

An MCP Server is a service that implements the Model Context Protocol, making external capabilities available to compatible AI agents.

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.

Retrieval-Augmented Generation (RAG) enriches model outputs by fetching external knowledge at runtime and conditioning generation on it.

Grounding is the practice of constraining generation with verifiable sources so outputs are accurate, attributable, and context-specific.

Hallucination refers to model outputs that sound plausible but are unsupported or false, often due to missing or weak source context.

Prompt Injection is an adversarial technique that embeds manipulative instructions in user or retrieved content to subvert model behavior.

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.

Model Routing is the strategy of directing requests to the most suitable model dynamically using policy and workload rules.

Related AI terms: Partner Models and Model Card.

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 client is the part of an app or MCP server and requests tools, resources, or prompts using Model Context Protocol (MCP).agent that connects to an

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.

A local MCP server is an MCP server that runs on the same machine as the MCP host, usually for low-latency access to local files, apps, or developer tools.

A hosted MCP server is a remote MCP server operated by a provider, letting an MCP client connect to tools or data without installing the server locally.

Real-time or on-demand suggestions provided by an AI model as a developer types, ranging from single-word completions to entire function bodies. Modern tools like GitHub Copilot and Cursor use large language models to infer intent from surrounding code and comments. Code completion reduces keystrokes, surfaces patterns, and helps developers stay in flow—while requiring judgment about whether suggestions are correct and appropriate.

An AI model integrated into a developer’s editor that participates in the coding process like a human pair—suggesting next steps, flagging potential bugs, explaining unfamiliar APIs, and generating boilerplate. GitHub Copilot popularized the term. Unlike agentic tools, an AI pair programmer typically acts reactively as the developer types rather than planning multi-step tasks autonomously.