Tag
AI
67 entries tagged AI · 67 terms.
Dictionary
Adaptive Thinking
An inference behavior where a frontier model self-scales its reasoning depth and tool-use budget to match the complexity of the prompt, without the operator flipping a manual extended-thinking or test-time-compute switch.
Agent Client Protocol
An open protocol that lets AI coding agents communicate with editors and IDEs in a standardized way, so the same agent can run inside Cursor, Devin Desktop, Zed, or any other compliant client.
Agent Confidence Score
A calibrated reliability rating attached to an AI agent's output, used to decide whether the result is safe to ship or must be routed to a human reviewer.
Agent Control Surface
The user interface that lets a human watch, approve, and redirect an AI agent that is running somewhere else, while the underlying work stays on the machine where the agent lives.
Agent Registry
A centralized directory that catalogs every AI agent operating within a system, assigns each one a verifiable identity, and tracks what each agent is authorized to do.
Agentic Browser
A web browser whose default surface is an AI agent that takes multi-step actions on the user's behalf across pages, not just a search box or a chatbot stapled to the sidebar.
Agentic Coding
A style of software development where an AI agent writes, edits, and manages code semi-autonomously while a human operator guides the direction.
Agentic Commerce
The pattern where an AI agent, not a human, executes the search, decision, checkout, and after-sales steps of a purchase on a user's behalf.
Agentic Workforce
The staffing pattern in which AI agents are counted alongside humans as productive units of an enterprise's labor capacity, with managers allocating work to whichever resource is faster, cheaper, or available.
AI Agent
An AI system that can take actions on its own, using tools and making decisions across multiple steps to accomplish a goal.
AI Pair Programming
Working alongside an AI assistant that helps you write, review, and debug code in real time as a collaborative partner.
Ambient Agent
An AI agent that runs persistently in the background of a workspace, watches the user's activity without being prompted, and takes initiative on what it sees.
Autonomous Software Engineer
An AI system sold as a unit of engineering labor rather than a coding assistant: you assign it a task and it plans, writes, tests, and submits the work for review on its own.
Background Agent
An AI agent that runs continuously on a remote server, executing tasks on a user's behalf even when the client device is closed.
Chain of Thought
A prompting technique that asks the AI to show its reasoning step by step, which leads to more accurate and reliable answers.
Claude
An AI assistant built by Anthropic, known for strong reasoning, long context windows, and a focus on safety.
Computer-Use Model
A foundation model purpose-built to operate software the way a person does, by clicking, typing, navigating menus, and manipulating files, rather than producing chat or code.
Content Credentials
A cryptographically signed provenance record that travels with a piece of media to say how, when, and by whom it was created or modified, including whether AI was involved.
Content Pipeline
An automated system that researches, creates, reviews, and publishes content through a series of connected steps with minimal manual intervention.
Context Engineering
The practice of designing the entire information ecosystem around an AI model (what it sees, what it remembers, what tools it can use) to produce consistently better results.
Context Window
How much an AI can 'remember' in a single conversation. Think of it as the AI's working memory.
Conversational Advertising
The practice of placing paid sponsored content inside the response surface of an AI chat product, where ads appear within the model's answer flow rather than above search results or alongside page content.
Conversational Commerce
The practice of discovering, comparing, and buying products inside a conversational AI interface rather than on a traditional website or app.
Credit Pool
A dollar-denominated monthly allotment that meters programmatic AI usage at API list prices, separate from the chat subscription that ships with the same plan, and that does not roll over between months.
Default Model
The model that a chat product silently serves to users who have not specified one, rotating beneath them without notice as providers update their infrastructure.
Drift
When an AI gradually loses track of your project's goals and starts making suggestions that don't fit anymore, usually because it's forgotten earlier context.
Embedded AI
The practice of AI capabilities moving into the response surface of existing productivity tools rather than living as a standalone application the user switches to.
Embeddings
A way of converting text into numbers so that AI can measure how similar or related different pieces of content are.
Fine-Tuning
The process of taking a pre-trained AI model and training it further on specific data to make it better at a particular task.
Frontier Lab
A small set of AI organizations training and operating the largest, most capable models at the boundary of current research, with the compute and capital to push that boundary forward.
Frontier Model
A frontier model is one of the most capable AI systems in existence at a given moment, advanced enough that its risks are not yet fully understood.
Hallucination
When an AI model confidently generates information that is incorrect, fabricated, or nonsensical.
In-Memory Compute
A processor architecture that performs calculations directly inside the memory cells holding the data, eliminating the round trip to a separate compute unit.
Indirect Prompt Injection
An attack that hides instructions inside content an AI agent reads, such as a web page or an email, so the agent executes them as if the user had given the command.
Inference
The process of an AI model generating a response to your input, as opposed to the training phase when it originally learned.
LangChain
An open-source framework that helps developers build applications powered by language models, especially multi-step AI workflows.
Large Language Model (LLM)
An AI system trained on massive amounts of text that can understand and generate human language.
Long-Horizon Agent
An AI agent designed to sustain coherent action across many steps and long elapsed time without losing the thread of the task it was given.
Managed Agent
An AI agent hosted by a platform (most commonly Anthropic's infrastructure) rather than running inside a personal terminal session. A Managed Agent persists beyond the operator's session, exposes a stable invocation surface (an API call or a button in an internal app), and reaches external systems through a governed tool gateway.
Memory Consolidation
The background process by which an AI assistant rewrites and merges short-term context, saved facts, and prior chats into a smaller, cleaner, longer-lived store the model can use later.
Model Context Protocol (MCP)
An open standard that lets AI models connect to external tools and data sources through a unified interface.
Model Jailbreak
A crafted input sequence that bypasses a model's safety guardrails and produces outputs the model was trained or filtered to refuse.
Model Routing
The practice of sending different tasks to different AI models based on complexity, cost, and speed requirements.
OpenAI
The company behind ChatGPT and the GPT series of AI models, one of the leading providers of large language models.
Personal AI
AI configured to stay with one operator across all their tools and contexts, building a persistent memory of work patterns instead of starting fresh per session.
Plan Mode
A structured scoping process in AI coding tools that interviews you about your project before any code gets written, producing a clear plan that prevents wasted effort.
Pre-Deployment Evaluation
The practice of an outside party, often a government body, testing a frontier AI model for dangerous capabilities before it is released to the public.
Private Cloud Compute
Apple's server-side compute architecture for Apple Intelligence requests too large for on-device processing, designed so Apple itself cannot read the input.
Project Memory
Systems that help AI tools remember past decisions and project context across sessions, surviving context window resets so you don't have to re-explain your project every time.
Prompt Engineering
The skill of writing clear, structured instructions to get better and more consistent results from AI models.
Recursive Self-Improvement
The threshold at which an AI system can autonomously design, train, and ship a more capable version of itself, with each new generation authored by the previous one rather than by human engineers.
Retrieval-Augmented Generation (RAG)
A technique that feeds relevant documents to an AI model at query time so it can answer questions using your actual data instead of guessing.
Safety Classifier
An in-model mechanism that detects when a query falls into a high-risk category and reroutes it to a safer model or refuses it outright.
Skill
A saved instruction file that an AI tool reads each time you invoke it, producing consistent output across runs without requiring the operator to remember and retype a long prompt. In Claude Code, Skills live at ~/.claude/skills/<name>/SKILL.md and are invoked by typing /<name>.
Sovereign AI
The practice of governments running their own LLM training and inference infrastructure inside national borders to keep model weights, data, and compute under domestic jurisdiction.
Structured Output
AI responses formatted in a predictable, machine-readable structure like JSON, so other software can reliably process the results.
Subagent
An autonomous AI agent that a parent agent spawns to handle one bounded task, usually in parallel with sibling subagents, then return a structured result for the parent to synthesize.
System Prompt
Hidden instructions given to an AI model that define its personality, rules, and behavior before the user ever sends a message.
Temperature
An AI setting that controls how creative or predictable the model's responses are, on a scale from 0 to 1 (or higher).
Token
The small chunks of text that AI models read and generate, roughly three-quarters of a word each.
Tool Use (AI Tool Calling)
The ability of an AI model to call external functions and services during a conversation, going beyond text generation to take real actions.
Training Data
The massive collection of text, code, and other content that an AI model learns from before it can generate responses.
Transformer
A neural network architecture, introduced in 2017, that uses attention mechanisms to process sequences of tokens in parallel and powers every modern large language model.
Usage-Based Pricing
A billing model that meters each AI prompt, token, or task against a per-model rate card instead of bundling unlimited usage into a flat subscription.
Vibe Coding
A casual approach to building software with AI where you describe what you want in plain language and let the AI handle the implementation details.
Wafer-Scale Engine
A processor built from an entire silicon wafer rather than smaller chips diced from one, integrating dramatically more on-chip memory and compute cores to eliminate the chip-to-chip communication bottleneck that limits conventional GPU clusters at inference time.
Zero-Day
A software vulnerability that is exploited or disclosed before the people responsible for fixing it know it exists, leaving zero days to patch.