You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/source/en/tutorials/building_good_agents.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -177,7 +177,7 @@ The first step to debugging your agent is thus "Use a more powerful LLM". Altern
177
177
178
178
Then you can also use less powerful models but guide them better.
179
179
180
-
Put yourself in the shoes if your model: if you were the model solving the task, would you struggle with the information available to you (from the system prompt + task formulation + tool description) ?
180
+
Put yourself in the shoes of your model: if you were the model solving the task, would you struggle with the information available to you (from the system prompt + task formulation + tool description) ?
181
181
182
182
Would you need some added claritications ?
183
183
@@ -217,4 +217,4 @@ agent = CodeAgent(
217
217
result = agent.run(
218
218
"How long would a cheetah at full speed take to run the length of Pont Alexandre III?",
0 commit comments