Intempt CLI
Instrument the codebase, not a spreadsheet.
Scan your source, generate a tracking plan, and ship typed SDK wrappers for 14 platforms - so an analytics call that does not match the plan fails at compile time, not in a dashboard three weeks later.
What you can do
Which accounts have power users who went quiet this month?
Resolves against the real accounts and users domains - no export, no spreadsheet.
Create a segment of trial users who haven't converted in 14 days.
One call against the segments domain builds it live, ready to route into a journey.
Get the funnel drop-off for our signup flow this quarter.
Pulls real funnel step analytics - the same data your dashboards already show, without opening one.
Summarize my last three meetings with Acme Corp.
Reads real meeting summaries and activity - the meetings domain, not a guess.
Draft outreach for the accounts that just hit power-user status.
Uses the same outreach drafting Blu runs in-app, callable directly from your agent.
List every journey with a live A/B experiment right now.
journeys is the largest domain in the registry (43 real operations) - experiments, schedules, and drafts included.
What's our brand voice guidance for outbound emails?
Reads real brand-kit and persona data so generated copy actually matches your brand, not a generic tone.
Pull the deal activity for every open deal over $50k.
Real deal and activity data from the deals domain - no CRM export required.
Get started
Pick how you want to use it, paste the matching prompt into your agent.
For scripted and batch work in the terminal. Every registry command supports --json for piping into other tools. Want to ask in plain language instead? Use the MCP server.
setup prompt - paste into Claude Code
You are helping me set up the Intempt CLI. It scans a codebase, proposes a tracking plan, and generates typed SDK wrappers for 14 platforms. Walk me through it one step at a time, run commands for me where you can, and wait for my confirmation before moving on. 1. Install it: npm install -g @intempt-technologies/cli The published package is @intempt-technologies/cli. Note @intempt/cli does NOT exist on npm - the repo README still says that and it 404s. 2. Run "intempt init" in my project. It detects the framework, language and package manager, then offers an AI scan, a guided walkthrough, or an empty plan. Use the AI scan and show me the events it proposes before accepting. 3. Show me the intempt.yaml it wrote and explain what each event captures. 4. Run "intempt generate" to write typed wrappers for my platform, and show me one call site so I can see what the types buy me. 5. Run "intempt status" and show me which planned events are still missing from the code. If a step fails, show me the exact error and fix it with me before moving on.
FAQ
What can it actually access?
Your own source tree, and nothing else. The CLI reads the code you point it at to propose a tracking plan; it does not read your Intempt data. Generating wrappers needs no credentials at all.
Do I need to be a developer to use this?
To run it, no - `intempt init` walks you through detection and proposes the plan for you. To use what it writes, yes: the output is typed wrapper code that lands in your repo and gets imported like any other module.
How does authentication work?
Device-code login runs from inside the chat itself - say "log me in to Intempt" and approve in your browser, no terminal needed. CI and automation use a static token instead.
Where do my credentials live?
Locally. The tracking plan is a plain intempt.yaml in your repo, and the AI scan sends source to the model provider only for the files you approve. Nothing routes through an Intempt server.
Is this an official Intempt product?
Yes - built and maintained by Intempt, not a community integration.