System prompt and revisions
The system prompt is the standing instruction an agent reads before every conversation: what it does, how it should decide, what it must never do. Every version you save is kept, so changing it is reversible.
When to use it
Section titled “When to use it”Reach for the prompt when the agent’s behavior is wrong — it does the wrong thing, in the wrong format, or asks you things it should already know. Reach for a connector or a skill when it lacks a capability. Prompting cannot substitute for access.
Write one
Section titled “Write one”-
Open the prompt section in Agent Builder.
You see the current text and the history of previous revisions.
-
State the job in one paragraph.
Who the agent works for, what it is responsible for, and what falls outside that. An agent that knows its boundaries asks fewer pointless questions.
-
Say what a good result looks like.
This is the part most prompts skip, and the part that changes results most. The agent chooses its own steps; what it cannot guess is your standard for “done”.
“Summarize my unread email” leaves everything to chance. “Summarize my unread email, grouped by sender; for anything asking me a direct question, quote the question verbatim so I can answer without opening it” does not.
-
List the hard rules.
Things that must always or never happen — never email anyone outside the company, always cite the source document, never guess at a number.
-
Save it as a new revision.
The previous text is not overwritten; it becomes a revision you can return to.
Revisions and rollback
Section titled “Revisions and rollback”Every save creates a revision. The history shows what the prompt was at each point, and you can restore an earlier one.
This is what makes prompt iteration safe rather than a gamble. Change something, use the agent for a day, and if the change made it worse, go back to the revision that worked — you do not have to remember what the old text said.
What belongs where
Section titled “What belongs where”| Put it in | When |
|---|---|
| System prompt | It applies to every conversation — your role, standing rules, output format |
| A message | It applies to this task only |
| Character | It is about tone, not about the job |
| Memory | It is a fact the agent should learn once and reuse — a preference, a name, a habit |
| A skill | It is a repeatable procedure with steps, not a standing instruction |
A prompt that has grown to cover four unrelated jobs is a sign you need a second agent, not a longer prompt.
Limits
Section titled “Limits”- A prompt cannot grant access. If the agent needs your calendar, it needs a bound connection — writing “you have access to my calendar” changes nothing.
- Restoring a revision replaces the whole prompt. There is no merge between revisions.
- The prompt is per agent. Two agents that should share standing rules need the text in both.