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

# How to build an AI receptionist and intake system

> A complete guide to building an AI receptionist for a law firm — what she answers, the intake she runs, what happens to the caller afterward, and how to test her before real clients call.

An AI receptionist is four decisions, not one product: **how she answers**, **what she
finds out**, **what happens to the caller next**, and **who she hands off to**. Get
those right and the build takes about ten minutes. Get them wrong and you have an
expensive voicemail.

This page is the whole picture. Follow it top to bottom and you'll have a receptionist
answering your firm's calls today.

<CardGroup cols={2}>
  <Card title="Build it yourself, no code" icon="wand-magic-sparkles" href="/studio/create-your-receptionist">
    Lawtte Studio walks you through all four decisions in a browser.
  </Card>

  <Card title="Build it on the API" icon="code" href="/api-reference/introduction">
    Wire the same pieces into your own product or intake stack.
  </Card>
</CardGroup>

## What you're actually building

Every call runs the same four stages. An AI receptionist worth having does all four —
most "AI answering services" only do the first.

<Steps>
  <Step title="Answer">
    She picks up in your firm's name, 24/7, and identifies herself as an automated
    assistant. No hold music, no "press 1."
  </Step>

  <Step title="Intake">
    She learns what happened, in the caller's own words, then fills in the specific
    facts your practice area needs — the date of the accident, whether they've been
    served, whether an insurer already called.
  </Step>

  <Step title="Outcome">
    One thing happens at the end of every call: the intake is emailed to your team, a
    consultation is booked on a real calendar, or the caller is transferred to a
    person.
  </Step>

  <Step title="Handoff">
    Everything she learned reaches a human in a form they can act on — a summary in an
    inbox, a calendar invite with the case on it, or a warm transfer with an
    introduction.
  </Step>
</Steps>

## Decision 1 — How she answers

Three things a caller hears in the first five seconds: your firm's name, her name, and
whether she sounds like your firm.

* **Firm name as spoken, not as registered.** "Reyes and Cole" beats "Reyes & Cole,
  LLP, A Professional Corporation."
* **Her name** is the one your clients will repeat back. Keep it easy to say.
* **Voice and languages.** Pick the voice, then add every language your callers
  actually use — she opens in your first language and switches when the caller does.

<Tip>
  Say your greeting out loud before you commit to it. Anything that's awkward to say is
  awkward to hear forty times a day.
</Tip>

## Decision 2 — What she finds out

This is where most intake systems fail, and it's not for lack of questions. It's the
opposite: a list so long the caller feels processed.

**A good intake has six or seven things she must learn and a dozen she'll ask only if
the conversation goes there.** The difference between "always" and "when it comes up"
is what makes a call feel like a conversation rather than a form.

Four behaviors that matter more than the list itself:

<AccordionGroup>
  <Accordion title="The caller talks first" icon="comments">
    She asks what's going on, listens, and pulls the facts out of what they already
    said. Re-asking something a caller just told you is the fastest way to sound like
    a robot.
  </Accordion>

  <Accordion title="Urgency interrupts everything" icon="triangle-exclamation">
    Someone detained, a hearing tomorrow, a protective order, a safety concern — she
    gets just enough to route the call and acts. She does not finish the questionnaire
    first.
  </Accordion>

  <Accordion title="The callback number comes second" icon="phone">
    Right after the name, with the reason said out loud: "in case we get cut off." A
    dropped call after a five-minute intake with no number is a lost client.
  </Accordion>

  <Accordion title="She reads contact details back" icon="check">
    Numbers and emails get confirmed out loud. Transcription is good; it isn't perfect.
  </Accordion>
</AccordionGroup>

In Lawtte you don't write this from scratch — each practice area comes with a real
intake list you edit. See [her intake questions](/studio/intake-questions).

## Decision 3 — What happens to the caller next

Pick one. Firms that try to do all three end up with calls that go nowhere.

| Outcome                           | Choose it when                             | What you set up                                                       |
| --------------------------------- | ------------------------------------------ | --------------------------------------------------------------------- |
| **Email the intake to your team** | Your team calls leads back themselves      | One inbox a human actually reads                                      |
| **Book the consultation**         | The consult is your conversion step        | A connected [calendar](/studio/calendar) and her booking rules        |
| **Transfer to a person**          | You want to talk to good leads immediately | A daytime number, and a choice for [after hours](/studio/after-hours) |

<Warning>
  If you pick email, point it at a monitored inbox. The most common failure in a new
  AI intake setup isn't the AI — it's perfect summaries landing in a shared mailbox
  nobody opens until Monday.
</Warning>

## Decision 4 — Who she hands off to, and when

Two separate things people conflate:

* **Office hours** tell her when a human is available to take a transfer. They do
  **not** control when she answers — she answers every call, always.
* **Urgent routing** overrides your hours. A caller in custody at 11pm either reaches
  your on-call number or generates an urgent-flagged message, depending on what you
  chose.

Decide what you want to happen at 2am *before* you go live, not after the first 2am
call. See [after-hours coverage](/studio/after-hours).

## The hard calls

Three calls every receptionist gets, and every one of them is a way to lose a client or
embarrass the firm:

1. **"What do you charge?"** — the safe default is that she doesn't discuss fees. If
   your firm quotes a consultation price or works on contingency, tell her once and
   she'll say it once.
2. **"I have a hearing tomorrow."** — flag it urgent, or transfer it. Your call.
3. **A salesperson pretending to be a client.** — she screens and ends the call, or
   points them at an email address.

Whatever else she does, she won't give legal advice, predict an outcome, quote a fee
you didn't give her, discuss an existing client's case, or say anything implying an
attorney–client relationship. Those guardrails aren't configurable, and that's what
makes it safe to let her answer every call.

## Build it in Studio

<Steps>
  <Step title="Open the builder">
    [lawtte.ai/studio](https://www.lawtte.ai/studio) — pick your practice areas, name
    your firm, name her.
  </Step>

  <Step title="Call her before you sign up">
    Once she has a name, a Call button appears. Role-play a real client. Free, no
    account.
  </Step>

  <Step title="Answer the four decisions">
    Intake list, voice and hours, the outcome, and the hard calls — each one is a
    screen. Full walkthrough: [create your AI receptionist](/studio/create-your-receptionist).
  </Step>

  <Step title="Give her a phone line">
    Claim a local number, then forward your office line to it or publish it directly.
    See [her phone number](/studio/phone-number).
  </Step>

  <Step title="Test, then go live">
    Three calls — a good new client, a current client, a salesperson. See
    [test her, then go live](/studio/test-and-go-live).
  </Step>
</Steps>

## Build it on the API instead

If you're wiring intake into your own product, the same four stages map onto endpoints:

| Stage                    | Endpoint                                                              |
| ------------------------ | --------------------------------------------------------------------- |
| Configure her            | `POST /api/v2/update-agent-prompt`, `POST /api/v2/update-agent-voice` |
| Answer (web)             | `POST /api/v2/create-web-call`                                        |
| Answer (phone, outbound) | `POST /api/v2/create-outbound-call`                                   |
| Capture the intake       | Your `call_analyzed` [webhook](/guides/call-webhooks)                 |
| Persist the lead         | `POST /api/leads`                                                     |
| Book the consult         | `POST /api/v2/{firm}/check-availability`, then `book-appointment`     |

Start at the [API overview](/api-reference/introduction) and
[authentication](/authentication).

## Then keep improving her

The build is the easy part. The firms that get the most out of an AI receptionist all
do the same unglamorous thing: **they read the transcripts.**

<CardGroup cols={2}>
  <Card title="Read every call for the first week" icon="file-lines" href="/studio/dashboard">
    You'll find the missing question faster than any amount of planning would.
  </Card>

  <Card title="Change one thing at a time" icon="sliders" href="/studio/intake-questions">
    Adjust a question, then call her about that question.
  </Card>
</CardGroup>

<Check>
  A receptionist that's been tuned for two weeks against real transcripts outperforms a
  perfectly planned one that nobody ever listened to.
</Check>


## Related topics

- [What is Lawtte Studio?](/studio/overview.md)
- [Studio FAQ](/studio/faq.md)
- [Lawtte documentation](/index.md)
- [Her intake questions](/studio/intake-questions.md)
- [Create your AI receptionist](/studio/create-your-receptionist.md)