Your Claude Code already knows Treasure AI

Query customer data, build segments, and ship journeys from the terminal you already live in — in natural language, with production-grade governance. One command to start.

90%

Less time on routine CDP work.

1 command

from install to your first AI-built segment.

$0

use your existing Claude plan — or run on AI Suite credits with Treasure Code.

Quick start

Three steps in your existing Claude Code

Install the tdx CLI, authenticate, and add TD Skills from the plugin marketplace. Your Claude Code — your model, your plan, your settings — now operates your CDP.

You already run Claude Code

Add Treasure AI to your Claude Code setup

The td-skills plugins teach Claude Code how to drive tdx — segments, SQL, workflows — with validation before anything ships.

# 1 · install & authenticate the CLI npm install -g @treasuredata/tdx tdx auth setup # 2 · inside Claude Code, add TD Skills /plugin marketplace add treasure-data/td-skills /plugin install tdx-skills@td-skills /plugin install sql-skills@td-skills # 3 · just ask > “Which of our databases has last week’s web events?”
  • Keeps your existing Claude plan and configuration
  • Skills for SQL, segments, workflows, journeys — pick what you need
  • Respects your TD roles and policies on every call
New to Claude Code?

Treasure Code: Claude Code, included

No Claude subscription? tdx claude launches Claude Code on the TD LLM backend — TD Skills pre-installed, billed to your AI Suite credits.

# everything included, one command npm install -g @treasuredata/tdx tdx auth setup tdx claude
  • No separate Claude subscription — uses AI Suite credits
  • All TD Skills and docs search pre-loaded
  • Same governance, zero setup decisions

Learn more about Treasure Code →

TD Skills

Expertise, pre-installed

TD Skills are Claude Code plugins written by the people who built the platform. Install just what you need from treasure-data/td-skills — or get all of them at once with Treasure Code.

tdx-skillsSegments, parent segments, journeys, activations, Engage campaigns, Foundry agents
sql-skillsTD-flavored Trino & Hive, query optimization, time filtering
workflow-skillsDigdag pipelines, dbt, LLM-powered workflows
realtime-skillsReal-time personalization, triggers, ID stitching
sdk-skillsJavaScript & Python SDK integration patterns
creative-skillsAd ideation, brand compliance, email & social creatives
studio-skillsTreasure AI Studio workspace and scheduling
field-agent-skillsDeployment, documentation, visualization

Browse all skills on GitHub →

What you can do

Real CDP work, in plain language

Not a chatbot bolted onto a dashboard — Claude Code drives the same tdx commands your team uses, so everything it makes is reviewable and reproducible.

⌕

Explore customer data

Browse databases, inspect schemas, and run Trino/Hive queries without leaving the conversation.

Which tables hold purchase events, and how fresh are they?
◎

Build & ship segments

Draft segment rules as YAML, validate match rates, and push to production with an audit trail.

Build a segment of lapsed high-LTV buyers in Japan
⚙

Debug workflows

Diagnose failed Digdag runs, patch the .dig file, and retry — with the error context pulled in automatically.

Why did last night’s enrichment workflow fail?
↦

Design journeys

Compose multi-stage journeys with decision points and A/B tests, validated before anything goes live.

Add a 3-day wait and a coupon branch to the winback journey
✉

Create campaigns

Generate Treasure Engage email templates that pass brand and compliance checks on the first try.

Draft the July renewal email for the cart-abandoner segment
❏

Ask the docs

Claude searches Treasure AI documentation as it works — answers come with citations, not guesses.

What operators can I use in behavior conditions?
How it works

No magic — just the CLI your team already trusts

There’s no private API and no side door. TD Skills teach Claude Code to drive the tdx CLI — every action is a real command you could type yourself, authenticated as you, governed and logged like any other.

Claude Code + TD Skills Your prompts, plus skills that know TD’s commands, schemas, and guardrails.
→
tdx CLI Plain tdx commands — visible in the transcript, validated before anything is pushed.
→
Treasure AI platform CDP, segments, journeys, workflows — with your org’s policies enforced.

Using Cursor, Codex, or building your own agent? The same operations are also exposed as an MCP server via tdx mcp.

Policy-scopedAgents inherit the caller’s TD roles — nothing more.
Fully auditedEvery command lands in the audit log, same as the console.
Version-controlledSegments and workflows are YAML — diffable, reviewable, revertible.
Private by defaultYour customer data is never used to train models.

FAQs

If you already have Claude Code, no — TD Skills and the tdx CLI work with your existing plan at no extra platform charge. If you don’t, Treasure Code (tdx claude) launches Claude Code on the TD LLM backend, billed to your AI Suite credits.

Actions run through tdx with your TD role and policies — the agent can’t do anything you couldn’t do yourself. Destructive operations require explicit confirmation, everything is audit-logged, and segment or workflow changes are plain YAML you can review before pushing.

Databases and SQL (Trino/Hive), parent segments and segments, journeys, activations, Digdag workflows, Treasure Engage campaigns, and Foundry agents — everything the tdx CLI covers. TD Skills add task-specific expertise on top.

Yes — that’s the point. Marketers describe the segment or journey they want in plain language; the YAML, validation, and push happen underneath. For a fully no-terminal experience, see Treasure AI Studio.

TD Skills are open on GitHub at treasure-data/td-skills — every skill is a readable Markdown playbook, not a black box. The tdx CLI is documented at docs.treasure.ai.

The tdx CLI and TD Skills are free to install. Bring-your-own Claude Code uses whatever Claude plan you already pay for. tdx claude sessions draw on your AI Suite credits.