Using AI agents to book things still costs as much mental effort as doing it yourself
nabeelqu · x · 2026-09-23
nabeelqu shares his experience using AI agents for booking tasks: watching the agent's progress and helping it past approval and failure points consumes roughly as much mental bandwidth as doing the task yourself. He still finds text interfaces great — he hadn't realized how much he dislikes clicking through random UIs — and expects the experience to improve if the web becomes more agent-friendly.
Related event: AI Agent Booking Still Requires as Much Oversight as Doing It Yourself(2 posts)→
More from coding & agent
- Everyone builds AI agents, almost nobody builds the harness around them — alex_verem · 2026-09-23
- Claude generates a stunning Three.js Japanese boat scene, and people can't believe it — nateliason · 2026-09-23
- The Agentic AI Storage Shock: enterprise agents turn storage into the next bottleneck — BenBajarin · 2026-09-23
- Claude Opus 5.5 impresses at building animated maps in hands-on test — DavidmComfort · 2026-09-23
- Self-host Firecrawl and give agents a Firecrawl skill for cleaner, cheaper web reading — gregmushen · 2026-09-23
- Daytona and LlamaIndex Host SF AI Builders Demo Night With 378 RSVPs — llama_index · 2026-09-23