points by gbnwl 2 days ago | 0 comments
What harness are you using? In both Claude Code and Codex I run into the issue of subagents being unable to dispatch their own subagents, so I haven't been able to play with "many layers of invocation".
[–] bob1029 2 days ago
[–] mickeyp 2 days ago
You can do this trivially in dreamcoder.ai.
Build the sub agent to your specification (prompt, how the parent agent should call it); give it tools and optionally skills; then give it permission to call some or all the other sub agents you have set up.
Easy-peasy.
With custom we don't have to disclose to the caller that the implementation of the tool is another LLM. Each piece of deterministic tool code can firewall the perspective of the model as appropriate.
Think of a sub agent as being isomorphic with a tool call.