Tell it what each kind of meeting should capture.
A discovery call, a one to one and an incident review are not the same conversation and should not be read the same way. Twenty-five frameworks arrive with your workspace, from BANT to GROW to a 5 Whys postmortem. Pick one, edit it, and every meeting of that kind is read the same way from then on.
It writes down every turn, then reads the transcript back: talk share per person, questions asked against questions answered, and the commitments somebody made out loud.
The process
Five steps to set up a meeting type.
Five steps, once, in Operations. After that every meeting of that kind is read the same way, which is what makes one quarter comparable with the next.
Name it, file it under a department, and describe it in a sentence. The description is not decoration: it goes into the analysis, so "a first call to establish whether there is a real opportunity" reads differently from "sales call".
What you write here changes what the analysis looks for.Saved, the analysis instruction is composed behind the scenes from the framework, your list and the sentence you wrote. Every meeting of this kind is then read the same way, which is what makes one quarter comparable with the next.
Pick a framework instead of writing a prompt.
The catalogue
Twenty-five frameworks, seeded for every workspace.
Not a blank text box and not a suggestion to describe what you want. The frameworks your industry already uses, grouped by the department that uses them, with a Custom option when none of them fits.
Budget, Authority, Need, Timeline
A deeper checklist for complex deals
Situation, Problem, Implication, Need-Payoff
Pain, Budget, Decision
Start from a blank list and write your own.
You see your own department's frameworks plus the general ones, so nobody scrolls past twenty-five to find the four that apply to them.
Context
Choose what it already knows before the meeting starts.
Give it the deal, the contact and your last few meetings, and it can tell you this is the third time budget has come up while the deal has not moved. Without that it can only tell you budget was mentioned.
Its stage, its value, how long it has sat where it is.
Who they are and everything said to them before.
The account behind the person in the call.
What was promised the last three times you spoke.
What somebody already owes them.
What is outstanding, where that is the conversation.
What has gone wrong lately, which changes the tone.
7, 14, 30, 90 or 180 days.
More context is not automatically better. Pulling invoices and tickets into a first discovery call adds noise, because there are none. Pull what a good colleague would have read before walking in.
Five kinds of answer to choose from.
Pick the one that fits each question: a score, a yes or no, a set of choices, a rating with reasoning, or free text.
- Score it out of a scale you set, for things that come in degrees
- Ask yes or no where the answer really is one or the other
- Offer a set of choices, for severity, sentiment or outcome
- Use a rubric where the reasoning matters as much as the rating
- Fall back to free text for anything that resists a number
The meeting updates your records for you.
Each of these is a switch on the meeting type, so a first call and a renewal review can behave differently.
- Log the meeting to the deal or contact it was about
- Turn action items into tasks with owners
- Send an action item to an engineering board instead, where it belongs there
- Get a suggested pipeline stage move, which you accept or ignore
- Post the summary into team chat
What happens afterwards
Choose what happens after every meeting.
Four of them happen automatically. The fifth, moving a deal to the next pipeline stage, is only ever suggested, so nothing moves without you.
The meeting appears in the history of the deal or contact it was about.
Action items become real tasks with owners, in the same list as everything else.
Where the action item belongs on a board rather than in somebody day.
A recommendation you accept or ignore. Nothing moves on its own.
The team reads it where they already are.
Access
Who can do what.
It is a department-scoped library, set up in Operations. People see their own department's types; senior roles work across all of them. Creating a type sets the standard every meeting of that kind is judged against, so it sits with a smaller group.
The meeting types your department uses.
Pick a type when a meeting is booked.
Create and edit types for your department.
Work across every department, and seed your own frameworks.
Admin is the highest role and is not limited by these permissions, so keep it to the few people who genuinely need it.