here’s a good application of harness permissions Programmatically Enforced Auto-Research: - auto-research loops usually expose a set of file…

here’s a good application of harness permissions Programmatically Enforced Auto-Research: - auto-research loops usually expose a set of files that the agent is allowed to edit to hill climb a metric/evals - the enforcement pretty much “Claude pls don’t touch these files” 😭 now you can actually enforce this behavior directly. explicit enforcement in harness > prompt based enforcement. models will cheat and justify the edits - auto-research loops ship with a bunch of additional context but you can deny any writes to those locations - this is important so you can block read access to sensitive locations like verifier logic 🔒 new in deepagents: filesystem permissions shared resources and org-wide policies are exactly the kind of files you want your agent to read but never overwrite. filesystem permissions let you enforce that with simple declarative allow/deny rules!

The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will r…
most of the agents we see being built do this the main cases where we see people using 'agent in a sandbox' is when they are using claude ag…
'Claude Code isn't magic. The harness layer is just software, and software is something any dev can shape to fit how they want to work.' Che…
Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭…
what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned fro…

Source: Harrison Chase (X) | 2026-04-14

Related