Agents should estimate your time, not just theirs, before long tasks
gethackteam · x · 2026-10-24
A crisp product insight: before an agent starts a long task, it should estimate not just the task's duration but your time — "one hour" means something very different if you can walk away versus staying at the keyboard.
It exposes a blind spot in current agent UX: tools report task-side time but never the human cost of waiting and intervening.
More from coding & agent
- Flywheel ships local UI: your graphs on your own machine, no account needed — tensorqt · 2026-10-25
- When your skill becomes your brand: the Claude Code skills hall of fame — garrytan · 2026-10-25
- Five settings and four built-in commands to stop Hermes Agent from burning tokens — alexcovo_eth · 2026-10-25
- Flint ranked a top-3 daily coding driver, running Recursive_SI's local model with day-zero MLX support — altryne · 2026-10-25
- Agent-assisted self-hosting now takes days, not months, dev argues on X — kuza55 · 2026-10-24
- PyMemoryEditor MCP lets your agent read and write any process's memory — SupermarketTrue7507 · 2026-10-24