Paid-acquisition planning engine (CLI, API, MCP) · In development · 2026

Ads Acquisition Engine

From brief and website to a full paid-acquisition plan, offline.

Type
Paid-acquisition planning engine (CLI, API, MCP)
Status
In development
Year
2026
Disciplines
Marketing automation
Data & planning
Developer tool
Technology
TypeScript
Node.js
zod
SQLite

In development. Version 1 with a test suite. It plans and exports; it ships no live connection to ad platforms, and execution is a dry run by default.

Disclosure. The demo runs on LumenDesk, a fictional brief included in the repository, with synthetic performance data.

Overview

The project in brief

An offline-first TypeScript engine that turns a brief and a website into a paid-acquisition plan — strategy, tracking, creative with QA, campaigns, experiments and diagnosis — through a CLI, an HTTP API and an MCP server.

The engine reads a brief and a landing page, infers the funnel, call to action and value proposition with flagged confidence, then produces channel strategy with feasibility warnings, a tracking plan and attribution model, creative concepts and platform-fitted variants checked by creative QA, campaign architecture and experiments with sample sizes. Imported performance data is diagnosed and turned into recommendations.

State lives in SQLite and every non-computed fact carries its source. Sending anything to a platform needs an approval bound to a hash, credentials and a registered transport; version 1 has none, so npm run demo runs the whole pipeline offline and contacts nothing.

Built by
SIMONVILSTECH
Nature
Own product
Client
None

01What it solves

Paid-acquisition plans are assembled by hand across tools, and nothing ties the creative back to the tracking and the landing page.

Who it is for
Marketing teams and agencies planning paid campaigns.

02What was built

  • Website analysis: offer, CTA, funnel, proof, friction
  • Channel strategy with feasibility warnings
  • Tracking plan and attribution model
  • Creative concepts and variants with QA
  • Campaign architecture
  • Experiment planning with sample sizes
  • Performance diagnosis and recommendations
  • Hash-bound approvals; dry run by default
  • CLI, HTTP API and MCP server

03In use

The offline demo in a terminal: brief → website analysis → strategy → tracking → creative and QA → campaigns → diagnosis → export → dry run, with no platform contacted
A full plan, offline, with nothing sent

04Built with

  • TypeScript
  • Node.js
  • zod
  • SQLite
  • MCP
  • Vitest

05Where it stands

In development

Version 1 with a test suite. It plans and exports; it ships no live connection to ad platforms, and execution is a dry run by default.

The demo runs on LumenDesk, a fictional brief included in the repository, with synthetic performance data.

Started
1 October 2026
Last updated
1 October 2026
Next projectVideo2BlogVideos into articles you can verify.

Have a routine that should run by itself?

Tell us what you need and by when. We read every enquiry and reply in writing, with questions, a next step, or a plain no if we’re the wrong studio.