Predicate Ventures
All projects

Liveproduct

Content Engine

The publishing pipeline behind this site.

A multi-tenant content service: keyword and SERP research, model-assisted drafting, Postgres storage, and a versioned read API that consuming sites fetch. This site is one tenant, and Content Engine serves every article on /writing.

  • Multi-tenant content API
  • Citation-gated
  • Versioned read API
  • Live
Join the waitlist
  • NLP & information extraction
  • Data science & evaluation
  • Cloud infrastructure
  • Architecture & developer experience
articles live on /writing
21
test files
66

The problem

Publishing that compounds needs research, drafting, editing, images, distribution and cache invalidation working as one pipeline. Assembled by hand from separate tools, it degrades the moment anyone gets busy.

The approach

Content Engine is a content API with tenants, not a content-management system. Research and generation sit upstream of a clean read surface, and a publish webhook invalidates the consumer’s cache. The consuming site stays a thin presentation layer. A citation gate holds an article in draft until source coverage clears a threshold: an editorial control rather than a disclaimer.

How Content Engine fits together

  1. Research

    SERP and keyword

  2. Draft

    Model-assisted

  3. Citation gate

    Held in draft until sources clear a threshold

  4. Read API

    Versioned and multi-tenant

  5. Consumer site

    A publish webhook invalidates its cache

Research and drafting upstream, a clean read API downstream.

What Content Engine does

  • A citation gate, not a disclaimer

    An article stays in draft until its source coverage clears a threshold. The gate is an editorial control, not a caveat.

  • A thin presentation layer

    The consuming site fetches from a clean, versioned read API, while research and drafting sit upstream.

  • Publish-time cache invalidation

    A bearer-authenticated webhook invalidates the consumer's cache the moment an article goes live.

  • Builds green when unreachable

    The consuming site degrades to an empty list rather than failing the build.

What’s inside Content Engine

  • A multi-tenant read API, versioned, with per-article citation sources and server-computed reading time
  • SERP and keyword research upstream; model-assisted drafting with a citation gate
  • Postgres for storage, blob storage for media
  • A bearer-authenticated publish webhook driving tag-scoped cache invalidation on the consumer
  • Graceful degradation: the consuming site builds green when the API is unreachable, returning an empty list rather than failing

Where Content Engine stands today

  • Twenty-one articles live on /writing, served through the read API
  • Replaced an earlier in-repo pipeline, now retired to a redirect manifest so no shared link ever 404s

The Content Engine tech stack

  • TypeScript
  • Node 20
  • Hono
  • Vercel
  • Neon Postgres
  • Vercel Blob
  • Claude
  • GitHub Actions

Get early access to Content Engine

Content Engine is not generally available yet. If you want a tenant of your own, leave an email and we will tell you when that is possible.