[verdict][generated prompt][source: perplexity.ai]
Can I vibecode Perplexity?
// buildable in a weekend, but real gaps stay open
A retrieval-plus-LLM answer engine is buildable, but Perplexity's search stack, source ranking, UX, mobile/browser surfaces, and model access make full parity hard.
confidence: medium
what it is: AI answer engine with web search, citations, and research modes
Buildability index · an editorial game
- Price 20 $/month weight: plus 2
- Time multi-day weight: plus 1
- Category ai search no weight
- Moat proprietary data · proprietary models · execution quality weight: minus 5
- Confidence medium weight: zero
- What you lose 6 items weight: minus 3
- Site perplexity.ai (si apre in una nuova scheda) no weight
It is not close. The prompt below rebuilds a piece, not the product.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Search the web/API, fetch pages, rank passages, ask an LLM to answer with citations, and store threads.
what you need
- search API
- web fetcher/parser
- LLM API
- citation renderer
- hosted backend
A nuanced kinda: there is real open-source prior art, but source quality and scale matter.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a personal answer engine like Perplexity, wrapping real search and LLM APIs,
not rebuilding them. Requirements:
- A local web app on localhost:3000: Node + Express + htmx, one input box, streamed
answers.
- Per question: query the Brave Search API (key in .env), fetch the top 6 results with
undici, extract readable text with @mozilla/readability + jsdom, then pass the
question plus numbered excerpts to Claude or GPT (key in .env) with instructions to
answer only from the excerpts and cite as [1][2].
- Render citations as footnote links; show the full source list under every answer.
- Follow-up questions stay in the same thread with prior Q&A in the context window.
- Threads stored in SQLite via better-sqlite3; a sidebar lists past threads by first
question.
- If a page fails to fetch or extract, drop it and continue. Never cite a page that was
not fetched.
- Binds to localhost only; no accounts, no telemetry, only the search and LLM calls
leave my machine.
- Out of scope: crawling my own web index, model routing, and mobile apps. Answer
quality tracks the search API, that is the deal.
- README: which keys to get (Brave Search has a free tier) and rough per-query cost.Prompt generated from the data on this page, not reviewed by hand yet. In English on purpose — it is the language coding agents work best in.
What you lose
- search quality
- source ranking
- model routing
- mobile/browser apps
- publisher integrations
- speed
Why people still pay
They pay because answers arrive fast with sources and fewer query-building chores.
moat: Proprietary data Proprietary models Execution quality what a moat is
search/data/model routing
Free alternatives
Not in the mood to build it? These already exist, they are free or open source, and we checked them one by one.
Rejected (1) — and why
- Perplexity Standard (si apre in una nuova scheda) — Basic searches are practically unlimited; Pro Search and Research are explicitly very limited, which is the paid product's point.
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- Perplexica (opens in a new tab) — Open-source AI search engine inspired by Perplexity. (alive)
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
