456
topic · #ai

Everything about ai

121 connected nodes across dictionary, workflows, comparisons, prompts, tool stacks and use cases.

/ Dictionary · 88
DEFDictionaryNODE·4C13A3

AI Agent

An autonomous AI system that plans and executes multi-step tasks.

#ai#automation
/ai-agentopen →
DEFDictionaryNODE·72CB4B

RAG (Retrieval-Augmented Generation)

Inject external knowledge into an LLM at query time.

#ai#retrieval
/ragopen →
DEFDictionaryNODE·4EF5FF

Prompt Chaining

Pipelining LLM calls where each step's output feeds the next.

#ai#prompting
/prompt-chainingopen →
DEFDictionaryNODE·139612

LLM Orchestration

Coordinating multiple model calls, tools, and data sources into one reliable system.

#ai#architecture
/llm-orchestrationopen →
DEFDictionaryNODE·C49C81

Vector Database

A database optimized for similarity search over embeddings.

#ai#infrastructure
/vector-databaseopen →
DEFDictionaryNODE·6525CF

AI SDR (Sales Development Rep)

An autonomous system that researches, qualifies, and contacts leads.

#sales#ai
/ai-sdropen →
DEFDictionaryNODE·55B6DE

Vibe Coding

Building software by describing intent in natural language and letting AI generate the code.

#ai#development#no-code
/vibe-codingopen →
DEFDictionaryNODE·48DEBE

MCP (Model Context Protocol)

Open protocol that lets LLMs connect to tools, data sources and apps through a standard interface.

#ai#protocol#agents
/mcp-model-context-protocolopen →
DEFDictionaryNODE·5BFF00

Agentic RAG

RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.

#ai#retrieval#agents
/agentic-ragopen →
DEFDictionaryNODE·214A15

Embedding

A numerical vector representation of text, image or audio that captures meaning for similarity search.

#ai#infrastructure#retrieval
/embeddingopen →
DEFDictionaryNODE·6C8EA5

Fine-Tuning

Continuing to train a base model on your own examples to specialize its behavior.

#ai#training#models
/fine-tuningopen →
DEFDictionaryNODE·120E48

AEO (Answer Engine Optimization)

Optimizing content to be cited by AI answer engines like ChatGPT, Perplexity and Google AI Overviews.

#seo#ai#content
/aeo-answer-engine-optimizationopen →
DEFDictionaryNODE·24BFA3

Guardrails

Runtime checks that constrain LLM inputs and outputs to keep behavior safe and on-spec.

#ai#safety#ops
/guardrailsopen →
DEFDictionaryNODE·4C52C3

AI Evals

Reproducible test suites that measure LLM output quality across model, prompt and code changes.

#ai#ops#testing
/ai-evalsopen →
DEFDictionaryNODE·66E03E

Context Window

The maximum amount of text (in tokens) an LLM can consider in a single call.

#ai#models
/context-windowopen →
DEFDictionaryNODE·25E10B

Multimodal AI

Models that natively process more than one input type — text, images, audio, or video.

#ai#models
/multimodal-aiopen →
DEFDictionaryNODE·3A1E84

AI Orchestration

Coordinating multiple AI models, tools and steps into a single reliable workflow.

#ai#orchestration
/ai-orchestrationopen →
DEFDictionaryNODE·72CB36

LLM (Large Language Model)

A model trained on huge text corpora that predicts the next token to produce human-like language.

#ai#llm#fundamentals
/llmopen →
DEFDictionaryNODE·12B809

Token

The atomic unit an LLM reads and generates — roughly ¾ of a word in English.

#ai#fundamentals
/tokenopen →
DEFDictionaryNODE·6C17D5

Hallucination

When an LLM confidently generates false or fabricated information.

#ai#risk
/hallucinationopen →
DEFDictionaryNODE·43762E

Chain of Thought

Prompting an LLM to reason step-by-step before answering, often improving accuracy on hard tasks.

#ai#prompting
/chain-of-thoughtopen →
DEFDictionaryNODE·2DC662

Prompt Injection

An attack where hostile input hijacks the LLM's instructions, causing it to leak data or misbehave.

#ai#security#risk
/prompt-injectionopen →
DEFDictionaryNODE·59314E

Few-Shot Prompting

Showing the model 2–5 examples of the task inside the prompt so it mirrors the pattern.

#ai#prompting
/few-shot-promptingopen →
DEFDictionaryNODE·EF9AED

System Prompt

A high-priority instruction that sets the model's role, tone and constraints for the whole conversation.

#ai#prompting
/system-promptopen →
DEFDictionaryNODE·4E2543

Reranking

A second-pass model that reorders retrieved chunks by true relevance to the query.

#ai#rag
/rerankingopen →
DEFDictionaryNODE·6285C0

Chunking

Splitting documents into retrievable pieces before embedding them for RAG.

#ai#rag
/chunkingopen →
DEFDictionaryNODE·DC4BA8

AI Copilot

An in-product AI assistant that helps a user complete a task inside an existing workflow.

#ai#product
/ai-copilotopen →
DEFDictionaryNODE·53DB46

AI Router

A layer that picks the cheapest capable model for each request, saving cost and latency.

#ai#infra#cost
/ai-routeropen →
DEFDictionaryNODE·246590

Synthetic Data

AI-generated data used to train, test or evaluate models when real data is scarce or sensitive.

#ai#data
/synthetic-dataopen →
DEFDictionaryNODE·7C0FDD

Agentic Workflow

A workflow where an LLM decides the next step instead of a hard-coded path.

#ai#agents
/agentic-workflowopen →
DEFDictionaryNODE·4FAFE9

Tool Use

An LLM invoking external functions to act beyond text generation.

#ai#agents
/tool-useopen →
DEFDictionaryNODE·386095

Retrieval

Selecting the most relevant chunks for a query before generation.

#ai#retrieval
/retrievalopen →
DEFDictionaryNODE·2BCFA7

Reranker

A second-stage model that reorders retrieved chunks for precision.

#ai#retrieval
/rerankeropen →
DEFDictionaryNODE·4DE225

Hybrid Search

Combining keyword (BM25) and vector search for better recall.

#ai#retrieval
/hybrid-searchopen →
DEFDictionaryNODE·2B32AF

Chunk Size

The length of text segments stored in a vector index.

#ai#retrieval
/chunk-sizeopen →
DEFDictionaryNODE·302F7C

Temperature

The randomness knob on an LLM's output distribution.

#ai#prompting
/temperatureopen →
DEFDictionaryNODE·12B7FD

Top-p (Nucleus Sampling)

Restricting sampling to the smallest set of tokens whose probability sums to p.

#ai#prompting
/top-popen →
DEFDictionaryNODE·31F10D

JSON Mode

A model setting that guarantees valid JSON output.

#ai#prompting
/json-modeopen →
DEFDictionaryNODE·138860

Evals

Automated tests that grade LLM outputs against expected behavior.

#ai#quality
/evalsopen →
DEFDictionaryNODE·59C631

Jailbreak

A prompt crafted to bypass a model's safety alignment.

#ai#security
/jailbreakopen →
DEFDictionaryNODE·1C505A

Cosine Similarity

The dot-product-of-unit-vectors metric that ranks embeddings.

#ai#retrieval
/cosine-similarityopen →
DEFDictionaryNODE·60C80C

Vector Index

A data structure that makes nearest-neighbor search fast.

#ai#retrieval
/vector-indexopen →
DEFDictionaryNODE·5B771E

Entity Extraction

Pulling structured entities (people, places, orgs, dates) from text.

#ai#extraction
/entity-extractionopen →
DEFDictionaryNODE·EBE0A1

Summarization

Compressing text while preserving meaning and structure.

#ai#content
/summarizationopen →
DEFDictionaryNODE·2737A3

Transcription (ASR)

Converting speech audio into text.

#ai#audio
/transcriptionopen →
DEFDictionaryNODE·3A50D4

Text-to-Speech (TTS)

Generating natural-sounding audio from text.

#ai#audio
/text-to-speechopen →
DEFDictionaryNODE·873CB9

Multimodal Model

A model that reads and reasons across text, images, audio, and video.

#ai#multimodal
/multimodal-modelopen →
DEFDictionaryNODE·395EF6

Vision Model

A model that interprets images as first-class input.

#ai#multimodal
/vision-modelopen →
DEFDictionaryNODE·310655

Long-Term Memory

Persistent state an agent carries between sessions.

#ai#agents
/long-term-memoryopen →
DEFDictionaryNODE·71B899

Episodic Memory

Session-scoped memory of specific past events.

#ai#agents
/episodic-memoryopen →
DEFDictionaryNODE·2B4D79

Quantization

Shrinking a model by lowering weight precision.

#ai#infra
/quantizationopen →
DEFDictionaryNODE·516445

Inference

Running a trained model to produce outputs.

#ai#infra
/inferenceopen →
DEFDictionaryNODE·626DE6

Streaming

Returning tokens as they are generated instead of waiting for completion.

#ai#ux
/streamingopen →
DEFDictionaryNODE·5B950E

Cost Per Token

The unit economics of LLM APIs.

#ai#economics
/cost-per-tokenopen →
DEFDictionaryNODE·775C66

Model Routing

Sending each request to the cheapest model that can handle it.

#ai#infra
/model-routingopen →
DEFDictionaryNODE·45B225

Moderation

Filtering unsafe input or output before it reaches users.

#ai#safety
/moderationopen →
DEFDictionaryNODE·3D79F9

PII Redaction

Stripping personally identifiable information before sending to a model.

#ai#privacy
/pii-redactionopen →
DEFDictionaryNODE·386DF7

Provenance

The trace of where a generated artifact came from.

#ai#compliance
/provenanceopen →
DEFDictionaryNODE·58B9C0

Embedding Dimensions

The vector length of an embedding model's output.

#ai#retrieval
/embedding-dimensionsopen →
DEFDictionaryNODE·5A9BB6

Context Caching

Reusing pre-processed input across requests to cut cost and latency.

#ai#economics
/context-cachingopen →
DEFDictionaryNODE·793BCB

Structured Generation

Constraining decoding to match a schema at every token.

#ai#prompting
/structured-generationopen →
DEFDictionaryNODE·33A8E0

Planner-Executor Pattern

Splitting agents into a planner LLM and a smaller executor LLM.

#ai#agents
/planner-executoropen →
DEFDictionaryNODE·3F3788

Self-Consistency

Sampling multiple answers and picking the majority to reduce errors.

#ai#prompting
/self-consistencyopen →
DEFDictionaryNODE·1EF41E

Reflection

An agent critiquing and revising its own output before returning.

#ai#agents
/reflectionopen →
DEFDictionaryNODE·D270FD

Prompt Template

A reusable prompt with named variables filled at runtime.

#ai#prompting
/prompt-templateopen →
DEFDictionaryNODE·160DD5

Prompt Versioning

Treating prompts as code: tracked, diffed, rollback-able.

#ai#ops
/prompt-versioningopen →
DEFDictionaryNODE·286E40

LLM Observability

Tracing every prompt, tool call, and token in production.

#ai#ops
/observabilityopen →
DEFDictionaryNODE·5206B1

LLM-as-Judge

Using a strong model to grade another model's output.

#ai#quality
/llm-judgeopen →
DEFDictionaryNODE·4D2771

Chain-of-Thought Prompting

Instructing a model to think step by step before answering.

#ai#prompting
/cot-promptingopen →
DEFDictionaryNODE·6851B5

Zero-Shot Prompting

Asking a model to do a task with no examples in the prompt.

#ai#prompting
/zero-shotopen →
DEFDictionaryNODE·1961BA

RLHF

Reinforcement learning from human feedback, the alignment technique behind ChatGPT.

#ai#training
/rlhfopen →
DEFDictionaryNODE·72CB18

DPO (Direct Preference Optimization)

A simpler alternative to RLHF that skips the reward model.

#ai#training
/dpoopen →
DEFDictionaryNODE·2CDB38

Model Distillation

Training a small model to mimic a large one.

#ai#training
/distillationopen →
DEFDictionaryNODE·196468

LoRA

Low-Rank Adaptation: cheap fine-tuning that patches only small matrices.

#ai#training
/loraopen →
DEFDictionaryNODE·6EE0DC

Function Calling

The API mechanism that lets a model request a tool call.

#ai#agents
/function-callingopen →
DEFDictionaryNODE·758727

MCP (Model Context Protocol)

Open standard letting AI clients call external tools, data and prompts.

#ai#protocol#agents
/model-context-protocolopen →
DEFDictionaryNODE·7DC568

Computer-Use Agent

An AI agent that controls a desktop or browser via screenshots and clicks.

#ai#agents#automation
/computer-use-agentopen →
DEFDictionaryNODE·4B108E

Deep Research (AI)

Long-running AI research task that produces a cited multi-page report.

#ai#research#agents
/deep-researchopen →
DEFDictionaryNODE·3EC772

Claude Code

Anthropic's terminal-native coding agent that edits real codebases.

#ai#coding#agents
/claude-codeopen →
DEFDictionaryNODE·D86938

Agent Architecture

Agent architecture is the structural blueprint of an AI agent: the model, the planning loop, the tools, the memory layer and the guardrails that decide how it acts.

#ai-agents#architecture#ai
/agent-architectureopen →
DEFDictionaryNODE·153648

MCP Server

An MCP server exposes tools, resources and prompts from one system so any MCP-compatible AI client can use them over a standard protocol.

#mcp#ai#integration
/mcp-serveropen →
DEFDictionaryNODE·5B8F33

MCP Client

An MCP client is the AI-side host that discovers servers, lists their tools and routes the model's calls to them.

#mcp#ai#integration
/mcp-clientopen →
DEFDictionaryNODE·3A9036

MCP Tools

MCP tools are typed, described functions an AI model can call — the unit of capability that decides whether an agent is useful or dangerous.

#mcp#tools#ai
/mcp-toolsopen →
DEFDictionaryNODE·D71EDC

MCP Resources

MCP resources are addressable read-only context — files, records, docs — that a client can pull into the model instead of calling a tool.

#mcp#context#ai
/mcp-resourcesopen →
DEFDictionaryNODE·4569E4

Research Automation

Research automation turns a question into a sourced, structured answer using search, retrieval, extraction and synthesis agents.

#automation#research#ai
/research-automationopen →
DEFDictionaryNODE·15ADB2

Document Extraction Agent

A document extraction agent reads unstructured files — PDFs, scans, emails — and returns validated structured data.

#automation#documents#ai
/document-extraction-agentopen →
DEFDictionaryNODE·18141C

Context Engineering

Context engineering is the discipline of deciding exactly what information enters a model's context window, in what order and at what cost.

#ai-development#context#ai
/context-engineeringopen →
DEFDictionaryNODE·263D26

AI Security

AI security protects systems where the model is an untrusted decision-maker acting on untrusted input with real tool access.

#ai-ops#security#ai
/ai-securityopen →
/ Comparisons · 26
VSComparisonNODE·411C54

ChatGPT vs Claude

Two leading conversational AI assistants compared across reasoning, writing, coding, and pricing.

#ai#tools
/chatgpt-vs-claudeopen →
VSComparisonNODE·6EE9B7

Lovable vs Bolt

Two AI app builders compared on speed, backend, deployment, and production readiness.

#ai#no-code#development
/lovable-vs-boltopen →
VSComparisonNODE·2D5E86

OpenAI API vs Anthropic API

Choosing between the two leading LLM API providers for production apps.

#ai#models#comparison
/openai-vs-anthropic-apiopen →
VSComparisonNODE·5D664C

Lovable vs Cursor

Prompt-to-app builder vs AI-assisted code editor — which one should you reach for?

#ai#builders#comparison
/lovable-vs-cursoropen →
VSComparisonNODE·41C517

Perplexity vs ChatGPT Search

Two answer engines, two philosophies: citation-first research vs conversational assistant.

#ai#search
/perplexity-vs-chatgpt-searchopen →
VSComparisonNODE·673D22

OpenAI vs Gemini for Agent Building

Both ship strong models and SDKs — differences are in tool calling, context and pricing.

#ai#models
/openai-vs-gemini-for-agentsopen →
VSComparisonNODE·2675FB

RAG vs Long Context Windows

Is RAG obsolete now that context windows are 1M+ tokens? Not quite — here's when each wins.

#ai#rag#architecture
/rag-vs-long-contextopen →
VSComparisonNODE·652548

LangChain vs LlamaIndex

Both are Python/JS frameworks for LLM apps. LangChain leans agents; LlamaIndex leans RAG.

#ai#frameworks
/langchain-vs-llamaindexopen →
VSComparisonNODE·6F31CE

Best AI Workflow Automation Tools: n8n vs Zapier vs Make

The three tools most operators consider for AI workflow automation — compared on pricing, AI integration and technical flexibility.

#automation#ai#comparison
/ai-automation-platformsopen →
VSComparisonNODE·26A503

Claude vs GPT vs Gemini

The three frontier model families, side by side.

#ai#models
/claude-vs-gpt-vs-geminiopen →
VSComparisonNODE·2EE290

Claude Sonnet vs Opus

When to spend up within the Claude family.

#ai#models
/sonnet-vs-opusopen →
VSComparisonNODE·55FB85

Llama vs Mistral

Two leading open-weight families.

#ai#open-source
/llama-vs-mistralopen →
VSComparisonNODE·163F3A

OpenAI vs Anthropic for Agents

Which provider builds better production agents in 2026.

#ai#agents
/openai-vs-anthropic-for-agentsopen →
VSComparisonNODE·241C40

Groq vs Together AI

Fast open-model inference: throughput vs breadth.

#ai#infra
/groq-vs-togetheropen →
VSComparisonNODE·1DABAB

ElevenLabs vs Play.ht

The two leading TTS platforms compared.

#ai#audio
/elevenlabs-vs-playhtopen →
VSComparisonNODE·4C4CF0

Whisper vs Deepgram

Open-weight accuracy vs streaming-first speed.

#ai#audio
/whisper-vs-deepgramopen →
VSComparisonNODE·1B2D6B

LangChain vs Vercel AI SDK

Kitchen-sink orchestration vs lean SDK for shipping apps.

#ai#dev
/langchain-vs-vercel-ai-sdkopen →
VSComparisonNODE·14FB0A

CrewAI vs AutoGen vs LangGraph

Three approaches to multi-agent orchestration.

#ai#agents
/crewai-vs-autogen-vs-langgraphopen →
VSComparisonNODE·1025BA

Chroma vs Qdrant vs Pinecone

Open-source local vs managed cloud vector databases.

#ai#infra
/chroma-vs-qdrant-vs-pineconeopen →
VSComparisonNODE·1F8A2B

Ollama vs LM Studio

Two ways to run LLMs locally on a laptop.

#ai#local
/ollama-vs-lm-studioopen →
VSComparisonNODE·665DF6

Cursor vs Windsurf vs GitHub Copilot

Three AI coding environments.

#dev#ai
/cursor-vs-windsurf-vs-copilotopen →
VSComparisonNODE·7654ED

Midjourney vs Ideogram vs Flux

Three image models with different strengths.

#ai#image
/midjourney-vs-ideogram-vs-fluxopen →
VSComparisonNODE·416539

Runway vs Kling vs Veo

State-of-the-art AI video generators in 2026.

#ai#video
/runway-vs-kling-vs-veoopen →
VSComparisonNODE·2DE7AE

Perplexity vs You.com vs SearchGPT

Three AI-first search engines compared.

#ai#search
/perplexity-vs-you-vs-searchgptopen →
VSComparisonNODE·3F445C

Cursor Agents vs Devin vs Lovable

Three ways AI writes code for you in 2026.

#dev#ai
/cursor-agents-vs-devin-vs-lovableopen →
VSComparisonNODE·F1E18A

Grok vs ChatGPT: Which Assistant Wins in 2026

Real-time X-native model vs the default all-rounder — different strengths for different jobs.

#ai#comparison#chatbots
/grok-vs-chatgptopen →
/ Workflows · 6
/ Tool Stacks · 1