Agents
@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. …
@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate
@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate so far: https://x.com/hwchase17/status/2021261552222158955?s=20
Related
- There's a speed and focus tradeoff when building a core product and just using a frontier model/harness, but this is a pretty compelling arg…
- managed agents are the right form factor but the lock-in is real if your agent harness lives inside a model provider, you dont own the memor…
- i agree there should be managed agents, i just think they should be built on open harnesses and open memory standards
- > which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want!
- harness engineering > prompt engineering prompts get you 80% there the last 20% — tool routing, memory retrieval, retry logic, evals — thats…
Source: Harrison Chase (X) | 2026-04-23