AI for Data & analytics teams
Claude for data analysis: Claude for Excel, text-to-SQL, notebooks with Claude Code, checking AI analyses, and the analytics tools that hold up.
Start here
Read these in order — each one assumes the last.
- 01GuideClaude for Data Analysis: The Complete 2026 GuideClaude for data analysis in 2026: chat, Excel, Claude Code, or Cowork, what the code execution sandbox is, its limits, failure modes, and how to verify results.
- 02GuideClaude for Excel: What It Does, Where It Fails, How to Use ItHow Claude for Excel works in 2026: install, supported builds, plan gating, cell-level citations, model debugging, what it cannot do, and a review checklist.
- 03GuideClaude Code for Data Analysts: Notebooks, SQL, and CSV Work Without a Data EngineerSet up Claude Code for analysis: an analysis repo with CLAUDE.md, CSV profiling, a pandas loop, read-only warehouse queries, and deny rules that hold.
- 04GuideThe Best AI Tools for Data Analysts in 202615 AI tools for data analysts in 2026: assistants with code execution, spreadsheet add-ins, notebooks, text-to-SQL, and terminal agents, with a verdict each.
- 05GuideWhich Claude Plan (and Model) Should a Data Analyst Pay For?Free, Pro, Max, or Team for data analysis: which plan unlocks Excel, Claude Code, and Cowork, how usage limits bite, and which model fits which analysis task.
Guides14
Tutorials and deep-dives
What Are Claude Skills? The Complete Guide
Claude Skills explained: what a SKILL.md is, how progressive disclosure keeps skills cheap, where they run, and how to install or write your own.
LLM API Pricing in 2026: Every Major Model Compared
Per-million-token prices for Claude, GPT, Gemini, DeepSeek, Mistral, and Grok — plus caching and batch discounts — verified against vendor pricing pages.
How RAG Actually Works: Ingestion, Chunking, Retrieval & Reranking
A clear, practical walkthrough of the retrieval-augmented generation pipeline — what each stage does, where it fails, and how the pieces fit together.
Anthropic's Data Plugin for Claude: Every Skill Explained
Every skill in Anthropic's open-source data plugin for Claude Cowork and Claude Code, the warehouse connectors it expects, the install commands, and its gaps.
ChatGPT vs Claude for Data Analysis
ChatGPT vs Claude for data analysis, compared on sandbox behavior, file limits, Excel add-ins, chart output, citations, warehouse access, and verification.
Claude Skills for Data Analysts: 5 to Upload Today
Five portable skills that make Claude behave like a careful analyst: first look, chart choice, memo writing, SQL explanation, and formula auditing.
How to Check an AI Data Analysis Before You Trust It
Eight ways an AI-generated analysis goes wrong, the specific check that catches each one, and a copyable checklist to run before a number ships.
Text-to-SQL with Claude: A Safe Read-Only Postgres Setup
Set up text-to-SQL with Claude on Postgres safely: a read-only role, an MCP server in read-only mode, schema and metric context, and a two-way check.
The Best Text-to-SQL Tools in 2026
Text-to-SQL tools compared on how they ground the model in your schema, what accuracy really means, read-only safety, deployment, licensing, and pricing model.
Claude's Document Skills: Excel, PowerPoint, Word, and PDF
How Anthropic's pre-built document skills let Claude produce real .xlsx, .pptx, .docx, and PDF files — on claude.ai, the API, and in Claude Code.
LLM Context Windows Compared (2026)
Context windows and max output tokens across Claude, GPT, Gemini, DeepSeek, and Grok — the million-token era, what it costs, and what fits in practice.
How Embeddings Work: Vectors, Similarity, and Choosing a Model
What an embedding actually is, how similarity is measured, how the models are trained, and the practical rules for using embeddings well in search and RAG.
Using Vision-Language Models for OCR, Documents, and Video Understanding
How to use vision-language models for OCR, documents, and video: how they differ from traditional OCR, their failure modes, and getting reliable output.
Choosing the Right Model: Haiku vs Sonnet vs Opus
How to pick the right Claude model tier — Haiku, Sonnet, or Opus — for any Claude Code agent or task, with a clear decision rubric and per-agent examples.
Tools12
The AI tooling directory
Databricks Genie
Databricks' conversational analytics layer: Genie Agents answer natural-language questions over Unity Catalog data using curated instructions and SQL.
Deepnote
A collaborative data notebook whose AI agent edits and runs your blocks, with data apps, a semantic layer, and integrations across warehouses and BI tools.
Hex
A collaborative notebook and data-app platform whose AI agents write SQL and Python, answer questions in Threads, and run on curated workspace context.
Julius
A chat-first AI data analyst: upload a spreadsheet or connect a warehouse, ask in plain English, and get charts, code, and shareable exports back.
Pandasai
A Python library that adds a chat method to your dataframes: it generates and runs pandas code to answer questions, with an optional Docker sandbox.
Thoughtspot Spotter
ThoughtSpot's agentic analyst: it resolves questions into search tokens against a governed semantic model rather than raw SQL, then acts on the answer.
Vanna
An MIT-licensed Python framework for text-to-SQL: a user-aware agent that learns from successful queries and streams tables, charts, and summaries back.
Docling
Open-source Python library that parses PDFs, DOCX, PPTX, HTML, and images into structured Markdown and JSON with layout, tables, and reading order for RAG.
LlamaParse
Hosted document-parsing API from LlamaIndex that turns complex PDFs — tables, charts, figures, handwriting — into clean, LLM-ready Markdown for RAG.
Postgres MCP Pro
The maintained Postgres MCP server — safe SQL execution, EXPLAIN with hypothetical indexes, workload-driven index tuning, and database health checks.
Supabase MCP
Supabase's official MCP server — run SQL and migrations, read logs and advisors, generate types, and deploy Edge Functions, with read-only and project scoping.
LM Studio
A desktop app for discovering, downloading, and running open-weight LLMs locally with a GUI and a local OpenAI-compatible server.
Glossary11
AI terms, defined precisely
AI Data Analyst
An AI data analyst is a tool that takes a data question, writes and runs the code or SQL to answer it, and returns a chart or summary you still have to check.
Code Execution (Code Interpreter)
Code execution lets an AI assistant write and run real code in a sandbox, so numbers, files, and charts come from a computation rather than an estimate.
Conversational Analytics
Conversational analytics is asking questions of governed business data in plain language and getting a chart or number back, without opening a dashboard.
Semantic Layer
A semantic layer defines business metrics, dimensions, and joins once, so every query and every AI agent computes the same number the same way.
Text-to-SQL
Text-to-SQL is turning a plain-language question into a SQL query a database can run, using a model grounded in your schema, documentation, and past queries.
Grounding
Grounding ties a model's output to verifiable sources — retrieved documents, tool results, citations — instead of training-data memory.
Context Window
The context window is the maximum text — measured in tokens — an LLM can consider at once: prompt, conversation, documents, and its own output combined.
Embedding
An embedding is a vector of numbers representing text's meaning, placed so similar texts land close together — the foundation of semantic search and RAG.
Hallucination
A hallucination is fluent, confident output that is factually wrong or fabricated — plausible text unsupported by any source, the signature LLM failure mode.
RAG (Retrieval-Augmented Generation)
RAG retrieves relevant documents from your own data and injects them into an LLM's prompt at query time, grounding answers in facts the model wasn't trained on.
Structured Output
Structured output makes an LLM return data in a guaranteed shape — JSON matching your schema — so code can consume model responses without parsing prose.
Agents3
Specialized subagents for focused work
Analysis Reviewer
Use this agent to review a finished analysis for methodological errors before it ships — checking grain and double counting, join fan-out, rows silently dropped by filters and inner joins, sampling and truncation, null handling, time zone and date boundaries, numbers in the prose that disagree with the code's output, charts that mislead, and causal language resting on correlational evidence. Examples — 'review this notebook before I send the deck', 'the query and the summary disagree somewhere, find it', 'does this analysis actually support the conclusion it draws?'.
SQL Pro
Use this agent for SQL itself — correct joins and window functions, indexing, EXPLAIN plans, schema design, and safe migrations on Postgres/MySQL. Examples — making a slow query fast, designing a normalized schema, writing a reversible migration.
Data Scientist
Use this agent for data analysis — exploration, statistics, SQL, and clear findings. Examples — analyzing a dataset, writing an analytical SQL query, summarizing experiment results.
Skills7
Reusable capabilities Claude loads on demand
Analysis Memo Writer
Turn findings and figures you supply into a stakeholder writeup with a fixed spine: headline finding, what the number is and what it is not, method in three lines, a mandatory caveats and limitations section, what would change the conclusion, and one recommended next step. Never invents a figure and never upgrades a correlation into a cause. Use when the analysis is done and has to survive being read by someone who was not in the query.
Chart Chooser
Pick the chart for a stated question and data shape and defend the choice: the recommendation, the reasoning, the alternatives rejected and why each fails this question, encoding rules for axis baseline, sorting, color, and labels, and generated code in the plotting library you name. Use when you know what you want the chart to say and need the one form that says it, not a gallery.
Dataset First Look
Turn a pasted CSV header with sample rows, a pasted table, or an attached data file into a fixed plain-language profile: shape, column inventory with inferred types, null and blank patterns, cardinality, suspicious columns, duplicate-key risk, outliers worth a look, and the questions to settle before analyzing. Use when a dataset just landed and you need to know what you are holding before you write a query.
Spreadsheet Formula Auditor
Audit pasted spreadsheet formulas or a described model for the errors that survive review: hardcoded values buried inside formulas, ranges that drift or truncate, one cell in a row that does not match its neighbors, circular references, sign errors, IFERROR masking a real failure, and volatile functions, returned as a fix list ordered by how much money the error moves. Use before a model that carries a real decision leaves your hands.
SQL Explainer
Walk through a pasted SQL query in execution order in plain language: what each step does, the grain of the result, where a join can fan rows out, which filters silently drop rows, and a ranked list of what could be wrong. Comprehension only, not performance tuning. Use when you inherited a query, are reviewing one before trusting its numbers, or have to explain it to someone who does not read SQL.
Multimodal Document Extractor
Extract structured data from documents and images with a vision-language model — define the target schema, prompt the VLM to fill it from the page (invoices, forms, receipts, statements, IDs), and verify critical fields against the source. Use when you need reliable structured output from messy, varied, or scanned documents that defeat template-based OCR.
SQL Optimizer
Diagnose a slow SQL query from its execution plan and propose a verified optimization — finding the real bottleneck (sequential scan, missing or unused index, bad join order, app-side N+1) and measuring the fix before and after. Use when a query is slow and you need a fix backed by EXPLAIN ANALYZE, not a guess.
Commands2
Slash commands for Claude Code
Define Metric
Write or refine a metric definition — name, plain-language meaning, grain, filters, source tables and columns, edge cases, and owner — into analysis/metrics/<slug>.md, after searching the repo for a definition that already exists.
First Look
Read the first rows and the true row count of a CSV or spreadsheet, profile it against a fixed checklist, and write the result to analysis/profiles/<name>.md so the dataset's condition is on record before anyone queries it.