A practical knowledge base for AI protocols, agents, core concepts, frameworks, and tools.
Learn what MCP Tasks means and how it is used. MCP Tasks is an official MCP extension for asynchronous long-running tool calls. A server returns a task handle first; the client can then check status, provide more input when supported, and retrieve the result after completion instead of holding one request open.
Learn what Loop Engineering means and how it is used. Loop Engineering means you stop writing prompts for an AI Agent one at a time and instead design a system that finds its own work, runs it, and checks the results. You move from being the person who asks to being the person who designs the loop, its goals, its acceptance criteria, and its fallbacks.
Learn what Context Compaction means and how it is used. Context Compaction is what happens when a long session is about to fill the context window: the system swaps earlier history for a summary that keeps progress, conclusions, and next steps while discarding verbose tool output, so the task can keep running instead of being forced to restart.
Learn what Context Engineering means and how it is used. Context Engineering is about deciding, within a finite context window, which information actually goes into the model each turn: system instructions, tool definitions, retrieved material, message history, external memory. What it cares about isn't wording but the selection and organization of information.
Learn what Agentic AI means and how it is used. Agentic AI refers to the class of AI systems that don't just generate content but plan their own steps, call tools, adjust based on results, and see a task through. The dividing line with generative AI is whether the output is content or action.
Learn what Evals means and how it is used. Evals are tests for an AI system: give it a set of inputs, then apply grading logic to judge whether the output is good. They turn "it feels worse this week" into a reproducible, comparable score you can gate a pipeline on — the precondition for daring to change a prompt or swap a model.
Learn what MoE (Mixture of Experts) means and how it is used. MoE (Mixture of Experts) splits a model's feed-forward layers into many "experts" and has a router decide which few each token passes through. Total parameter count can be enormous while only a small fraction actually computes on any given step.
Learn what Test-time Compute means and how it is used. Test-time Compute means spending more computation at the moment you ask, in exchange for accuracy: letting the model think longer, try several paths, and check its own work. It changes no parameters and requires no retraining — it's the mechanism behind 2026's reasoning models answering better by thinking longer.
Learn what Subagent means and how it is used. A Subagent is an independent instance the main agent dispatches: its own context window, its own tool permissions, returning only a conclusion so the digging never pollutes the main session. The core problem it solves is who gets to spend the context.
Learn what World Model means and how it is used. A World Model is a model that can internally simulate how an environment changes in response to actions: give it a current state and an action, and it predicts what happens next. Language models predict the next word; world models predict the next state.
Learn what Agent Skills means and how it is used. Agent Skills is an open format for packaging "how to do this" for an AI: a folder plus a SKILL.md spelling out the procedure, with scripts and reference material alongside. MCP lets an agent use tools; Skills teach it what to do with them.
Learn what Guardrails means and how it is used. Guardrails are the validation and control layers wrapped around a model's inputs, tool calls, and outputs: check before the model, validate after it, intercept before an action executes. They run outside the model's context, so "ignore previous instructions" can't route around them.
Showing 12 of 12 entries
Every entry grouped by topic — one click straight to the explanation.
