Spaces:
Running
Running
Update prompts.yaml
Browse files- prompts.yaml +18 -5
prompts.yaml
CHANGED
@@ -209,10 +209,23 @@
|
|
209 |
After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
|
210 |
|
211 |
Now write your new plan below.
|
212 |
-
"managed_agent":
|
213 |
-
|
214 |
-
|
215 |
-
|
216 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
217 |
"final_answer": |-
|
218 |
The final answer to the task is: {{answer}}
|
|
|
209 |
After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
|
210 |
|
211 |
Now write your new plan below.
|
212 |
+
"managed_agent":
|
213 |
+
"task": |-
|
214 |
+
You're a helpful agent named '{{name}}'.
|
215 |
+
You have been submitted this task by your manager.
|
216 |
+
---
|
217 |
+
Task:
|
218 |
+
{{task}}
|
219 |
+
---
|
220 |
+
You're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.
|
221 |
+
Your final_answer WILL HAVE to contain these parts:
|
222 |
+
### 1. Task outcome (short version):
|
223 |
+
### 2. Task outcome (extremely detailed version):
|
224 |
+
### 3. Additional context (if relevant):
|
225 |
+
Put all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.
|
226 |
+
And even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.
|
227 |
+
"report": |-
|
228 |
+
Here is the final answer from your managed agent '{{name}}':
|
229 |
+
{{final_answer}}
|
230 |
"final_answer": |-
|
231 |
The final answer to the task is: {{answer}}
|