> ## Documentation Index
> Fetch the complete documentation index at: https://docs.revcenter.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> What Revcenter does and who it's for

Revcenter turns a plain-language description of a role into a validated candidate search:
a recruiter or deal-team member describes who they're looking for, the system extracts
structured search criteria, and (as the orchestration layer comes online) sources and
scores candidates against those criteria.

The product is built around three ideas:

<CardGroup cols={3}>
  <Card title="Calibrate first" icon="sliders">
    Before any paid API call runs, the system extracts structured criteria from your
    description and shows you exactly what it understood — location, job title, years of
    experience, industry, skills — so you can correct it before spending anything.
  </Card>

  <Card title="Numbers come from SQL, not the model" icon="calculator">
    The LLM never produces a score. It extracts data and writes short rationale prose.
    Every ranking, every difficulty score, every dollar figure is computed in Postgres,
    versioned, and auditable.
  </Card>

  <Card title="Keys live in the database" icon="key">
    API keys for Harvest, Serper, Anthropic, and Prospeo can be rotated from the
    Credentials page and take effect immediately — no redeploy, no Vercel environment
    variable to update.
  </Card>
</CardGroup>

## Where things stand

Revcenter is being built in phases. Today, the following are real and working:

* **Sign up, log in, organizations** — email/password auth with verification, password
  reset, and multi-user organizations with invitations.
* **Calibrate screen** (`/intake`) — describe a role in your own words or paste a job
  description; the system extracts structured criteria and shows you which parts it's
  confident about.
* **Credentials** (`/admin/credentials`) — add, rotate, and deactivate API keys for the
  providers the system depends on, encrypted at rest.

Scans, firm profiles, and outreach sequencing are still landing — see
[Using the App](/guides/using-the-app) for what's live today versus what's still marked
"coming soon" in the product itself.

## Where to go next

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get the app running locally against a real Postgres database.
  </Card>

  <Card title="Using the App" icon="compass" href="/guides/using-the-app">
    Walk through the calibrate flow, admin pages, and what each does.
  </Card>

  <Card title="Authentication" icon="lock" href="/guides/authentication">
    How sign-up, verification, organizations, and invitations work.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    The actual HTTP endpoints the app exposes.
  </Card>
</CardGroup>