{% extends "admin/_layout.html" %} {% from "_macros.html" import icon %} {% set section = "prompts" %} {% block title %}Prompts - {{ brand.name }}{% endblock %} {% block heading %}Prompts{% endblock %} {% block admin_content %}
Everything {{ brand.name }} puts in front of a model on its own: what day it is, how to use each tool, what it has been asked to remember. These sit above whichever system prompt was authored for the instance, the model or the chat — that prompt still wins where the two disagree. Clear a box to leave that piece out altogether; press Use default to put the built-in wording back.
{% if saved %}
Write these in double braces. Anything in double braces that is not on this
list is left exactly as you typed it — variable names are lowercase letters,
digits and underscores, so {"total": 1} and ${PATH}
are never mistaken for one. A variable with nothing in it takes its whole
line with it, so a section never appears empty.
{{{{ variable.name }}}}
{{ variable.description }}
{% if variable.name not in resolved %}
only in the title request
{% elif resolved[variable.name] %}
{{ resolved[variable.name] | truncate(80) }}
{% else %}
empty
{% endif %}
The whole system message, assembled from what is in the boxes below — including changes you have not saved yet. Your own memories and skills are used, because a preview against invented ones cannot tell you whether it reads well against what is actually there.
Empty means a chat that can see everything.
Only reaches the prompt with agent ticked below. The
machine, directory and plan shown there are samples.
Defined in code — part of the schema sent to the endpoint alongside the prompt, not guidance layered on top of it. They are statements of fact about what each tool does, so they change when the tool does; editing them here would let the text quietly become a lie. A custom tool's description will be editable, because a custom tool is a row rather than a function.
{{ tool.name }}
{{ tool.description }}
{{ tool.family }}