Building with AI

https://ecosystem.samcarlton.com/ai
Last changed: 2026-11-14. Dates track content changes, not independent source checks.

Use your browser’s Print command to print this list.

• AI

  Concept

  Artificial intelligence.

  Last changed: 2026-11-15

• LLM

  Concept

  Large language model.

  Last changed: 2026-11-14

• Model

  Concept

  The trained system at the center of an AI product.

  Last changed: 2026-11-14

• Training

  Concept

  Teaching an AI model by showing it a very large number of examples before anyone uses it.

  Last changed: 2026-11-14

• AI agent

  Concept

  An AI tool that does more than answer a question.

  Last changed: 2026-11-14

• Prompt

  Concept

  The instructions or question you give an AI tool in everyday words.

  Last changed: 2026-11-14

• Context window

  Concept

  How much text an LLM can take into account at one time.

  Last changed: 2026-11-14

• No-code

  Concept

  Tools that let you build an app or site by arranging visual blocks or describing what you want…

  Last changed: 2026-11-14

• Coding agent

  Concept

  An AI agent that writes and changes code.

  Last changed: 2026-11-14

• Inference

  Concept

  An AI model producing an answer to a request.

  Last changed: 2026-11-14

• Hallucination

  Concept

  When an AI model states something false or invented as though it were true.

  Last changed: 2026-11-14

• Local model

  Concept

  A model that is downloaded and run on a person's own computer or a company's own servers, not on a…

  Last changed: 2026-11-14

• RAG

  Concept

  Retrieval-augmented generation.

  Last changed: 2026-11-14

• Evals

  Concept

  Tests that check whether the outputs of a model or an AI product meet the criteria its builders set.

  Last changed: 2026-11-14

• Token

  Concept

  In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.

  Last changed: 2026-11-14

• Vibe coding

  Concept

  Building software by describing what you want to an AI tool and accepting the code it writes…

  Last changed: 2026-11-14

• AI chat assistant

  Concept

  A finished app where a person types or talks to an AI model and gets replies in conversation.

  Last changed: 2026-11-14

• Speech-to-text

  Concept

  Software that turns spoken words into written text.

  Last changed: 2026-11-14

• Tool use

  Concept

  A way for a model to ask the software around it to run a defined action, such as a search or a…

  Last changed: 2026-11-14

• AI use policy

  Concept

  An organization's rules for which AI tools its people may use and what information they may put…

  Last changed: 2026-11-14

• Embedding

  Concept

  A way of turning a piece of text into a list of numbers that captures its meaning, so software can…

  Last changed: 2026-11-14

• Session

  Concept

  One stretch of work with an AI agent, from a blank start until it is cleared, closed or compacted.

  Last changed: 2026-11-14

• AFK

  Concept

  Short for away from keyboard.

  Last changed: 2026-11-14

• AGENTS.md

  Concept

  A plain text file in a project that many coding agents read automatically at the start of every…

  Last changed: 2026-11-14

• AI safety

  Concept

  The work of making AI systems behave safely and of measuring how safe they are.

  Last changed: 2026-11-14

• Frontier model

  Concept

  One of the most capable general-purpose AI models available at a given time.

  Last changed: 2026-11-14

• GPU

  Concept

  Graphics processing unit.

  Last changed: 2026-11-14

• Human in the loop

  Concept

  Designing an AI process so a person reviews, approves or corrects the AI's work at key steps…

  Last changed: 2026-11-14

• Open source vs open weights

  Concept

  Two labels for AI models that people often mix up.

  Last changed: 2026-11-14

• Weights

  Concept

  The numbers inside a model that it learned during training.

  Last changed: 2026-11-14

• Model provider

  Concept

  The company or service that runs an AI model and answers requests to it, usually over the internet…

  Last changed: 2026-11-14

• System prompt

  Concept

  Standing instructions that the builder of an AI product gives the model before any user types.

  Last changed: 2026-11-14

• Vector database

  Concept

  A database built to store embeddings and quickly find the items closest in meaning to a question…

  Last changed: 2026-11-14

• Agent skills

  Concept

  A packaged set of instructions, sometimes with scripts, that an agent loads when a task calls for…

  Last changed: 2026-11-14

• Fine-tuning

  Concept

  Extra training of an existing model on a smaller, narrower set of examples, so it suits one task…

  Last changed: 2026-11-14

• Harness

  Concept

  The software wrapped around an AI model that turns it into a working agent.

  Last changed: 2026-11-14

• Multimodal

  Concept

  Describes a model that works with more than one type of content, such as text plus images or audio.

  Last changed: 2026-11-14

• Subagent

  Concept

  A second agent that the main agent starts to handle one piece of a job in its own separate session.

  Last changed: 2026-11-14

• Automated check

  Concept

  A test or rule a computer runs to catch problems without a person looking, such as tests, type…

  Last changed: 2026-11-14

• Clearing

  Concept

  Ending a session and starting a completely empty one.

  Last changed: 2026-11-14

• Guardrails

  Concept

  Checks and limits built around a model inside a product.

  Last changed: 2026-11-14

• Input tokens

  Concept

  The tokens an AI product sends to the model on each request: the instructions, the conversation so…

  Last changed: 2026-11-14

• Neural network

  Concept

  A kind of software model made of many layers of simple math units connected by weights, loosely…

  Last changed: 2026-11-14

• Sandbox

  Concept

  A walled-off space where an agent can run commands and change files without reaching the rest of…

  Last changed: 2026-11-14

• Spec

  Concept

  A written description of what is being built and why, for work too big to finish in one session.

  Last changed: 2026-11-14

• Transformer

  Concept

  The design that most modern language models are built on, introduced by Google researchers in 2017.

  Last changed: 2026-11-14

• Agent environment

  Concept

  Everything outside the agent's own software that it can look at or change: your files, terminal…

  Last changed: 2026-11-14

• AI literacy

  Concept

  Enough understanding of AI to use it well and safely: what it is good and bad at, how to write a…

  Last changed: 2026-11-14

• Attention

  Concept

  The part of a language model that decides, for each token, how much every other token in the input…

  Last changed: 2026-11-14

• Compaction

  Concept

  Shrinking a long session by replacing its history with a summary and carrying on from that summary…

  Last changed: 2026-11-14

• Handoff artifact

  Concept

  The written document that carries a handoff, produced by one session for another to read.

  Last changed: 2026-11-14

• Latent space

  Concept

  The internal map of numbers where a model places the things it reads.

  Last changed: 2026-11-14

• Memory system

  Concept

  A setup that tries to give an agent memory across sessions by saving notes to files or a database…

  Last changed: 2026-11-14

• Model provider request

  Concept

  One trip from an AI product to the model provider and back.

  Last changed: 2026-11-14

• Next-token prediction

  Concept

  The one job a language model performs.

  Last changed: 2026-11-14

• Parameters

  Concept

  The values a model learns during training.

  Last changed: 2026-11-14

• Probabilistic vs deterministic

  Concept

  Deterministic software gives the same output for the same input every time.

  Last changed: 2026-11-14

• Progressive disclosure

  Concept

  Giving an agent only what it needs right now, with pointers to the rest, instead of loading…

  Last changed: 2026-11-14

• Prompt injection

  Concept

  A security weakness in AI products.

  Last changed: 2026-11-14

• Smart zone

  Concept

  A name for the early part of a session, when an agent is focused and accurate.

  Last changed: 2026-11-14

• Sycophancy

  Concept

  The habit AI models have of telling you what you want to hear: agreeing too readily, praising weak…

  Last changed: 2026-11-14

• Attention budget

  Concept

  A way of picturing attention as a fixed amount each token can spread across everything else in the…

  Last changed: 2026-11-14

• Attention degradation

  Concept

  The drop in an agent's sharpness as a session gets long.

  Last changed: 2026-11-14

• Automated review

  Concept

  Having an AI model read and critique work, usually code, before a person does.

  Last changed: 2026-11-14

• Benchmark

  Concept

  A shared, public test used to score different models on the same tasks so they can be compared.

  Last changed: 2026-11-14

• Contextual knowledge

  Concept

  Facts the model can read directly in front of it right now, such as documents you pasted, files…

  Last changed: 2026-11-14

• Filesystem

  Concept

  The files and folders on a computer.

  Last changed: 2026-11-14

• Grilling

  Concept

  Having an agent question you one decision at a time until the plan is clear, before any building…

  Last changed: 2026-11-14

• Handoff

  Concept

  Passing work from one session to the next, or from one agent to another, so the new one can…

  Last changed: 2026-11-14

• Human review

  Concept

  A person reading and approving what an agent produced before it goes live.

  Last changed: 2026-11-14

• NIST AI Risk Management Framework

  Concept

  A voluntary framework from NIST, the US standards agency, that helps organizations manage the…

  Last changed: 2026-11-14

• Output tokens

  Concept

  The tokens the model writes back.

  Last changed: 2026-11-14

• Permission mode

  Concept

  The rules that decide which actions an agent may take on its own and which need your approval first.

  Last changed: 2026-11-14

• Prefix cache

  Concept

  A provider feature that remembers the opening of a request it has just handled.

  Last changed: 2026-11-14

• Similarity search

  Concept

  Finding the stored items whose vectors are closest to a query's vector, so results match by…

  Last changed: 2026-11-14

• Software factory

  Concept

  A way of organizing work where events, not people, start agent sessions.

  Last changed: 2026-11-14

• Stateless

  Concept

  Describes something that keeps nothing between uses.

  Last changed: 2026-11-14

• Vibe coding vs software engineering

  Concept

  Two ways to build software with AI.

  Last changed: 2026-11-14

• Agent mode

  Concept

  A named setting in a coding agent that changes how freely it acts.

  Last changed: 2026-11-14

• AX

  Concept

  Agent experience: how well a project is set up for an AI agent to do good work, with a clear…

  Last changed: 2026-11-14

• Cache tokens

  Concept

  Input tokens the provider did not need to process again because they matched the start of a recent…

  Last changed: 2026-11-14

• Context engineering

  Concept

  Deciding what information, instructions, examples and tools to put in front of an AI model for…

  Last changed: 2026-11-14

• Ground truth

  Concept

  The verified, correct answers or facts that an AI system's output is checked against.

  Last changed: 2026-11-14

• Knowledge cutoff

  Concept

  The date where a model's training data ends.

  Last changed: 2026-11-14

• Parametric knowledge

  Concept

  What a model knows from its training, stored in its parameters.

  Last changed: 2026-11-14

• Reasoning model

  Concept

  A model, or a mode of a model, that works through a problem in intermediate steps before it answers.

  Last changed: 2026-11-14

• Secondary source

  Concept

  A description of the original material rather than the material itself, such as a summary, a…

  Last changed: 2026-11-14

• Tool result

  Concept

  What comes back to the model after it uses a tool: a file's contents, the output of a command, a…

  Last changed: 2026-11-14

• Agent loop

  Concept

  The repeating cycle that makes an AI agent work: the model decides on a step, calls a tool, reads…

  Last changed: 2026-11-14

• Alignment

  Concept

  Work to make AI models pursue what people actually intend and behave according to agreed values…

  Last changed: 2026-11-14

• Attention relationship

  Concept

  The link between two tokens in the input, measured by how much one shapes the model's reading of…

  Last changed: 2026-11-14

• Autocompact

  Concept

  Compaction that the agent's software starts on its own when the context window is nearly full.

  Last changed: 2026-11-14

• Chunking

  Concept

  Splitting long documents into smaller passages before creating embeddings, so a search can return…

  Last changed: 2026-11-14

• Context pointer

  Concept

  A short mention in one document that tells an agent where to find more, such as 'deployment steps…

  Last changed: 2026-11-14

• Cosine similarity

  Concept

  A common way to measure how alike two vectors are by the angle between them.

  Last changed: 2026-11-14

• Dark factory

  Concept

  Part of a product where agents write and ship code that no person ever reviews.

  Last changed: 2026-11-14

• Design concept

  Concept

  The shared picture of what is being built, held by you and by the agent, separate from any…

  Last changed: 2026-11-14

• Diffusion model

  Concept

  A kind of AI model that creates images, and sometimes audio or video, by starting from random…

  Last changed: 2026-11-14

• Dimension

  Concept

  One number position in a vector, like one axis on a map.

  Last changed: 2026-11-14

• Distillation

  Concept

  Training a smaller model to copy the outputs of a larger one, so it keeps much of the quality…

  Last changed: 2026-11-14

• DX

  Concept

  Developer experience: how easy and pleasant a tool, codebase or service is for the people who…

  Last changed: 2026-11-14

• Effort

  Concept

  A setting that tells a reasoning model how much thinking to do before it answers.

  Last changed: 2026-11-14

• Home repo

  Concept

  One repository that acts as your base for working with agents.

  Last changed: 2026-11-14

• Hybrid search

  Concept

  Combining keyword search and similarity search, so results match both exact terms, such as product…

  Last changed: 2026-11-14

• Loss function

  Concept

  A formula that scores how wrong a model's output is compared with the right answer.

  Last changed: 2026-11-14

• Permission request

  Concept

  The pause where an agent asks before it takes an action its permission mode does not allow on its…

  Last changed: 2026-11-14

• Primary source

  Concept

  The original material itself, such as the code, a full transcript or the raw data.

  Last changed: 2026-11-14

• Prompt optimization

  Concept

  Improving a prompt through repeated testing: change it, run it against a set of examples, measure…

  Last changed: 2026-11-14

• Quantization

  Concept

  Shrinking a model by storing its weights with fewer digits of precision.

  Last changed: 2026-11-14

• Rate limit

  Concept

  A cap on how many requests or tokens an account can send to an API in a set period.

  Last changed: 2026-11-14

• Stateful

  Concept

  Describes something that carries information forward from one moment to the next.

  Last changed: 2026-11-14

• Turn

  Concept

  One round of a conversation with an agent: you send a message, and the agent works until it hands…

  Last changed: 2026-11-14

• Backpropagation

  Concept

  The calculation that works out how much each weight in a neural network contributed to an error…

  Last changed: 2026-11-14

• Deep learning

  Concept

  Machine learning using neural networks with many layers.

  Last changed: 2026-11-14

• Few-shot prompting

  Concept

  Including a few worked examples in a prompt so the model copies the pattern.

  Last changed: 2026-11-14

• Gradient descent

  Concept

  The method used to train neural networks: measure how wrong the model is, work out which direction…

  Last changed: 2026-11-14

• Interpretability

  Concept

  Research into what is happening inside an AI model: which internal patterns represent which ideas…

  Last changed: 2026-11-14

• LoRA

  Concept

  Low-rank adaptation.

  Last changed: 2026-11-14

• MCP

  Concept

  Model Context Protocol.

  Last changed: 2026-11-14

• MLOps

  Concept

  The practices and tools for running machine learning models in production: versioning data and…

  Last changed: 2026-11-14

• Overfitting

  Concept

  When a model learns its training examples too closely, including their quirks, and then performs…

  Last changed: 2026-11-14

• Reranking

  Concept

  A second pass in search where a more careful model reorders the first batch of results by how well…

  Last changed: 2026-11-14

• RLHF

  Concept

  Reinforcement learning from human feedback.

  Last changed: 2026-11-14

• Sampling

  Concept

  How a model chooses each next token from its list of likely options.

  Last changed: 2026-11-14

• Sentiment analysis

  Concept

  Using software to classify the tone of text or speech, such as positive, negative or neutral…

  Last changed: 2026-11-14

• Temperature

  Concept

  A setting that controls how random an AI model's word choices are.

  Last changed: 2026-11-14

• Tokenizer

  Concept

  The step that splits text into tokens, the small pieces a model actually reads, and turns each one…

  Last changed: 2026-11-14

• Vector

  Concept

  An ordered list of numbers.

  Last changed: 2026-11-14

• Agent swarm

  Concept

  Many AI agents working on parts of a larger task at the same time, coordinated by software or by a…

  Last changed: 2026-11-14

• Deepfake

  Concept

  Realistic fake video, audio or images of a real person made with AI, showing them saying or doing…

  Last changed: 2026-11-14

• Virtual try-on

  Concept

  Showing how clothing, glasses or makeup would look on a person by generating or overlaying an…

  Last changed: 2026-11-14