Designing an AI Booking Agent for service businesses

Helping home service pros fix misconfigured online booking through a conversational agent that surfaces high-impact improvements they can accept or skip.

At Housecall Pro, a long tail of online booking users had enabled the feature but never configured it well. Incomplete services, wrong availability, vague copy. A bad configuration can quietly kill conversion, and plenty of pros were getting zero bookings without understanding why.

We set out to fix that: help more users reach a working setup, raise conversion across the board, and surface the configuration problems that were leaving money on the table.

The result is an interactive, agentic experience where pros review configuration improvements one at a time, accept or decline each suggestion, and move to the next highest-impact change. Simple and conversational, not another settings maze.

HCP AI booking agent showing a high-impact scheduling type recommendation with accept and decline actions

Interactive prototype

A dynamic prototype with multiple scenarios. See how the recommendation system responds to different booking configurations.

Open prototype

Grounding suggestions in real data

To help users fix their setup, we first had to define what good online booking actually looks like. We analyzed product data and studied top-performing HVAC pros: what they configured, how their services were structured, and what separated high-converting booking pages from ones that stalled.

That research became a set of guidelines covering services, availability, copy, and flow, which we fed into the AI so suggestions reflected patterns that were already working for the best performers in the category.

The prototype stress-tests that system across several scenarios: incomplete setups, misconfigured availability, weak service descriptions. Switch between them to see how the same logic surfaces different improvements depending on what the pro actually has live today.

The agentic flow

The experience moves through clear states, like working with someone who knows the product:

  1. Look through your settings: the agent reviews the pro’s current online booking configuration
  2. Analyze: identify what’s misconfigured, incomplete, or likely hurting conversion
  3. Suggest: surface specific improvements, categorized by business impact
  4. Decide: the pro accepts or declines each change before anything is applied
  5. Continue: move to the next recommendation and keep improving over time

Each step is one conversation, not a wall of options, aimed at steady progress toward a booking page that actually converts.

Setup diagnosis

The agent reads what’s already live: service lists left half-finished, availability that doesn’t match real working hours, descriptions too vague to convert. For many users, online booking itself wasn’t broken, their configuration was, and they had no way to see it. The diagnosis step made those gaps visible in plain language before proposing any change.

Recommendations ranked by impact

Suggestions aren’t a flat checklist. Each improvement is categorized by the impact it could have on the business, so pros can focus on what matters most first: rewrite a service description, tighten availability windows, fix a routing rule that sends customers nowhere. One meaningful change at a time, ordered by what matters most.

Human-in-the-loop by default

Nothing applies automatically. Every recommendation comes with a clear summary of what would change on the live booking page, and the pro decides whether to accept it. That keeps trust intact, especially for users who already felt unsure about their setup: the agent proposes, the pro decides.

A conversational UI

The interface stays lightweight: short messages, obvious next steps, no dense admin panels. States like analyzing settings or waiting for approval are always visible, so the pro knows where they are in the flow, and momentum carries naturally from one improvement to the next.

Connecting to Online Booking settings

The agent doesn’t replace existing settings, it sits on top of them, reading the same configuration pros would edit manually and applying only what’s approved. Accepted suggestions land in the familiar Online Booking surfaces pros already know. The agent guides; the product stays the source of truth.

Looking ahead, this booking agent is designed as one specialist in a broader Housecall Pro AI system. A single conversational interface could spin up focused agents like this one based on what the user needs: fix my booking setup, improve scheduling, adjust pricing. Each agent handles its own domain, but they can work together when a request spans multiple areas.