AI learning guide

Best AI resources for data teams

Connect data, ML, retrieval, observability, and production workflows.

Best production ML habits: Made With ML. Free course covering production ML workflows. Start here if your data team needs engineering habits that transfer to AI systems.

Best structured ML engineering path: DataTalks.Club ML Zoomcamp. Free cohort course for machine learning engineering. Use it when data engineers need a clear bridge into ML and AI engineering.

Best observability path: Phoenix by Arize. Open-source tracing and eval tooling for LLM applications. Use it when data teams own quality measurement and debugging.

Data teams already own many AI foundations

Data teams understand pipelines, quality checks, schemas, dashboards, experiments, and production data. Those skills transfer directly into RAG, evals, observability, and AI product measurement.

Made With ML and DataTalks.Club are good bridges into ML engineering. Phoenix is useful when the team needs to inspect LLM traces and evaluate workflow quality.

Move from data access to AI quality

A data team supporting AI should think about source freshness, permissions, feature stores, retrieval quality, eval datasets, and monitoring. The model is only one part of the system.

Good resources should connect data engineering habits to AI workflows: reproducibility, lineage, test sets, observability, and clear ownership of failure modes.

Recommended courses and resources

OpenAI eval design guide

Guide · OpenAI · Intermediate

You need practical guidance for designing representative eval datasets, choosing graders, and turning model testing into an engineering loop instead of ad hoc spot checks.
OpenAI evals quickstart and datasets

Guide · OpenAI · Intermediate

You want OpenAI's current quickstart for turning examples into dataset-backed evals and improvement loops instead of relying on a deprecated docs path.
Anthropic MCP guide

Guide · Anthropic · Intermediate

You want Anthropic's official guidance for exposing tools and data to Claude through MCP instead of only reading the base spec.
OpenRouter benchmarks API

API reference · OpenRouter · Intermediate

You want machine-readable benchmark data for coding, intelligence, or agentic tasks before choosing or routing across model families.
OpenRouter rankings data API

Data API · OpenRouter · Intermediate

You want current usage and rankings data that reflects what developers are actually using, not only benchmark scores or launch-day marketing.

Roll a learning mission

Pick one small move from this guide instead of opening ten tabs.

Open mission

About this guide

Author: Learnetto Editorial Team. Learnetto maintains this AI learning directory by organizing public course pages, official documentation, educator material, and practical learning resources.

How it is made: Learnetto uses public course pages, official documentation, educator material, and directory data to compile these recommendations. AI may help draft and organize the page, but recommendations are checked against the listed sources, page topic, and learner intent.

Review policy: We only add a named personal reviewer when that person has substantially reviewed the page. Until then, the page is attributed to Learnetto rather than a founder, editor, or individual expert.

Last updated: June 27, 2026. Suggest a correction if a course, doc, or recommendation is outdated.

Videos to watch

►

Pinecone semantic search

Pinecone

►

ML Zoomcamp supervised learning

DataTalks.Club

Educators and sources

Educator / source	Best for	Skills	Start with
Rachel Thomas fast.ai	Developers, data scientists	Practical ML, Ethics, Education	Use fast.ai essays and course material alongside hands-on notebooks.
Jason Liu Instructor	Developers building LLM apps	Structured outputs, Extraction, RAG	Try the Instructor examples for extraction and validation.
Eugene Yan Eugene Yan	ML engineers, data teams	Applied ML, Recommenders, LLM systems	Read the applied ML and LLM systems posts.
Christopher Penn Trust Insights	Marketers, analysts, business leaders	AI marketing analytics, Prompting, Data strategy, Measurement	Find a generative AI or analytics workflow and run it on your own marketing data.
Rand Fishkin SparkToro	Marketers, founders, audience researchers	AI search, Audience research, Marketing strategy, Content quality	Use AI as an analysis assistant after gathering audience data, not as a substitute for research.
Chase Dimond Email marketing and AI workflows	Ecommerce marketers, email marketers, founders	AI email marketing, Lifecycle campaigns, Copywriting, Ecommerce	Use AI to draft variants for one email campaign, then edit with performance data in mind.
Jerry Liu LlamaIndex	Developers building RAG and document agents	RAG, Agents, Document workflows, Context augmentation	Read the LlamaIndex introduction, then build a small document Q&A app.
Ben Lorica The Data Exchange	Data and AI practitioners	Data systems, ML engineering, AI trends	Search episodes by topic: RAG, evaluation, agents, MLOps.
Greg Kamradt Data Independent AI tutorials	Developers learning RAG and LLM apps	RAG, LLM apps, Prompting, Evaluation	Search the channel for the RAG or LangChain workflow you are building.
Connor Shorten Weaviate education videos	Developers learning retrieval	Vector search, RAG, Hybrid search, Agents	Use Weaviate videos on hybrid search and RAG basics.
Tina Huang Tina Huang AI and data career videos	Beginners and career switchers	AI literacy, Data skills, Career learning, Prompting	Use beginner learning-roadmap videos to choose a first path.
Krish Naik Krish Naik AI tutorials	Developers and data science learners	Machine learning, Deep learning, LLM apps, MLOps	Pick a playlist that matches your current level and follow the code.
Sean Grove OpenAI and AI engineering talks	AI engineers and product builders	AI engineering, Developer tools, Agents, Structured data	Watch talks on AI-native interfaces and structured workflows.

Resources

OpenAI eval design guide

Guide · OpenAI · Intermediate

You need practical guidance for designing representative eval datasets, choosing graders, and turning model testing into an engineering loop instead of ad hoc spot checks.

OpenAI evals quickstart and datasets

Guide · OpenAI · Intermediate

You want OpenAI's current quickstart for turning examples into dataset-backed evals and improvement loops instead of relying on a deprecated docs path.

Anthropic MCP guide

Guide · Anthropic · Intermediate

You want Anthropic's official guidance for exposing tools and data to Claude through MCP instead of only reading the base spec.

OpenRouter benchmarks API

API reference · OpenRouter · Intermediate

You want machine-readable benchmark data for coding, intelligence, or agentic tasks before choosing or routing across model families.

OpenRouter rankings data API

Data API · OpenRouter · Intermediate

You want current usage and rankings data that reflects what developers are actually using, not only benchmark scores or launch-day marketing.

OpenRouter models API

API reference · OpenRouter · Intermediate

You want a machine-readable way to inspect current models, filters, and metadata across providers.

Hugging Face model hub

Model catalog · Hugging Face · Beginner to advanced

You need to discover, compare, and run open model checkpoints, datasets, and demos.

LlamaIndex Docs

Docs and examples · LlamaIndex · Intermediate

You need to connect LLMs to documents, data, and retrieval.

Kaggle Intro to Machine Learning

Micro-course · Kaggle · Beginner

You need small exercises for ML basics.

Weaviate Academy

Free academy · Weaviate · Beginner to intermediate

You want structured vector database and retrieval lessons.

DataTalks.Club ML Zoomcamp

Free cohort course · DataTalks.Club · Beginner to intermediate

You want a structured free path into ML engineering.

Mission Control AI

Preconfigured AI workers · Mission Control AI · Business to enterprise

Use this when you want role-specific AI workers with SOPs, integrations, and governance policies already built in. Map one operational process, identify data and approval boundaries, and evaluate whether a prebuilt worker fits before building custom agents.