Design and diagrams decision

RelayThat

A capable developer can reproduce the core templating, resizing, and headline-generation workflow in ~30 hours, but the full product value (large image library, polished team workspace, and long-term product polish) is not practical to replicate quickly.

Visit website
You pay

$15/mo

$180/yr

Per seat. Read off the official pricing page.

You’d pay instead

$50one-off30 h to build

$20/mo6 h/mo upkeep

On cash alone, building overtakes the subscription at 2 seats.

No open-source build does this yet

Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.

What a replacement has to do

  • Create templated layouts from brand assets, auto-resize/remix layouts to multiple channel sizes, render/export images, manage/upload brand assets (fonts, colors, logos), and run a headline/text generator.

What it still won’t have

  • Large built-in curated image library (3M images) and any included image licensing
  • Polished UX and turn-key team/collaboration features
  • Ongoing product improvements and proprietary template collections
  • Brand portal and workspace-level management features at relaythat scale

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 2 seats.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal RelayThat-style service using Node.js (Express), Postgres, S3, and a React frontend. Implement: (1) brand asset management (fonts, colors, logos) stored in Postgres with files in S3; (2) a server-side template/layout engine that composes images and text into configurable templates and produces multiple output sizes using Sharp; (3) a batch export endpoint that zips channel-sized images; (4) a simple headline generator wired to an LLM API (configurable API key); (5) auth, project/workspace switching, and a basic web UI to select templates and assets. Out of scope: analytics dashboard, large curated image library, multi-user enterprise features, and white-labeling. Include error handling, input validation, unit tests for core image pipeline and export flows, and Docker-based deployment scripts.
How we checked2 sources · 1/3 runs agreed · evidence score 56

How the score was reached

  • Partly verdict base52
  • 2 cited sources+1
  • Price verified on pricing page+3
  • Evidence score56

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 1 of 3 runs agreed; the verdict is the middle of them✓ Citations limited to fetched pages! 1 moat recorded