Curious to see what you do
Commit
4be36de
My biggest issue today is that after an agent cooks, the review agent gives feedback to tune it. I often end up with a huge, over-engineered mess. So have the cut out the fat.
commit 4be36de
Runar also asked this, but can you expand on your setup. I just usually use one model, and then review it myself.
Ponytail (specially /ponytail-review command) helped me about this. Specially we I use another agent to review