AI news
Asana reports lower browser-agent costs after changing cache and history handling
Asana says it shipped changes to StackAI browser navigation after a 144-run internal study of one book-catalog task. Keeping more browsing history intact and pruning screenshots in batches made the optimized workflow using GPT-6.1 Sol average $0.47 in estimated model cost and about four minutes per run, versus at least $36.21 and 22.5 minutes for its earlier production setup on another model. The 76x cost and 5x speed figures combine workflow and model changes in that test; they are not guaranteed savings for other tasks or customers. Asana says people set the goals and reviewed the agent-led experiments.
Primary source · Asana · October 8, 2026
Opens Asana in a new tab. Read it there before you rely on the summary above.
Read the original
Free, email only
Unlock the full brief free.
- What to check before you trust this story, written down
- Each verified source, with why it matters and who published it
- A note whenever a source has been withdrawn
- Thirty days of stories to browse, not seven