# Building with AI

Every entry in Building with AI on the Tulsa Ecosystem Map. Tulsa entries first, then by connections.

- [AI](https://ecosystem.samcarlton.com/terms/ai): Artificial intelligence.
- [LLM](https://ecosystem.samcarlton.com/llm): Large language model.
- [Model](https://ecosystem.samcarlton.com/model): The trained system at the center of an AI product.
- [Training](https://ecosystem.samcarlton.com/training): Teaching an AI model by showing it a very large number of examples before anyone uses it.
- [AI agent](https://ecosystem.samcarlton.com/ai-agent): An AI tool that does more than answer a question.
- [Prompt](https://ecosystem.samcarlton.com/prompt): The instructions or question you give an AI tool in everyday words.
- [Context window](https://ecosystem.samcarlton.com/context-window): How much text an LLM can take into account at one time.
- [No-code](https://ecosystem.samcarlton.com/no-code): Tools that let you build an app or site by arranging visual blocks or describing what you want, instead of writing code.
- [Coding agent](https://ecosystem.samcarlton.com/coding-agent): An AI agent that writes and changes code.
- [Inference](https://ecosystem.samcarlton.com/inference): An AI model producing an answer to a request.
- [Hallucination](https://ecosystem.samcarlton.com/hallucination): When an AI model states something false or invented as though it were true.
- [Local model](https://ecosystem.samcarlton.com/local-model): A model that is downloaded and run on a person's own computer or a company's own servers, not on a provider's.
- [RAG](https://ecosystem.samcarlton.com/rag): Retrieval-augmented generation.
- [Evals](https://ecosystem.samcarlton.com/evals): Tests that check whether the outputs of a model or an AI product meet the criteria its builders set.
- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Vibe coding](https://ecosystem.samcarlton.com/vibe-coding): Building software by describing what you want to an AI tool and accepting the code it writes, often without reading that code closely.
- [AI chat assistant](https://ecosystem.samcarlton.com/chatbot): A finished app where a person types or talks to an AI model and gets replies in conversation.
- [Speech-to-text](https://ecosystem.samcarlton.com/speech-to-text): Software that turns spoken words into written text.
- [Tool use](https://ecosystem.samcarlton.com/tool-use): A way for a model to ask the software around it to run a defined action, such as a search or a database lookup, and send back the result.
- [AI use policy](https://ecosystem.samcarlton.com/ai-use-policy): An organization's rules for which AI tools its people may use and what information they may put into them.
- [Embedding](https://ecosystem.samcarlton.com/embedding): A way of turning a piece of text into a list of numbers that captures its meaning, so software can tell which pieces of text are about…
- [Session](https://ecosystem.samcarlton.com/session): One stretch of work with an AI agent, from a blank start until it is cleared, closed or compacted.
- [AFK](https://ecosystem.samcarlton.com/afk): Short for away from keyboard.
- [AGENTS.md](https://ecosystem.samcarlton.com/agents-md): A plain text file in a project that many coding agents read automatically at the start of every session.
- [AI safety](https://ecosystem.samcarlton.com/ai-safety): The work of making AI systems behave safely and of measuring how safe they are.
- [Frontier model](https://ecosystem.samcarlton.com/frontier-model): One of the most capable general-purpose AI models available at a given time.
- [GPU](https://ecosystem.samcarlton.com/gpu): Graphics processing unit.
- [Human in the loop](https://ecosystem.samcarlton.com/human-in-the-loop): Designing an AI process so a person reviews, approves or corrects the AI's work at key steps instead of letting it act alone.
- [Open source vs open weights](https://ecosystem.samcarlton.com/open-source-vs-open-weights): Two labels for AI models that people often mix up.
- [Weights](https://ecosystem.samcarlton.com/weights): The numbers inside a model that it learned during training.
- [Model provider](https://ecosystem.samcarlton.com/model-provider): The company or service that runs an AI model and answers requests to it, usually over the internet through an API.
- [System prompt](https://ecosystem.samcarlton.com/system-prompt): Standing instructions that the builder of an AI product gives the model before any user types.
- [Vector database](https://ecosystem.samcarlton.com/vector-database): A database built to store embeddings and quickly find the items closest in meaning to a question, not just the ones that share its exact…
- [Agent skills](https://ecosystem.samcarlton.com/agent-skills): A packaged set of instructions, sometimes with scripts, that an agent loads when a task calls for it, such as how to write a press release…
- [Fine-tuning](https://ecosystem.samcarlton.com/fine-tuning): Extra training of an existing model on a smaller, narrower set of examples, so it suits one task or style.
- [Harness](https://ecosystem.samcarlton.com/harness): The software wrapped around an AI model that turns it into a working agent.
- [Multimodal](https://ecosystem.samcarlton.com/multimodal): Describes a model that works with more than one type of content, such as text plus images or audio.
- [Subagent](https://ecosystem.samcarlton.com/subagent): A second agent that the main agent starts to handle one piece of a job in its own separate session.
- [Automated check](https://ecosystem.samcarlton.com/automated-check): A test or rule a computer runs to catch problems without a person looking, such as tests, type checkers and style checkers.
- [Clearing](https://ecosystem.samcarlton.com/clearing): Ending a session and starting a completely empty one.
- [Guardrails](https://ecosystem.samcarlton.com/guardrails): Checks and limits built around a model inside a product.
- [Input tokens](https://ecosystem.samcarlton.com/input-tokens): The tokens an AI product sends to the model on each request: the instructions, the conversation so far, files and tool results.
- [Neural network](https://ecosystem.samcarlton.com/neural-network): A kind of software model made of many layers of simple math units connected by weights, loosely inspired by the brain.
- [Sandbox](https://ecosystem.samcarlton.com/sandbox): A walled-off space where an agent can run commands and change files without reaching the rest of your computer, your accounts or the open…
- [Spec](https://ecosystem.samcarlton.com/spec): A written description of what is being built and why, for work too big to finish in one session.
- [Transformer](https://ecosystem.samcarlton.com/transformer): The design that most modern language models are built on, introduced by Google researchers in 2017.
- [Agent environment](https://ecosystem.samcarlton.com/agent-environment): Everything outside the agent's own software that it can look at or change: your files, terminal, browser, databases and connected services.
- [AI literacy](https://ecosystem.samcarlton.com/ai-literacy): Enough understanding of AI to use it well and safely: what it is good and bad at, how to write a prompt, how to check its work and what…
- [Attention](https://ecosystem.samcarlton.com/attention): The part of a language model that decides, for each token, how much every other token in the input should shape its meaning.
- [Compaction](https://ecosystem.samcarlton.com/compaction): Shrinking a long session by replacing its history with a summary and carrying on from that summary in a fresh context window.
- [Handoff artifact](https://ecosystem.samcarlton.com/handoff-artifact): The written document that carries a handoff, produced by one session for another to read.
- [Latent space](https://ecosystem.samcarlton.com/latent-space): The internal map of numbers where a model places the things it reads.
- [Memory system](https://ecosystem.samcarlton.com/memory-system): A setup that tries to give an agent memory across sessions by saving notes to files or a database and loading them back when a new session…
- [Model provider request](https://ecosystem.samcarlton.com/model-provider-request): One trip from an AI product to the model provider and back.
- [Next-token prediction](https://ecosystem.samcarlton.com/next-token-prediction): The one job a language model performs.
- [Parameters](https://ecosystem.samcarlton.com/parameters): The values a model learns during training.
- [Probabilistic vs deterministic](https://ecosystem.samcarlton.com/probabilistic-vs-deterministic): Deterministic software gives the same output for the same input every time.
- [Progressive disclosure](https://ecosystem.samcarlton.com/progressive-disclosure): Giving an agent only what it needs right now, with pointers to the rest, instead of loading everything at the start.
- [Prompt injection](https://ecosystem.samcarlton.com/prompt-injection): A security weakness in AI products.
- [Smart zone](https://ecosystem.samcarlton.com/smart-zone): A name for the early part of a session, when an agent is focused and accurate.
- [Sycophancy](https://ecosystem.samcarlton.com/sycophancy): The habit AI models have of telling you what you want to hear: agreeing too readily, praising weak ideas or giving up a correct answer…
- [Attention budget](https://ecosystem.samcarlton.com/attention-budget): A way of picturing attention as a fixed amount each token can spread across everything else in the input.
- [Attention degradation](https://ecosystem.samcarlton.com/attention-degradation): The drop in an agent's sharpness as a session gets long.
- [Automated review](https://ecosystem.samcarlton.com/automated-review): Having an AI model read and critique work, usually code, before a person does.
- [Benchmark](https://ecosystem.samcarlton.com/benchmark): A shared, public test used to score different models on the same tasks so they can be compared.
- [Contextual knowledge](https://ecosystem.samcarlton.com/contextual-knowledge): Facts the model can read directly in front of it right now, such as documents you pasted, files the agent opened or search results.
- [Filesystem](https://ecosystem.samcarlton.com/filesystem): The files and folders on a computer.
- [Grilling](https://ecosystem.samcarlton.com/grilling): Having an agent question you one decision at a time until the plan is clear, before any building starts.
- [Handoff](https://ecosystem.samcarlton.com/handoff): Passing work from one session to the next, or from one agent to another, so the new one can continue without the full history.
- [Human review](https://ecosystem.samcarlton.com/human-review): A person reading and approving what an agent produced before it goes live.
- [NIST AI Risk Management Framework](https://ecosystem.samcarlton.com/nist-ai-rmf): A voluntary framework from NIST, the US standards agency, that helps organizations manage the risks AI can pose to people, organizations…
- [Output tokens](https://ecosystem.samcarlton.com/output-tokens): The tokens the model writes back.
- [Permission mode](https://ecosystem.samcarlton.com/permission-mode): The rules that decide which actions an agent may take on its own and which need your approval first.
- [Prefix cache](https://ecosystem.samcarlton.com/prefix-cache): A provider feature that remembers the opening of a request it has just handled.
- [Similarity search](https://ecosystem.samcarlton.com/similarity-search): Finding the stored items whose vectors are closest to a query's vector, so results match by meaning rather than exact words.
- [Software factory](https://ecosystem.samcarlton.com/software-factory): A way of organizing work where events, not people, start agent sessions.
- [Stateless](https://ecosystem.samcarlton.com/stateless): Describes something that keeps nothing between uses.
- [Vibe coding vs software engineering](https://ecosystem.samcarlton.com/vibe-coding-vs-software-engineering): Two ways to build software with AI.
- [Agent mode](https://ecosystem.samcarlton.com/agent-mode): A named setting in a coding agent that changes how freely it acts.
- [AX](https://ecosystem.samcarlton.com/ax): Agent experience: how well a project is set up for an AI agent to do good work, with a clear structure, automated checks that catch…
- [Cache tokens](https://ecosystem.samcarlton.com/cache-tokens): Input tokens the provider did not need to process again because they matched the start of a recent request in its cache.
- [Context engineering](https://ecosystem.samcarlton.com/context-engineering): Deciding what information, instructions, examples and tools to put in front of an AI model for each task, and what to leave out.
- [Ground truth](https://ecosystem.samcarlton.com/ground-truth): The verified, correct answers or facts that an AI system's output is checked against.
- [Knowledge cutoff](https://ecosystem.samcarlton.com/knowledge-cutoff): The date where a model's training data ends.
- [Parametric knowledge](https://ecosystem.samcarlton.com/parametric-knowledge): What a model knows from its training, stored in its parameters.
- [Reasoning model](https://ecosystem.samcarlton.com/reasoning-model): A model, or a mode of a model, that works through a problem in intermediate steps before it answers.
- [Secondary source](https://ecosystem.samcarlton.com/secondary-source): A description of the original material rather than the material itself, such as a summary, a README or a compaction note.
- [Tool result](https://ecosystem.samcarlton.com/tool-result): What comes back to the model after it uses a tool: a file's contents, the output of a command, a search result or an error.
- [Agent loop](https://ecosystem.samcarlton.com/agent-loop): The repeating cycle that makes an AI agent work: the model decides on a step, calls a tool, reads the result and decides the next step…
- [Alignment](https://ecosystem.samcarlton.com/alignment): Work to make AI models pursue what people actually intend and behave according to agreed values, such as being honest and refusing harmful…
- [Attention relationship](https://ecosystem.samcarlton.com/attention-relationship): The link between two tokens in the input, measured by how much one shapes the model's reading of the other.
- [Autocompact](https://ecosystem.samcarlton.com/autocompact): Compaction that the agent's software starts on its own when the context window is nearly full.
- [Chunking](https://ecosystem.samcarlton.com/chunking): Splitting long documents into smaller passages before creating embeddings, so a search can return just the relevant part instead of a…
- [Context pointer](https://ecosystem.samcarlton.com/context-pointer): A short mention in one document that tells an agent where to find more, such as 'deployment steps are in the deploy guide'.
- [Cosine similarity](https://ecosystem.samcarlton.com/cosine-similarity): A common way to measure how alike two vectors are by the angle between them.
- [Dark factory](https://ecosystem.samcarlton.com/dark-factory): Part of a product where agents write and ship code that no person ever reviews.
- [Design concept](https://ecosystem.samcarlton.com/design-concept): The shared picture of what is being built, held by you and by the agent, separate from any document or code.
- [Diffusion model](https://ecosystem.samcarlton.com/diffusion-model): A kind of AI model that creates images, and sometimes audio or video, by starting from random noise and removing it step by step until a…
- [Dimension](https://ecosystem.samcarlton.com/dimension): One number position in a vector, like one axis on a map.
- [Distillation](https://ecosystem.samcarlton.com/distillation): Training a smaller model to copy the outputs of a larger one, so it keeps much of the quality while being cheaper and faster to run.
- [DX](https://ecosystem.samcarlton.com/dx): Developer experience: how easy and pleasant a tool, codebase or service is for the people who build with it, such as clear documentation…
- [Effort](https://ecosystem.samcarlton.com/effort): A setting that tells a reasoning model how much thinking to do before it answers.
- [Home repo](https://ecosystem.samcarlton.com/home-repo): One repository that acts as your base for working with agents.
- [Hybrid search](https://ecosystem.samcarlton.com/hybrid-search): Combining keyword search and similarity search, so results match both exact terms, such as product codes, and overall meaning.
- [Loss function](https://ecosystem.samcarlton.com/loss-function): A formula that scores how wrong a model's output is compared with the right answer.
- [Permission request](https://ecosystem.samcarlton.com/permission-request): The pause where an agent asks before it takes an action its permission mode does not allow on its own.
- [Primary source](https://ecosystem.samcarlton.com/primary-source): The original material itself, such as the code, a full transcript or the raw data.
- [Prompt optimization](https://ecosystem.samcarlton.com/prompt-optimization): Improving a prompt through repeated testing: change it, run it against a set of examples, measure results and keep the better version.
- [Quantization](https://ecosystem.samcarlton.com/quantization): Shrinking a model by storing its weights with fewer digits of precision.
- [Rate limit](https://ecosystem.samcarlton.com/rate-limit): A cap on how many requests or tokens an account can send to an API in a set period.
- [Stateful](https://ecosystem.samcarlton.com/stateful): Describes something that carries information forward from one moment to the next.
- [Turn](https://ecosystem.samcarlton.com/turn): One round of a conversation with an agent: you send a message, and the agent works until it hands control back to you.
- [Backpropagation](https://ecosystem.samcarlton.com/backpropagation): The calculation that works out how much each weight in a neural network contributed to an error, layer by layer from the output back, so…
- [Deep learning](https://ecosystem.samcarlton.com/deep-learning): Machine learning using neural networks with many layers.
- [Few-shot prompting](https://ecosystem.samcarlton.com/few-shot-prompting): Including a few worked examples in a prompt so the model copies the pattern.
- [Gradient descent](https://ecosystem.samcarlton.com/gradient-descent): The method used to train neural networks: measure how wrong the model is, work out which direction to nudge each weight to be less wrong…
- [Interpretability](https://ecosystem.samcarlton.com/interpretability): Research into what is happening inside an AI model: which internal patterns represent which ideas and how they lead to an output.
- [LoRA](https://ecosystem.samcarlton.com/lora): Low-rank adaptation.
- [MCP](https://ecosystem.samcarlton.com/terms/mcp): Model Context Protocol.
- [MLOps](https://ecosystem.samcarlton.com/mlops): The practices and tools for running machine learning models in production: versioning data and models, deploying them, monitoring quality…
- [Overfitting](https://ecosystem.samcarlton.com/overfitting): When a model learns its training examples too closely, including their quirks, and then performs poorly on new data.
- [Reranking](https://ecosystem.samcarlton.com/reranking): A second pass in search where a more careful model reorders the first batch of results by how well each actually answers the question.
- [RLHF](https://ecosystem.samcarlton.com/rlhf): Reinforcement learning from human feedback.
- [Sampling](https://ecosystem.samcarlton.com/sampling): How a model chooses each next token from its list of likely options.
- [Sentiment analysis](https://ecosystem.samcarlton.com/sentiment-analysis): Using software to classify the tone of text or speech, such as positive, negative or neutral, often across many customer messages at once.
- [Temperature](https://ecosystem.samcarlton.com/temperature): A setting that controls how random an AI model's word choices are.
- [Tokenizer](https://ecosystem.samcarlton.com/tokenizer): The step that splits text into tokens, the small pieces a model actually reads, and turns each one into a number.
- [Vector](https://ecosystem.samcarlton.com/vector): An ordered list of numbers.
- [Agent swarm](https://ecosystem.samcarlton.com/agent-swarm): Many AI agents working on parts of a larger task at the same time, coordinated by software or by a lead agent.
- [Deepfake](https://ecosystem.samcarlton.com/deepfake): Realistic fake video, audio or images of a real person made with AI, showing them saying or doing something they never did.
- [Virtual try-on](https://ecosystem.samcarlton.com/virtual-try-on): Showing how clothing, glasses or makeup would look on a person by generating or overlaying an image, so shoppers can preview items before…

Map view: https://ecosystem.samcarlton.com/ai