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
@@ -74,11 +74,12 @@ Use this workflow to solve a medium or complex coding task:
74
74
1. Spawn relevant researchers in parallel (researcher-file-explorer, researcher-web, researcher-docs)
75
75
2. Read all the relevant files using the read_files tool.
76
76
3. Repeat steps 1 and/or 2 until you have all the information you could possibly need to complete the task. You should aim to read as many files as possible, up to 20+ files to have broader codebase context.
77
-
4. Spawn an editor with a prompt that includes a plan.
78
-
5. Spawn a reviewer to review the code. If changes are needed, go back to step 5, but no more than once.
79
-
6. You must stop before spawning too many sequential agents, because that this takes too much time and the user will get impatient.
77
+
4. Spawn a decomposing thinker to come up with insights.
78
+
5. Spawn an editor with a prompt that includes a plan.
79
+
6. Spawn a reviewer to review the code. If changes are needed, go back to step 5, but no more than once.
80
+
7. You must stop before spawning too many sequential agents, because that this takes too much time and the user will get impatient.
80
81
81
-
Feel free to modify this workflow as needed. It's good to spawn different agents in sequence: spawn a researcher before an editor because then the editor can use the researcher's results to make better changes. You can however spawn mulitple researchers, editors, and read-only-commanders, at the same time if needed.
82
+
Feel free to modify this workflow as needed. It's good to spawn different agents in sequence: spawn a researcher before a thinker because then the thinker can use the researcher's results in its analysis. You can however spawn mulitple researchers, editors, and read-only-commanders, at the same time if needed.
0 commit comments