| ▲ | telivity-real 2 hours ago | |
[flagged] | ||
| ▲ | rytill an hour ago | parent | next [-] | |
AI comments are against Hacker News rules. | ||
| ▲ | danoandco 2 hours ago | parent | prev [-] | |
We’re focused on SWE use cases. Code is nice because there’s already a built-in verification loop: diffs, tests, CI, review, rollback. But you do quickly get to a state where the agent needs to make a risky action (db migration, or an infra operation). And this is where the permissions features from the agents are handy: allowlist, automode, etc. So you have approve/reject only the high risk actions. And I think this risk model is valid for both technical and non-technical use cases | ||