Skip to content

Guide library

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.

  1. 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 →
  2. 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 →
View all 7 lessons and the capstone project →

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.

  1. 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 →
  2. 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 →
View all 7 lessons and the capstone project →

Everyday AI

Tools & workflows

Choose useful AI tools and put them to work.

  1. 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 →
  2. 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 →
  3. 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 →
  4. 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 →
  5. 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 →
  6. 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 →
  7. 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 →
  8. 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 →
  9. 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 →
  10. 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 →
  11. 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.

  1. 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 →
  2. 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 →
  3. 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.

  1. 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 →
  2. 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 →
  3. 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.

  1. Comparison · 9 min

    Vector Database Comparison: 6 Options for AI Agents

    Compare six vector database options, including Postgres with pgvector. Understand current entry pricing, access filters, operating effort and a fair workload test.

    Read guide →

Platforms & infrastructure

Hosting & inference

Plan GPU capacity, latency and serving costs.

  1. 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 →
  2. 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 →
  3. 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 →
  4. 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 →
  5. 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.

  1. 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 →
  2. 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 →
  3. 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 →
  4. 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 →
  5. 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 →
  6. 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 →
  7. 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 →
  8. 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 →
  9. 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 →
  10. 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 →
  11. 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 →