AI assistants and search decision
Earthly Insight
A capable developer can reproduce the core chat + donation-tracking product in a few weeks using existing LLM APIs and open-source agent UIs; the vendor's durable advantage is mainly brand and donation partnerships rather than technical barriers.
Visit website↗$20/mo
$240/yr
Read off the official pricing page.
$100one-off60 h to build
$70/mo3 h/mo upkeep
On cash alone, building overtakes the subscription at 4 seats.
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 Earthly Insight alternatives, with the arithmetic →
What a replacement has to do
- User sends text prompts -> backend forwards to an LLM provider -> receive & render responses in chat UI -> track per-user query usage and compute donation amount
What it still won’t have
- Polished native mobile apps and app-store deployment
- Any bundled or negotiated model access the vendor may have
- Brand, paid user trust, and turnkey donation partnerships/fulfilment
What remains hard
- Brand trust
Trusted by 5,000+ people
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 4 seats.
Money you would actually spend
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
Build a minimal web AI chat assistant using Next.js for the frontend, Node.js/Express for the API, PostgreSQL for storage, and integrate OpenAI (and optionally Anthropic) via their HTTP APIs. Core features in scope: email-based sign-up/login, a chat UI with message history, per-user query counting and a monthly donation-tracking table that records "subscription contribution = 33% of revenue" calculation, and an admin page to view totals. Explicitly out of scope: native mobile apps, payment processing/recurring billing UI (assume subscription exists), multi-vendor model-chooser UI beyond a single configured provider. Include input validation, error handling, unit tests for API routes, and deployment scripts for Vercel (frontend) and Railway/Heroku (backend).
How we checked
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
- Evidence score67
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.
- official productEarthly Insight — homepage
- official pricingEarthly Insight — pricing section on homepage
- open sourceChatGPTNextWeb/NextChat
- open sourceleon-ai/leon
Integrity checks
What held up, and what did not.
