Guides
Choose, use and build with AI
Start with an everyday task or go deeper into building an AI system. Our guides explain the setup, evidence and trade-offs behind a decision. Proposed tests and documentation reviews are labeled; rankings are never sold.
Everyday AI / Decision guide
How to choose an AI tool for your everyday work
Choose AI tools by the job, setup, data, language and total cost. Compare two candidates with a free worksheet and practical tests, without coding.
Read the guide
Everyday AI / Decision guide
How to research and learn with AI without losing the sources
A practical AI research workflow: define a question, collect sources, verify citations and separate evidence from inference. Includes a worked source-checking exercise.
Read the guideEveryday AI / Decision guide
How to write with AI and keep control of the final draft
Use AI for emails, summaries and first drafts with a clear brief, a fact ledger and a review checklist. Includes practical prompts and a fictional before-and-after exercise.
Read the guide
MCP setup / Decision guide
How to add an MCP server to Claude Code, Cursor, VS Code, Claude Desktop and Codex
The exact commands and config files for local and hosted servers in all five clients, checked against each client's own documentation.
Read the guide
Decision models / Decision guide
What is Jev AI? Pricing, use cases and limits
TypeSafe's decision model explained: Choice, Score and Noul, the cost per evaluation, and what to test before trusting its answers.
Read the guideRAG / Decision guide
How to build a RAG knowledge assistant
Platform or compose-it-yourself, then the seven layers — ingestion, chunking, vector store, retrieval, orchestration, memory, and eval.
Read the guide
Voice / Decision guide
Choose and evaluate a voice agent stack
Vapi, Retell, LiveKit and Pipecat: compare architectures, test twelve difficult call scenarios, and model the complete cost.
Read the guide
Coding / Decision guide
How to build a coding agent
Adopt an agent or build your own harness, then the layers — the agent loop, code context, safe execution, the model, memory, and review.
Read the guide
Browser / Decision guide
How to build a browser-automation agent
Perception is the hard part, not clicking. DOM vs vision vs VLA, then the runtime, the driver, the model, planning, and reliability.
Read the guide
Autonomous / Decision guide
How to build an autonomous agent
Autonomy is a control problem, not a capability problem. Adopt, build, or hand-roll — then framework, tools, memory, execution, orchestration, and governance.
Read the guideMCP / Decision guide
How to build an MCP server
The protocol is trivial; tool design is the craft. Wrap, build, or aggregate — then SDK and transport, tool design, resources, reliability, and distribution.
Read the guideSelf-hosted / Decision guide
The self-hosted agent stack
Run agents on your own infrastructure. What you're actually protecting, the platform, the model question, safe execution, data, and boring ops.
Read the guideFrameworks / Decision guide
How to choose an agent framework
Do you need one at all? The five archetypes — code-first, role-based, typed, TypeScript-native, visual — and the criteria that actually predict regret.
Read the guideWorkflow / Decision guide
How to build AI workflow automation
Most “agents” should be workflows with LLM steps. Triggers, the engine, the LLM step, approval gates, reliability — and when to graduate to an agent loop.
Read the guide