Can I vibecode AmICited?

What you build

Run your buyer questions through the answer-engine APIs on a schedule, store each answer, and score brand and competitor mentions plus cited sources, as a rough personal proxy for the real consumer-surface answers.

what you need

• headless browser automation (Playwright/Puppeteer) to reach the real consumer surfaces, not just model APIs
• residential or geo-targeted proxies to query from specific countries
• a scalable scheduler/queue and the infra to run and retry many browser sessions in parallel
• durable per-run storage that never overwrites an answer, so history compounds
• ongoing upkeep as each engine and surface changes its UI, models, and citation format

The scoring is a weekend project; the geo-proxied real-browser fleet, the compounding archive, and the human consulting behind it are not. Recheck EUR pricing before merge.

The prompt

A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.

Build me a local AI answer-engine citation tracker for one brand, as a rough personal proxy. Requirements:

- Node 22, TypeScript, SQLite via better-sqlite3, a CLI, and a plain server-rendered
  dashboard. Local only, no accounts, no telemetry.
- brand.json holds my brand name, aliases, domain, and competitor names. prompts.json
  holds up to 50 buyer questions.
- `track run` sends every prompt through OpenAI, Anthropic, Gemini, Perplexity, and xAI
  (Grok) with each provider's web search or grounding tool enabled. Keys live in .env.
- Store one immutable row per run, prompt, and provider: the full raw answer, cited
  URLs, model id, latency, and error text. Never overwrite an existing run, so the
  archive compounds over time.
- Cap concurrency at 3 per provider, retry twice on 429 and 5xx with backoff, and keep
  failed cells visible in the report instead of dropping them.
- Detect brand and competitor mentions case-insensitively using the alias list, and
  record the first-mention character offset as a crude prominence proxy.
- Normalize citations to hostname plus canonical path, strip tracking parameters, then
  compute owned-domain citation share and a top 25 cited-sources table.
- `track serve` renders visibility per provider over time, share of voice against each
  competitor, the sources table, and the prompts where competitors are cited and I am
  not (the gap list is the point).
- `track export` writes runs, mentions, and citations to CSV.
- Fixture tests for mention detection and URL normalization.
- Out of scope, and be honest in the README that these are exactly what a paid product
  like this sells: the real consumer surfaces (this uses model APIs, which do NOT match
  what the ChatGPT app, AI Overviews, AI Mode, Copilot, or Grok actually serve users),
  country-specific results via a proxied real-browser fleet, running that fleet at
  scale, and any human AEO consulting. Do not try to automate the consumer web UIs.
- README: setup, a per-run cost estimate, a cron line for daily runs, and a plain note
  that API answers only approximate what users actually see.

What you lose

• the faithful signal: API answers only approximate what the ChatGPT app, AI Overviews, AI Mode, Copilot, and Grok actually serve real users, which is what AmICited measures with real browsers
• country-level results: what users see varies by geography, which needs a proxy fleet a solo build will not stand up
• scale and reliability: running and retrying thousands of real browser sessions in parallel is the hard engineering, not the scoring
• months of stored answers and competitor baselines, without which a single week's visibility number is noise, and which you cannot backfill once you start late
• human AEO consultations on higher plans, advice from real experience acting on your data, which no self-hosted script reproduces

Why people still pay

Because the scoring is the cheap half and everything real is the expensive half. AmICited does not call the model APIs, it drives real browsers through country-level proxies to capture what users genuinely see, which is faithful and hard to run at scale and keep working as the surfaces change. It stores every full answer so the value compounds into a history you cannot recreate once you start late, exposes an MCP server so your AI agents can act on the gaps, and on higher plans adds human AEO consulting that acts on your data from real experience. A personal API script gives you a rough proxy; it does not give you any of that.

moat: Proprietary data Infrastructure scale Integrations what a moat is

a geo-proxied real-browser fleet plus the compounding archive of full answers, with an MCP server and human AEO consulting on top

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.

Who has already built it

Starting from here is still vibecoding: the prompt is for when you want it exactly your way.

• Elmo (opens in a new tab) — MIT-licensed self-hosted AEO/GEO tracker: runs your prompts across the major answer engines and records mentions, competitors, and cited sources
• llm-brand-tracker (opens in a new tab) — Small research-grade toolkit for monitoring brand visibility in LLM search; a reasonable starting point

Do you agree?

Related apps

Profound 99 $ KIND OF 100 Questions 9 $ KIND OF Semrush 140 $ NOT REALLY