Back to full roadmap
topicadvanced★ Pro
Skeleton-of-Thought
First produce the skeleton (outline), then fill sections IN PARALLEL — 2-3× latency reduction.
2 hours1 resources1 prereqs
Classic CoT is sequential — long answers are slow. SoT is two-stage:
- Tell the model to "produce a 5-point skeleton"
- Make a parallel API call per point
Great for blog posts, reports, stories. Trade-off: cost 1.x → 5× per point, but wall-clock drops ~50%.