Harvey and Baseten Discuss Technical Challenges of Long-Running Agents

Harvey and Baseten executives held an in-depth discussion on the technical bottlenecks of building reliable, long-running agents. They noted that current agents struggle primarily with weak search capabilities and long context windows, leading to poor reliability.

2026-07-23 ~ 2026-07-23 · 3 related posts

• A deep dive on building agents that can work for days, not minutes — baseten · 2026-07-23
• Harvey and Baseten Deep Dive: Building Reliable Long-Horizon Agents with 100M-Token Context and KV Cache Compaction — baseten · 2026-07-23
• Baseten discussion explores how to make agents reliable over hours and days — baseten · 2026-07-23