How Templi learns your firm's way of working
Templi keeps two stores that outlive any one conversation: Knowledge, which is what is true about your firm, and Memory, which is what is true about one client. Templi reads both before it writes anything, and both grow as you work rather than through a setup project.
Why two stores
They answer different questions, and keeping them apart stops your house style leaking into one client's file, or one client's circumstances leaking into every report.
Knowledge | Memory | |
|---|---|---|
Scope | The whole firm | One client |
Holds | Your terminology, house standards, how you write | Decisions, objections, goals, changes in circumstances |
Where you find it | Customise > Knowledge, at | The client's Memory, at |
Changes when | You write a note, or tell Templi how the firm works | Templi learns something lasting about the client |
To write a note yourself, see Add a knowledge note. Client memory covers the client side.
Knowledge overrides Templi's own defaults
A note is not a hint. Where your knowledge disagrees with what Templi would otherwise write, your firm wins, and that includes wording it would normally consider standard.
A firm that writes its reports in Spanish, or calls the ongoing advice charge something specific, or orders its suitability sections a fixed way, gets that in every report once it is a note. You are not re-explaining it in each chat.
How knowledge grows
Knowledge changes only when someone writes or edits a note, or tells Templi in chat. When you say something that should hold for every future piece of work, Templi adds it to the note that covers it, or creates one, and tells you which. A one-off instruction for the task in hand is not stored.
Every change is kept. A note's Changes list shows each version, marked Edited by Templi when Templi made it, and you can restore any of them.
Not everything is loaded every time
Each note says when Templi should read it, because Templi carrying every note on every run has less room for your client's actual circumstances.
Always load puts the note in front of Templi in full, on every run. Suited to short, universal notes such as a charges glossary.
When relevant shows Templi the note's name and description, and it opens the note when the work calls for it. This is the default.
Manual only hides the note until someone names it, or a skill points to it.
An always-loaded note also names which parts of Templi read it under Used by, so report wording can reach Document generation without also reaching your Meetings write-ups. The other choices are Fact find and forms, Compliance and Assistant chat.
Keep always-loaded notes short and few. Templi reads up to 40,000 characters of them on each run. Long notes belong on When relevant, where Templi opens them only for the work that needs them.
Templi lists up to 60 of your other notes by name and description on each run, and can search for the rest, so a clear description matters more than the name.
Templi asks when a new fact contradicts an old one
When what Templi has just learned conflicts with a note, it stops and asks you rather than choosing. It quotes both the stored wording and the new wording and names the note, so you can see exactly what would change.
This matters most for firm knowledge, where a silent overwrite would change every future report. Your own standard is never replaced without you saying so.
What Templi will not record
Templi records what your firm has told it. It does not invent regulatory, tax or compliance guidance and store that as your firm's position.
Notes marked Templi baseline come from us and are read-only. To replace one, write your own note with the same name, and yours is used instead.
Ask Templi
Ask in any chat what your knowledge says, or tell Templi something new. For example:
What does our knowledge say about how we describe the ongoing advice charge?
Remember for the whole firm that we always recommend a protection review when a client's mortgage changes.