Set up meeting types, agenda sections, and CSAT
Settings > Clients holds Meetings & Agendas, where the AI agenda generator's meeting types and reusable prompt sections live, and CSAT, where the post-ticket rating email is configured.
What you will have
- Find Meeting Types and know what a meeting type is and how its prompt gets used.
- Know what the Custom Prompt toggle changes about how a meeting type's prompt is written.
- Find Agenda Sections and know how a section's prompt becomes part of a generated agenda, and assign sections to a meeting type.
- Know what makes a good section prompt.
- Find CSAT Scale and CSAT Labels and know how they relate to each other.
- Know what happens after a customer submits a CSAT rating.
- Know who gets emailed when a CSAT rating comes in low.
Why it works this way
A meeting type's single prompt field changes what it does depending on the Custom Prompt toggle: off, it is an AI Prompt Note appended to the standard system prompt so section-by-section generation still runs; on, it is a Default Custom Prompt that replaces the standard prompt outright, so the AI runs on that one instruction over the whole client record instead of composing it from sections.
CSAT Labels always shows one input per rating value, so changing CSAT Scale first changes how many label boxes appear before you fill them in.
Steps
Open Settings > Clients > Meetings & Agendas and look at the Meeting Types table.
Each row is a meeting type the AI agenda generator can build from: a Name, a Slug, a Default Title Format (built from placeholders like {MONTH}, {YEAR}, {Q}), and a Prompt. Monthly Review, Quarterly Business Review, Annual Review, Security Review, and Onboarding / New Client ship with the product and carry a padlock icon, meaning they cannot be deleted, though their prompt notes and title formats can still be edited freely. Custom is a special type whose prompt is written fresh each time an agenda is generated from it, shown here as "Custom (user-provided)" rather than a fixed prompt.
Open Settings > Clients > Meetings & Agendas and look at the Meeting Types table. Click a meeting type's pencil to open it, then look at Show custom prompt field at generate time and the prompt field below it.
This walkthrough opened Quarterly Business Review. Show custom prompt field at generate time is off here, so the field underneath reads AI Prompt Note, described as appended to the default AI prompt to shift emphasis - the standard section-by-section agenda still runs, and this note just steers its tone (this type's note asks for strategic value, ROI, budget impact, and quarterly trends). Turning the toggle on renames the same field to Default Custom Prompt, shown as a placeholder at generate time, and switches the type to writing the whole agenda from that one prompt instead of composing it from sections.
Click a meeting type's pencil to open it, then look at Show custom prompt field at generate time and the prompt field below it. In the same open meeting type, scroll to Sections and look at the assigned list.
Sections lists the agenda sections this meeting type runs, in the order they generate - Ticket Summary, Device Health, Security Posture, License & Renewals, Key Talking Points, and Recommendations for Quarterly Business Review. Drag a row by its handle to reorder, or click its X to remove it from this type without deleting the section itself. Select a section to add and Add, below the list, assign another section from the shared library.
In the same open meeting type, scroll to Sections and look at the assigned list. Close the meeting type and look at the Agenda Sections table further down the page.
This is the shared library every meeting type's Sections list draws from. Each row is one section: its Title, a Slug, a Description (a short hint shown when assigning it), and the start of its AI Prompt. Ticket Summary, Device Health, Security Posture, License & Renewals, User Changes, Known Issues, Key Talking Points, and Recommendations ship with the product and carry a padlock icon, so they can be edited but not deleted. When a meeting type runs, the AI generates each of its assigned sections from this library in turn and stitches the results together.
Close the meeting type and look at the Agenda Sections table further down the page. Click a section's title or pencil to open it, then look at Title, Description, and AI Prompt.
This walkthrough opened Security Posture. Title and the optional Description are what a person sees when assigning or browsing sections; AI Prompt is the actual instruction sent to the AI when this section generates, and it always runs with the client's full profile already available - the prompt only needs to say what to focus on, not restate what data exists. Security Posture's own prompt asks for MFA adoption, admin account counts, and recent alerts, framed as business risk rather than technical detail, closing with "Lead with the most important finding." A good prompt for a new section follows the same shape: name the specific data to surface (open tickets, overdue patches, expiring licenses) rather than leaving it open-ended.
Click a section's title or pencil to open it, then look at Title, Description, and AI Prompt. Open Settings > Clients > CSAT and look at CSAT Scale and CSAT Labels.
CSAT Scale picks how many rating buttons the ticket-closed email shows: 1-3 (emoji), 1-5 (standard, the default), or 1-10 (NPS-style). CSAT Labels holds the text shown under each button, one input per rating value - the number of inputs always follows whichever scale is picked above, so changing the scale first adds or removes label rows before they can be edited. This tenant's labels read Terrible, Poor, OK, Good, and Excellent for its 1-5 scale.
Open Settings > Clients > CSAT and look at CSAT Scale and CSAT Labels. Look at Google Review URL and Google Review Threshold (% of scale).
A CSAT email is queued the moment a ticket closes, and the customer clicks one rating button with no login required, landing on a confirmation page. If that rating is at or above Google Review Threshold - a percentage of the CSAT scale, 80% by default, meaning a rating of 4 or higher on a 1-5 scale - the confirmation page redirects to Google Review URL so a happy customer can post a public review in one more click. A rating below the threshold just stays on the confirmation page. The redirect needs a Google Review URL filled in here; this tenant has not set one yet.
Look at Google Review URL and Google Review Threshold (% of scale). Check a group under Low-Score Alert Groups and save.
Every permission group checked here - pulled from Team > Staff Roles - gets emailed the moment a CSAT rating comes in at 50% or lower of the scale, so an unhappy customer reaches dispatch or management without anyone having to watch the inbox for it. This walkthrough checked Service Manager and saved, then unchecked it and saved again to leave the tenant as it found it - no group is on by default.
Note: Checking a group here does not send anything by itself - it only takes effect the next time a real CSAT rating comes in at or below 50% of the scale.Check a group under Low-Score Alert Groups and save.
If it did not work
- If a generated agenda reads generically instead of following a section's own instructions, open that section on Agenda Sections and check its AI Prompt is specific about what data to surface, not just "discuss the client's situation."
- If a meeting type's agenda ignores a section entirely, confirm that section is still in the type's own Sections list on the Edit Meeting Type panel - removing it from one type's list does not delete it from the shared Agenda Sections library.
- If a happy customer's rating never redirects to Google, confirm Google Review URL is actually filled in on CSAT - the threshold alone does nothing without a URL to redirect to.
- If nobody gets notified about a bad rating, check that at least one group is actually checked under Low-Score Alert Groups - none are checked by default.
Questions this page answers
What is a meeting type?
A reusable template the AI agenda generator runs against to build a meeting agenda (QBR, Security Review, Onboarding, etc.). Each type composes one or more Agenda Sections (the prompts that tell the AI what to write). Use Capabilities to scope what data the AI sees (open tickets, RMM signals, etc.) instead of dumping the full client record.
What is "Custom Prompt" mode?
Two AI generation modes: section-composed (default - runs each Agenda Section's prompt in turn, then stitches) and custom-prompt (monolithic - runs your single Prompt Note over the whole client record). Section mode gives finer control; custom mode is faster to author when you have one consistent style. The Custom Prompt toggle picks which mode this type uses.
How do agenda sections work?
Each section is a named prompt block (e.g. "Open Issues", "Hardware Health"). When a meeting type uses sections, the AI runs each section's prompt in order and concatenates the output. System sections can be edited but not deleted (they're what the seeded meeting types depend on, so the lock marks them non-removable); custom sections you write are fully editable and deletable.
How do I write a good section prompt?
Be specific about format: "List up to 5 open Critical tickets older than 7 days, bullet-pointed, with a one-line summary each." Avoid open-ended asks ("discuss…") - the AI is generating prep notes, not having a conversation. Reference the client data fields the agenda generator collects (clientData.tickets, clientData.devices, etc.) when you want it to be specific.
Scale vs. Labels - what controls what?
Scale picks how many rating buttons render in the email (3 = simple, 5 = standard, 10 = NPS-style). Labels lets you customize the text under each button. The Labels field auto-resizes to match the Scale (5 inputs when Scale=5, 10 when Scale=10).
What happens after a customer rates a ticket?
They land on a confirmation page. If their rating is at or above the Google Review Threshold (default 80% of scale - e.g. ≥4 on a 5-scale), the page redirects to your Google Review URL so happy customers post a public review. Lower ratings stay internal.
Who gets emailed when CSAT is low?
Every member of the Low-Score Alert Groups (Permission Groups picked from Team → Staff Roles) gets an email when a CSAT rating comes in at 50% or lower of the scale. Use it to surface unhappy customers to dispatch or management without watching the inbox.
Was this helpful?