The MetaRix guide library
Find your next step with AI
Understand a concept, compare your options or build something useful. Browse by topic, or follow a complete learning path from the foundations to a capstone project.
48 guides to explore
Learning paths
Applied AI Engineer Roadmap
Follow six ordered lessons and a runnable capstone covering Python, model APIs, retrieval, RAG, evaluation and reliability. Build an inspectable document assistant and document its limits.
- Lesson 1 · 5 min
Applied AI Foundations: Python, APIs and JSON
Define application inputs and outputs, validate a source collection, and separate errors from unsupported questions.
Read guide → - Lesson 2 · 5 min
LLM APIs: Prompts, Structured Outputs and Validation
Design a model-response contract and reject malformed, incomplete, uncited or unsupported outputs.
Read guide →
Learning paths
Machine Learning Engineer Learning Path
Build the classical-ML engineering core through six focused lessons and a reproducible classifier capstone: data contracts, splits, pipelines, evaluation, local serving and monitoring.
- Lesson 1 · 4 min
Frame an ML Problem Before Training a Model
Write a testable prediction contract and explain available features, delayed labels, a baseline and excluded uses.
Read guide → - Lesson 2 · 4 min
Prevent Data Leakage: Splits, SQL and Data Checks
Explain training, validation and test roles, verify label-availability gaps and identify temporal, group and preprocessing leakage.
Read guide →
Everyday AI
Tools & workflows
Choose useful AI tools and put them to work.
- Guide · 15 min
Best AI News Websites and Apps: 12 Compared
Compare AI news websites, digests and reader apps by specialty, then build a small reading routine for product updates, practical guides and wider technology trends.
Read guide → - Guide · 11 min
AI Tools for Small Business: A Practical, Low-Cost Guide
Choose AI software by the job: customer drafts, source-based research, marketing or app handoffs. Compare five tools, free limits, costs and review requirements.
Read guide → - Comparison · 15 min
AI Tools Comparison 2026: ChatGPT vs Claude vs Gemini and More
We compared nine major AI assistants on official October 2026 pricing: every tier from free to $500, what each includes, how the limits work and which tool fits which job.
Read guide → - Comparison · 8 min
Best Open-Weight Coding Models in 2026, Compared
Kimi K3.1 Pro, Mistral Large 4, DeepSeek V4.1 Flash and Qwen3.8 compared on agentic coding benchmarks, licenses, prices and self-hosting, with every score attributed.
Read guide → - Guide · 3 min
Chat to Set Up WhatsApp Business
Meta's new WhatsApp MCP lets Claude, Cursor, Codex, or ChatGPT create the account, verify the number, and test templates. You still sign in. The agent can also send.
Read guide → - Guide · 8 min
EU AI Act Delay: What's Postponed and What Already Applies
The AI Omnibus pushed high-risk AI Act rules for hiring and credit to December 2027. What is already in force, and how the US compares.
Read guide → - Guide · 10 min
Google’s Elephant–Goldfish Plugin Explained: Uses and Limits
EGM separates the AI that drafts a plan from fresh-context reviewers. Here is how it works, who can use it, and which compatibility and cost limits matter.
Read guide → - Comparison · 3 min
Salesforce Koa vs Claudeforce: Two AI Stacks
Koa is a CRM reasoner Salesforce trains and hosts. Claudeforce puts 37 sales skills inside Claude. Same Dreamforce week; two control models.
Read guide → - Guide · 8 min
Stop Starting Over: Build a Reusable AI Brief
Keep your project context outside the chat. A reusable brief and two handoff prompts help you resume work without copying an entire conversation.
Read guide → - Guide · 4 min
Why Your Local AI Runs Out of Memory—and How to Fix It
Reduce context and concurrency before replacing your hardware. Model weights, context memory and the runtime all need space; the download size is not the total memory requirement.
Read guide → - Guide · 7 min
Your Offline Tech Kit: Power, Backups and Local AI
A practical preparedness checklist for developers and tech users: charge safely, protect your data and test a downloaded AI model before connectivity disappears.
Read guide →
Building AI applications
Agents, APIs & MCP
Connect models to tools, data and applications.
- Guide · 10 min
Best MCP Servers for Developers in 2026: 6 Official Picks
Six official MCP servers that earn a place in a developer's agent setup, what each is good for, and how to start with the narrowest access.
Read guide → - Guide · 10 min
Git Worktrees for AI Coding Agents: Run Agents in Parallel
Give each AI coding agent its own Git worktree so parallel sessions never touch each other's files. The commands, how Claude Code, Codex, Cursor and VS Code handle it, and the setup that makes it work.
Read guide → - Guide · 12 min
How to Deploy an AI Agent on AWS: Lambda vs ECS vs Fargate
Lambda, durable functions, ECS on Fargate or AgentCore Runtime: where an AI agent should run on AWS, with limits, Oct 2026 prices and a verdict.
Read guide →
Platforms & infrastructure
Cloud AI platforms
Compare providers, model access and deployment choices.
- Comparison · 13 min
AWS Bedrock vs Google Vertex AI: Cloud AI Platforms Compared
Google folded Vertex AI into Gemini Enterprise Agent Platform in April 2026. Here is how it compares with Amazon Bedrock on models, pricing tiers, RAG, agents and guardrails, with list prices as of Nov 11.
Read guide → - Comparison · 10 min
Claude API vs Bedrock vs Vertex AI: Pricing and Limits
Claude costs the same per token on the Claude API, Amazon Bedrock and Vertex AI at global endpoints. Features, rate limits, data handling and billing decide which one fits.
Read guide → - Comparison · 14 min
AI Gateways Compared: Vercel vs Cloudflare vs OpenRouter
Vercel AI Gateway, Cloudflare AI Gateway, and OpenRouter all pass tokens through at list price. Here is how their fees, BYOK, caching, routing, and limits actually differ.
Read guide →
Platforms & infrastructure
Vector databases
Choose and use a store for semantic search.
Platforms & infrastructure
Hosting & inference
Plan GPU capacity, latency and serving costs.
- Guide · 11 min
LLM Latency and Throughput Explained
This guide defines TTFT, time to first answer token, output tokens per second, and end-to-end latency the way major benches and provider docs use them. It then shows which clocks coding agents and batch jobs should optimize—and how to compare speed claims without mixing harnesses.
Read guide → - Guide · 10 min
Spot vs Reserved GPUs for LLM Inference: When to Commit
Spot GPUs are up to 90% cheaper but can be reclaimed with seconds to minutes of warning, while reservations and commitments trade flexibility for certainty. Here is how to split an LLM inference fleet across them.
Read guide → - Guide · 11 min
How to Benchmark LLM Inference: Tools and Method
A repeatable method for load-testing LLM serving, the metrics to report (TTFT, ITL, goodput), and vllm bench serve, SGLang bench_serving, GuideLLM and AIPerf compared.
Read guide → - Comparison · 12 min
Serverless GPU Inference Compared: Pricing and Cold Starts
Modal, Runpod Serverless, Replicate, Baseten and Cloud Run with GPUs compared on list price, cold starts and idle billing, with a worked cost example and a decision flow for picking one.
Read guide → - Comparison · 11 min
vLLM vs SGLang vs TensorRT-LLM: Which to Use
The three leading open-source LLM inference engines compared on hardware, prefix caching, disaggregated serving and release churn, with setup commands and a clear pick for each situation.
Read guide →
Evaluation & reliability
Quality, cost & reliability
Evaluate answers, control spending and handle failures.
- Guide · 10 min
LLM-as-a-Judge: How to Build a Grader You Can Trust
LLM judges make open-ended evals scalable, but they favour first-listed answers, longer answers and their own writing. Here is how to pick a judge format, write a rubric, and check a judge against human labels.
Read guide → - Guide · 4 min
Prompt Caching: When It Saves Money—and When It Does Not
Calculate cache-write cost, reuse and expiry together. A discounted read price only helps when an eligible unchanged prefix is actually reused.
Read guide → - Comparison · 10 min
AI Agent Benchmarks Compared: Which Ones Matter in 2026
Agent benchmarks test very different jobs, from rule-following and MCP tool use to web research and computer use. Here is what each one measures and how to read its scores.
Read guide → - Guide · 4 min
Before You Connect an MCP Server: A Practical Security Checklist
Treat an MCP connection as a grant of access. Check the server, data, permissions, credentials and revocation path before allowing an agent to use it.
Read guide → - Comparison · 10 min
Best AI CLI Coding Agents in 2026: Pricing and Verdict
Claude Code, Codex CLI, Copilot CLI, Antigravity CLI and OpenCode compared on pricing, setup, safety controls and fit, with prices as of Nov 2, 2026.
Read guide → - Comparison · 11 min
Best AI Code Review Tools in 2026: Pricing and Verdict
Seven AI code reviewers compared on official pricing, Git host support and what they do with a finding, from CodeRabbit and Copilot to Bugbot, Greptile and Claude Code Review.
Read guide → - Guide · 10 min
Build LLM Evals: Promptfoo vs Inspect
A practical guide to building a private LLM eval suite with Promptfoo or Inspect, plus how to move off OpenAI Evals before its Nov 30 shutdown.
Read guide → - Guide · 4 min
Cheap Model or Expensive Model? Measure Cost per Successful Task
Compare total cost divided by verified successes. Include failed attempts, retries, routing and tools before deciding that a cheaper token rate saves money.
Read guide → - Guide · 4 min
Get Reliable JSON from a Local LLM: Schema, Validation and Retries
Use structured outputs to constrain shape, then validate types and business rules. Valid JSON is a starting point, not evidence that the extracted facts are right.
Read guide → - Guide · 6 min
How to Read LLM Leaderboards in 2026 (Without Being Misled)
Arena votes, single benchmarks and composite indexes measure different things. Here is how to read scores, setups, ties and cost before you pick a model.
Read guide → - Guide · 12 min
How to Stop AI Coding Agents Leaking Secrets
A layered guide to keeping API keys away from Claude Code, Codex CLI and Cursor: deny rules, sandboxes, env filtering, pre-commit hooks, push protection and expiring tokens.
Read guide →