Everything you configure and monitor lives under HomeRunner -> AI Concierge in your WordPress dashboard. This guide walks through each tab.
Tab map #
The admin panel is organized into tabs. It opens on the Overview tab by default: a card for each settings area with jump links into it. If something needs attention, like your license nearing expiry or your OpenRouter credits running low, a colored badge appears on the relevant card and links straight to the tab where you fix it. This guide walks through the rest of the tabs in the order you’re likely to use them.
| Tab | What you do here |
|---|---|
| Overview | Landing screen: a card per settings area, with jump links and status badges for anything that needs attention |
| General | Master enable/disable, debug mode, voice-input language |
| Performance | Cost dashboard, booking attribution, response times |
| Health | Diagnostic counters for the chat pipeline, mainly useful for support troubleshooting |
| License | License activation, deactivation, trial status |
| API | OpenRouter API key, default model, response temperature, daily spend cap |
| Search Prompt | Tune which property attributes the AI prioritizes |
| Concierge | Setup checklist, brand voice, recovery messaging, lessons |
| Chatbot | On-page chat drawer, greeting, search recovery, and the Search Ask Tab |
| Live Concierge | Live human takeover: availability, Slack operator chat, session mirror |
| Integrations | Push high-value Concierge events to Slack |
| Property KB | Property page experience toggle and bulk per-property knowledge editor |
| Self-Assessment | Quality loop where the AI grades its own responses |
| Photo Analysis | One-time vision pass over property photos |
| Test Search | Operator sandbox for dry-running queries |
| Chat Sessions | Review every chat conversation |
| Search History | Analytics over guest search queries |
General #
- Enable Enhancer: the single switch that turns the Concierge on or off site-wide, including the chat drawer, voice input, and AI-powered search.
- Debug Mode: adds verbose logging to your PHP error log. Leave off for production.
- Voice Input Language: language preference for the voice-input feature on the chat drawer. Default is “auto” (let the browser decide).
Save settings before leaving the tab.
License #
Activate, deactivate, and monitor your subscription:
- Activate / Deactivate: paste your license key (format
HRAI-XXXX-XXXX-XXXX) from your welcome email and click Activate. Deactivating frees up the activation slot for use on another site. - Trial status: shows whether you’re in an active trial, with the trial end date, or on a paid subscription.
- Last checked: the timestamp of the most recent license validation.
The license controls your subscription eligibility only; it does not power AI replies by itself. You still need a working OpenRouter API key on the API tab (see below) for the Concierge to actually respond to guests.
API #
Where the Concierge gets its AI horsepower:
- OpenRouter API Key: your key from openrouter.ai. Required for any AI feature to work; without a valid key the Concierge cannot answer guests even with an active license.
- Model: which model OpenRouter routes requests to. Defaults to a fast, cost-efficient model suited to high call volume.
- Temperature: how much variation the model allows itself in its wording. Defaults low, favoring consistent, predictable replies over creative ones.
- Daily Spend Cap (USD): a hard ceiling on estimated OpenRouter spend across every AI feature (chat, concierge, photo analysis, self-assessment) for the day. Once the cap is hit, further AI calls are refused until the next day. Default is $10. Set to 0 to disable the cap.
Search Prompt #
Controls which property attributes the AI sees when reasoning about a guest’s search. Each field is its own on/off toggle, off by default, with a description of its approximate token cost per property so you can weigh richer context against cost:
| Field | What it adds |
|---|---|
| Intro | Short marketing intro. Low token cost, good context for the AI. |
| The Home | Full property description with features and rooms. Highest token impact of the group. |
| Neighbourhood | Neighborhood description for location context. |
| Content | Main property description (post content or summary). |
| Notes | Host notes: check-in details, house rules, special instructions. |
| Space | Description of the physical space, layout, and rooms. |
| Base Daily Rate | Enables price-related filtering. Minimal token cost. |
| Locations | Sub-location taxonomy for area matching. |
| Property Tags (custom) | Per-property tags. On most sites this taxonomy holds internal or back-office tags, so it defaults off; turn it on only if you use it as a guest-facing curated layer. |
| Coordinates | Enables proximity-based search, like “near downtown” or “within 5 minutes of the beach.” |
More fields on gives the AI richer context to work with, at the cost of more tokens (and a little more cost) per search.
Concierge #
This tab is where you shape how the assistant talks and recovers.
- Concierge setup checklist: at the top of the tab, a green/red checklist shows whether four core pieces are configured: your OpenRouter API key, brand voice, site-wide local knowledge, and a PMS custom-field mapping for per-property knowledge. Use it to confirm you’re fully set up.
- Brand Voice: a short description of how your team talks, applied to every reply. Give it examples and guidance. Specific input produces specific output. “Warm but professional, drop coffee-shop references” beats “friendly tone” every time.
- Concierge Lessons Panel: the Self-Assessment loop periodically reviews Concierge replies, flags patterns where it’s off-target, and writes lessons back into the prompt automatically. This panel shows the active lessons; you can delete an individual lesson or clear all of them if one turns out to be wrong.
Chatbot #
Configure the on-page chat drawer guests interact with.
Drawer settings #
- Position: left or right side of the screen
- Greeting: the opening message guests see when they open the drawer
- Tooltip: optional small nudge that appears next to the chat tab after N seconds on the page
Search Ask Tab #
A separate, optional entry point: an “Ask our concierge” bar you place on any page with the [hr_hero_ask] shortcode, so guests can describe what they want in plain language instead of using search filters. Off by default. Settings here include the open mode (starts collapsed until clicked, or expanded), header label, sub-line, submit button label, rotating example questions, suggestion chips, brand accent color, and a fallback target URL used only if the page doesn’t have the chat drawer loaded. See Ask Bar for the full walkthrough.
Recovery & Outreach #
When a search returns zero results or too many results, the Concierge offers proactive recovery instead of a dead-end:
- Progressive filter relaxation: for a thin search, the Concierge tries relaxing bedroom/bathroom minimums, guest count, geographic area (city, then state, then anywhere), and specific amenities one at a time, checks how many properties each relaxation would actually surface, and offers whichever one gets the guest the most options, not a fixed drop order.
- Recovery chips: tappable suggestions the guest can act on in one click, such as relaxing a size or guest-count constraint.
- Alternative-date chips: “Your dates aren’t available, but the same property is open the week before.”
- Lead-capture prompt: for queries that genuinely exceed the catalog (“we couldn’t find that, want to tell us more so a human can follow up?”).
Live Concierge #
Live Concierge is where you set up handing a guest conversation to a real person. You choose the hours your team is available, connect the Slack app your operators chat from, and decide whether to mirror conversations into Slack and let an operator take over a chat the guest did not request. The “talk to a live person” option only appears to guests when live takeover is on, the current time is within your hours, and an operator has marked the team available. See Live Concierge Takeover for the full setup.
Integrations #
Push high-value Concierge events to the tools your team already uses. Slack notifications are available now: one-way alerts for moments worth a human’s attention, such as a captured lead. See Slack Notifications for what gets sent and how to connect it.
Property KB #
Property KB is where you turn the property-aware chat on and feed it per-listing knowledge. The Property Page Experience settings sit at the top of the tab, and a bulk knowledge browser sits below.
Property Page Experience #
A site-wide toggle for the property-aware chat behavior:
- Enable Property Page Chat: when ON, the chat drawer opens on individual listings with a property-specific greeting, three contextual chips, and the property’s knowledge base injected into the prompt. This master switch is off by default.
- PMS Knowledge Base custom field: a picker of the custom fields found across your published properties. The Concierge reads this field per property and includes it in the prompt. Default:
homerunner_concierge_kb. If your PMS doesn’t sync a knowledge field, leave it and author content manually below. - Property Page Tooltip: optional custom text shown next to the chat tab on property pages, in place of the standard tooltip. Supports a
{property}placeholder to insert the listing name. Blank by default.
A short pulse animation draws guest attention to the chat tab on property pages without being intrusive.
Local knowledge browser #
A single table lists every published property, drawing on the PMS-synced custom field and a per-property local field you can edit by hand. Review or edit local knowledge across the whole catalog in one place: a few sentences on your top properties (house rules, local tips, owner notes) noticeably sharpens answers. See Property Chat.
Self-Assessment #
A quality loop where the AI grades its own responses over a rolling window of conversations and surfaces patterns where it’s off-target. Lessons flow back into the Concierge prompt automatically (see the Concierge Lessons Panel above). This is the foundation of how AI Concierge gets better at your specific catalog over time. Worth checking every 1 to 2 weeks once you’re settled in.
Health #
A diagnostics view of the chat pipeline’s behind-the-scenes reliability, kept over a rolling two-week window. On a healthy site everything on this tab reads zero: the counters here track fallbacks, retries, and expired requests, not normal guest traffic. There is nothing to configure here. If you ever contact support about a chat issue, this tab is what they will ask about first, since it shows exactly what degraded and when.
Photo Analysis #
A vision pass over your property photos that extracts both an overall summary and per-room observations the chatbot can cite when a guest asks about a specific space. Six canonical room types are captured for each property: living, kitchen/dining, bedrooms, bathrooms, outdoor, amenities. That room data feeds directly into the Concierge’s answers.
Click Edit on any property row to expand its analysis. You’ll see three sections:
- Summary: a 2 to 3 sentence whole-property description the Concierge uses for top-of-conversation context.
- Rooms (read-only): a table showing each room type the model observed, with visible features as pill chips and a qualitative note. This is exactly what the Concierge can cite in chat. A room with no visible feature pills won’t appear in the table.
- Details (JSON): per-photo descriptions and tags. Operator-editable if you want to tweak captions.
The Rooms table only shows rooms the model actually saw in your gallery. A missing room means the gallery lacked a clear photo of it, not that the property lacks the space. The Concierge treats photo data as supportive observation, never as a complete inventory, and will never tell a guest a feature is absent based on photo absence. See Photo Analysis for the full detail, including regenerating a single property’s analysis.
Test Search #
An operator sandbox for dry-running queries the way a guest would, so you can sanity-check brand voice, recovery behavior, and matching before going live.
Chat Sessions #
Review every chat conversation guests have had with the Concierge. Useful for spotting where guests get stuck and where the assistant is performing well.
Search History #
Analytics over guest search queries: what people are asking for, where searches dead-end, and which recovery chips get clicked. Pairs with the Performance dashboard.
Related #
- Setting up for the first time? See Getting Started
- Data handling and cost controls: Privacy, Data, and Cost Controls
- Stuck on something? See FAQ & Troubleshooting