Here’s how I picture it, using our setup as the example. Our main agent has five subagents:
| Subagent | Picked when |
|---|---|
| publicator | a member shares a text to improve before posting |
| links | loose links to draft into a post |
| web | things that change outside the forum |
| base | curated archive: older discussions, documents, books |
| at | a chart a member shares, reviewed against our public method |
Today the parent LLM reads the subagent descriptions and picks one with spawn_agent. The gate would take that decision from it:
- A gate setting on the agent, pointing to a decision model.
- The choices are the subagent descriptions that already exist, plus “answer yourself”. Nothing new for admins to write.
- Only the subagents the current user can access are offered.
- Above a confidence threshold, the subagent runs directly. Below it, the result reaches the parent LLM as a hint and the LLM decides, as it does now.
- Since decision models classify images, “member shared a chart” comes from the image itself.
The same gate, as a yes/no question, would also work as a guard before the LLM runs.
We’re an education community and we don’t give signals, price targets or investment advice, so “is this asking for a trading signal?” → fixed reply. Today that rule is a line in every prompt, and models drift from it under pressure.
If you get to it, we’d be glad to try an early version on our forum.