# Build brief — a focused alternative to BrandGEO

> **Verdict:** Partly, if you narrow it · **Buildability:** 58/100 · **Category:** SEO Marketing
> **Source:** https://www.canitbevibecoded.com/brandgeo
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from BrandGEO. Verify current pricing and capabilities before acting.

## Context

**BrandGEO** — Audits how ChatGPT, Claude, Gemini, Grok, and DeepSeek describe your brand, with white-label reports for agencies. It currently costs $79/mo.

Running a fixed battery of brand questions through five model APIs and scoring the answers with a second LLM pass is a genuine focused build, and for one brand it answers the headline question: what does AI say about us. The gaps are the ones every tracker in this category shares. API answers approximate but do not equal the consumer apps, a score with no trend history behind it is a screenshot rather than a signal, and a rubric only becomes comparable after it has scored many brands.

This brief describes a focused, single-operator replacement for the part of BrandGEO 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

Send a fixed set of brand questions through the OpenAI, Anthropic, Gemini, xAI, and DeepSeek APIs, score each answer against a six-dimension rubric with a second LLM pass, store every run, render a Markdown or PDF report.

- Automate a bounded research or reporting workflow using permitted data sources.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- A written scoring rubric with per-dimension definitions.
- Durable per-run storage for trend history.
- A scheduler for recurring audits.

### Data and integrations

- API keys for OpenAI, Anthropic, Gemini, xAI (Grok), and DeepSeek.
- An API budget that scales with prompts x engines.

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 local AI brand visibility auditor for one brand. Requirements:

- Node 22, TypeScript, better-sqlite3, a CLI. Local only, no accounts, no telemetry.
- brand.json holds my brand name, aliases, domain, one competitor, and up to 25
  audit questions (who is X, best tools for Y, X vs competitor, is X legit).
- `audit run` sends every question through OpenAI, Anthropic, Gemini, xAI, and
  DeepSeek APIs. Keys from .env; skip engines whose key is missing and say so in
  the report instead of failing.
- Store one immutable row per run, question, and engine: raw answer, model id,
  latency, error text. Never overwrite a previous run.
- Cap concurrency at 2 per engine and retry twice on 429 and 5xx with backoff.
- A separate scoring pass grades each stored answer 0-10 on six dimensions:
  recognition, knowledge depth, competitive context, sentiment, contextual
  recall, discoverability. Rubric text lives in rubric.md, scores must cite the
  answer sentence that justifies them.
- `audit report` renders a Markdown report: overall score per engine, the
  six-dimension table, competitor mentions, and every flat-out wrong claim the
  models made about the brand, quoted.
- `audit history` prints score per engine across runs from SQLite, so week two
  starts meaning something.
- Out of scope: white-label PDFs, multi-brand management, scheduled monitoring,
  and scraping the consumer web UIs. One brand, run by hand.
- README: setup, per-run cost estimate by engine, and a plain note that API
  answers only approximate what the apps actually show users.

## 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:

- White-label PDF reports an agency can hand to a client.
- Weekly monitoring that keeps running when nobody is thinking about it.
- A rubric calibrated across many brands, so scores are comparable.
- Competitor benchmarks per brand.
- The consumer app surfaces, which no API exactly reproduces.

## 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 reviewed project implementation is linked yet.

## Existing alternatives

Before building, compare these checked options:

- [Elmo](https://www.elmohq.com/) — A self-hosted AI visibility dashboard that runs your prompts across the major engines and records mentions and citations; the white-label reporting is the part you keep paying for

## Prior art

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

- [Elmo](https://github.com/elmohq/elmo) — MIT-licensed self-hosted AEO/GEO tracker, a working reference for the prompt-battery loop
- [llm-brand-tracker](https://github.com/sarahkb125/llm-brand-tracker) — research-grade toolkit for monitoring brand visibility in LLM search, a small starting point

---

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