Learn
Guides
21 of 46 guides
Prompt Patterns That Work Across Every Assistant
Seven reusable prompting patterns, from role and few-shot examples to critique loops, with templates you can paste into any chatbot.
5 min read
BuilderAny assistantMembersHow to Write a System Prompt That Actually Holds
Learn the structure of a strong system prompt, how to set role, rules and format, and how to test it so your assistant or bot behaves consistently.
6 min read
BuilderAny assistantMembersGetting Reliable JSON and Structured Output from AI
Techniques for making a model return clean JSON every time, from prompt wording and schemas to validation and retry loops in your code.
6 min read
BuilderAny assistantBuilding Your First AI Agent, Step by Step
Understand what an agent is, then build a simple one: a goal, a loop, a few tools and clear stopping rules, with a framework-free Python sketch.
7 min read
BuilderAny assistantLong Chats, Forgetting and Memory: How to Keep AI on Track
Why assistants lose details in long conversations, and how to use summaries, fresh chats, projects and memory features to keep context sharp.
5 min read
BuilderPerplexityMembersDoing Research with Perplexity and Other Search-Based Assistants
How answer engines with live citations differ from plain chatbots, and a repeatable method for checking sources and getting trustworthy research.
6 min read
BuilderLlamaMembersRunning Open Models: Llama, Mistral and DeepSeek Explained
What open-weight models are, why people run them locally or via hosting providers, and how to get started while respecting hardware limits and licenses.
6 min read
BuilderAny assistantMembersQuantization and Hardware: What You Need to Run Models Locally
Understand parameters, memory, and quantization in plain terms so you can pick a local model that actually fits your computer.
6 min read
BuilderClaudeMembersClaude API Basics - Keys, a First Request, Streaming and Errors
Make your first call to the Claude API safely: get a key, keep it out of your code, send a request, stream the reply and handle errors.
7 min read
BuilderChatGPTMembersOpenAI API Basics - Keys, a First Request, Streaming and Errors
Send your first request to the OpenAI API with the key kept out of your code, then add streaming, retries and sensible error handling.
6 min read
BuilderGeminiMembersGemini API Basics - Keys, a First Request, Streaming and Errors
Get a Gemini API key, keep it safe, make a first request, stream a reply and handle the errors you are most likely to meet.
6 min read
BuilderGrokMembersxAI (Grok) API Basics - Keys, a First Request, Streaming and Errors
Use the xAI API with a familiar client library, a key stored safely in the environment, a first request, streaming and calm error handling.
6 min read
BuilderAny assistantMembersTool and Function Calling Explained
How models use tools without running anything themselves, with a clear walk-through of the request, the tool result and the final answer.
6 min read
BuilderAny assistantMembersDesigning Good Tools for AI Agents
Practical rules for naming, describing, scoping and returning results from agent tools so the model picks the right one and recovers from mistakes.
6 min read
BuilderAny assistantMembersMCP in Practice - Connecting AI to Tools Safely
What the Model Context Protocol does, how servers and clients fit together, how to try one, and how to vet a server before you trust it.
6 min read
BuilderAny assistantMembersHuman-in-the-Loop Approvals for AI Agents
Decide which agent actions need a person's yes, design approval prompts people can actually judge, and avoid the trap of clicking approve without reading.
6 min read
BuilderAny assistantMembersReasoning Models and Chain-of-Thought Prompting
Learn what reasoning models do differently, when step-by-step thinking helps, when it only adds cost, and how to prompt each kind well.
6 min read
BuilderAny assistantMembersAvoiding Sycophancy - Getting Honest Feedback from AI
Assistants tend to agree with you and praise your work. Learn why, how to spot it, and prompts that bring out honest critique instead.
5 min read
BuilderAny assistantMembersUsing AI for IT Helpdesk and Sysadmin Work
Where an assistant genuinely speeds up troubleshooting, scripting and documentation, and the habits that keep it from breaking a production system.
7 min read
BuilderAny assistantMembersReviewing AI-Written Code - Tests, Security and Common Traps
How to review code from an assistant: what to read first, what to test, the security mistakes that appear again and again, and when to throw it away.
7 min read
BuilderAny assistantRate Limits and Usage Caps - Why You Hit Them and How to Cope
Understand the difference between app usage caps and API rate limits, why they exist, and how to work within them with batching, caching and retries.
6 min read