# Build brief — a focused alternative to Perplexity

> **Verdict:** Partly, if you narrow it · **Buildability:** 41/100 · **Category:** AI Search
> **Source:** https://www.canitbevibecoded.com/perplexity
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from Perplexity. Verify current pricing and capabilities before acting.

## Context

**Perplexity** — AI answer engine with web search, citations, and research modes. It currently costs $20/mo.

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.

This brief describes a focused, single-operator replacement for the part of Perplexity that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

## What you are building

Search the web/API, fetch pages, rank passages, ask an LLM to answer with citations, and store threads.

- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- Web fetcher/parser.
- Citation renderer.
- Hosted backend.

### Data and integrations

- Search API.
- LLM API.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

### Non-functional

- Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
- Security: server-side secrets, validated input, and no credentials in the client bundle.
- Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
- Portability: the operator can export their data and leave without losing it.

## Implementation brief

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.

## Delivery standard

- Inspect the repository first, then write a short implementation plan before writing code.
- Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
- Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
- Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
- Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
- Add structured logs around every external call and return actionable errors without leaking sensitive details.
- Write unit tests for the core logic and one automated test of the main user journey.
- Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

## Acceptance criteria

- [ ] A clean install starts the app using only the README and .env.example.
- [ ] The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
- [ ] Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
- [ ] The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
- [ ] Tests, type checking, linting, and a production build all pass with no ignored failures.
- [ ] No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

## Non-goals

Do not build these, and do not claim to have replaced them:

- Search quality.
- Source ranking.
- Model routing.
- Mobile/browser apps.
- The useful dataset is owned, accumulated, or expensive to reproduce.
- Model quality and inference operations are part of the product.

## What you still own after launch

- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.

## Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: medium. No independent one-shot implementation is linked yet.

## Prior art

Working open-source software you can read, fork, or borrow from before starting:

- [Perplexica](https://github.com/ItzCrazyKns/Perplexica) — Open-source AI search engine inspired by Perplexity

---

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/perplexity