Email and newsletters decision

Shortwave

A competent developer can build a narrow Shortwave-like workflow (summaries, AI search, basic triage) over several weeks, but the full paid product's compliance, broad integrations, polished cross-platform apps, and advanced automation are costly to replicate.

Visit website
Subscription$30/month ✓ verified
Initial build80 hours
Monthly upkeep12 hours + $100
Evidence3/3 runs agree

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Shortwave alternatives, with the arithmetic →

What a replacement has to do

  • Fetch users' mail, index messages & attachments, run LLM prompts to summarize/search/compose, present an inbox UI with triage controls and apply mailbox actions (labels/archive/send) via provider APIs

What it still won’t have

  • Enterprise CASA Tier 2 compliance
  • Built-in integrations and sister-product Tasklet automation
  • Polished cross-platform native apps (iOS/Android/Mac/Windows)
  • Deeply integrated team collaboration features (shared threads, real-time comments)
  • Optimized AI usage quotas, advanced model options, and long-term search history guarantees

What remains hard

  • Compliance and regulationMeets the strict requirements of CASA Tier 2 compliance
Read the build prompt

First-year cost

Keep paying

Paying ischeaper in year one.

On cash alone, building overtakes the subscription at 4 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 Shortwave-like web app using React for the frontend, Node.js + Express for the backend, Postgres for metadata, Pinecone or Milvus for embeddings, and OpenAI/Anthropic APIs for LLM features. In scope: Gmail OAuth sync, indexing emails & attachments, embedding storage, AI-powered summaries, a searchable inbox UI with bundles and basic triage actions (label, archive, reply), and server-side job to apply scheduled delivery. Out of scope: native mobile/desktop builds, advanced enterprise compliance, multi-tenant billing, and sister-product automation. Include error handling for failed syncs and API rate limits, per-user usage accounting, and automated tests for sync, indexing, and summarize endpoints.
How we checked4 sources · 3/3 runs agreed · evidence score 64

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 4 cited sources+3
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • Hard moats found in the evidence-3
  • Evidence score64

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 · 4

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat quoted from the page