109
Published
AI Place Hub
@aiplacehub moderator
Maintainer account. Publishes the baseline library that ships with the site.
Joined September 2026
23
Glossary terms
0
Likes received
5.1k
Views
Published
- GuideUniversal
How to check what an AI tells you
A few checks that catch most wrong answers: which claims to verify, how to ask for sources, and why a confident tone tells you nothing.
- GuideUniversal
Meta-prompting: ask the model to write the prompt
Use a model to draft or improve the prompt before you use that prompt for the real task. It pays off for a recurring job and is overkill for a…
- GuideUniversal
Add a self-critique pass before the final answer
A two-step pattern: draft, then have the model check its own draft against a specific list of failure modes. It catches a kind of mistake that a…
- GuideUniversal
Force a strict output contract
How to make a model response reliably machine-parseable: exact fields, no preamble, no trailing summary. For anything that downstream code reads and…
- GuideUniversal
Few-shot examples: showing instead of telling
Why two or three worked examples in a prompt often beat a page of written rules, and how to choose examples that teach the right pattern and not an…
- GuideUniversal
Common prompt mistakes and how to fix them
Five patterns that reliably give a worse answer than you meant, each with a one-line fix. Use it as a checklist when a prompt keeps returning…
- GuideUniversal
Prompt templates worth keeping
Four reusable prompt shapes. They are structures with blanks and not finished prompts, for tasks that come up often enough to save once and stop…
- GuideUniversal
How to write a prompt that actually works
A short checklist to run any prompt through before you send it: who, what, shape and what to leave out. Those four things separate a specific prompt…
Notion MCP server
Gives the model access to your Notion pages and databases: read project docs, update a status field, or draft a new page from a conversation.
Tested on Claude Sonnet · Jun 2026
Slack MCP server
Lets the model read and post to the Slack channels it can access: search history, summarise a thread, or draft a message for you to send.
Tested on Claude Sonnet · Jun 2026
Instructor
A small Python library that forces a model output into a Pydantic schema and retries automatically when the response fails validation.
Tested on Claude Sonnet · Jun 2026
Haystack
An open-source Python framework from deepset for production retrieval and search pipelines, with more explicit pipeline control than most…
Tested on GPT-5 · Jun 2026
Replicate
Run thousands of community-published models, image, audio, video and language, behind one API without hosting any of them yourself.
Tested on GPT-5 · Jun 2026
Together AI
Hosted inference for open-weight models such as Llama, Mixtral and Qwen, plus fine-tuning, at a lower price than most proprietary-model APIs.
Tested on Llama 3.3 70B · Jun 2026
ChatGPT desktop app
The native macOS and Windows app: a global hotkey, screen access on request, and a persistent window in place of a browser tab you keep losing.
Tested on GPT-5 · Jun 2026
Comet
The Perplexity browser with an AI assistant built into the browser itself. It reads the open tab, summarises it and acts on the page, and does not…
Tested on GPT-5 · Jun 2026
Teacher who checks the starting level first
Asks one question about what you already know before it explains. That beats guessing your level and landing an explanation that is too basic or…
Tested on Claude Sonnet · Jun 2026
Researcher who separates what a source says from what it concludes
Keeps a finding, an interpretation of it and a guess labelled as three separate things, so they do not blend into one confident paragraph.
Tested on GPT-5 · Jun 2026
Collections
-
4 items
First week with a coding model
Read these in order if you only just started using a model on a real codebase. Four entries, about an hour.
-
3 items
Going local
How to stop paying for an API: the hardware maths, the install, and the two tools that matter.
-
5 items
Set up your AI once
Stop retyping the same rules. Five lessons on moving them into a config file for Claude Code and Cursor, and on picking a model…
-
5 items
AI on a budget
Five free lessons, from the free ways to use AI through choosing a model to running one on your own computer. You spend nothing.
-
6 items
Prompt engineering: zero to fluent
Six lessons. You start with what a single prompt is made of and end with few-shot examples and a self-critique pass. No…
-
5 items
AI for study and everyday work
Five free lessons on turning a messy task into a clear prompt, getting summaries you can trust, and studying without handing the…
-
5 items
Use AI without getting burned
Five free lessons about checking answers, keeping private data out of chats and dealing with prompt injection. No sign-up.
-
5 items
Work with a coding assistant
Five free lessons: how to brief an assistant, where to keep your rules, and how to review what it changed.
Glossary contributions
Agent
A model with tools and a goal that picks its own next steps in a loop and does not answer just once.
API key
A secret string that identifies you to an AI service and lets your code call it. Whoever has the key can spend your money.
Chain of thought CoT
Prompt the model to write out its intermediate steps before giving the final answer.
Connector
A link between an AI app and an outside service, such as a drive, calendar or chat tool, that lets the model read your data from there.
Context window
The most text, counted in tokens, that a model can consider at once. Your prompt and its answer share that space.
Embeddings
Lists of numbers that stand for text, built so that similar meanings end up close together. Semantic search runs on them.
Few-shot prompting
Put two or three worked examples of the task in the prompt, on top of the description.
Fine-tuning
More training for an existing model on your own examples. It changes how the model behaves, not what it knows.
Hallucination
A fluent, confident answer that is plain wrong: an invented citation, function, statistic or fact.
Inference
Running a trained model to get output. It happens every time you send a prompt.
Large language model LLM
A model trained on huge amounts of text to predict the next token. That one skill lets it write, summarise, translate and reason over text.
Model Context Protocol MCP
An open standard that lets an AI app connect to outside tools and data, such as files, databases or services, through small programs called servers.