Deterministic SEO/AEO/GEO automation platformMVP
SearchOps AI
A TypeScript monorepo that runs crawl, analyze, workorder, and recheck loops deterministically without LLM dependence, isolating AI inside a replaceable ai-core.
Overview
SearchOps AI closes SEO, AEO, and GEO operations into a crawl, analyze, workorder, and recheck loop.
The core rule engine is kept independent from LLMs, while AI lives inside a replaceable ai-core package. App and package boundaries separate the API, web app, worker, connectors, and rule engines so each can evolve independently.
Its strength is treating search operations as a repeatable system, not a one-off report. It generates human-actionable workorders and then closes the loop through rechecks.
Core skills
Rule-based SEO/AEO/GEO engine design
Monorepo boundaries, runtime separation, and workorder modeling
GSC, GA4, PageSpeed, and CMS connector boundaries
Implementation
- 1Split responsibilities across apps/api, apps/web, apps/worker, and packages/*, then documented dependency rules.
- 2Kept the SEO core independent from AI packages so rule execution and rechecks remain reproducible.
- 3Modeled workorders as human-actionable tasks and closed them through a recheck loop.
Strengths
- Separates core SEO judgment from LLMs so the same input produces the same output.
- Defines clear boundaries across 13 packages and 3 apps for extension and testing scope.
- Includes medical compliance plus AEO/GEO rules inside the operations loop.
Metrics
16
workspaces
106
commits
3
runtimes
0
core LLM deps
Tech stack
TypeScriptNext.js 15FastifyPrisma 6PostgreSQLRedisBullMQTurborepopnpm
Screenshots