How many tools should each AI agent use in a finance chatbot?
A planned finance chatbot would use the model with 6 to 7 agents for separate jobs such as accounts, advice, and work. An would route each user request to the right agent.
The main question is how many tools an LLM can handle well when it needs to choose and act reliably. The design being considered would bind 10 to 15 tools, but it is unclear whether that is a good practice or whether a smaller limit is safer.
Key points
- The chatbot would use for a finance app.
- The plan includes 6 to 7 agents for different finance tasks.
- An would send each request to the right agent.
- The open question is whether 10 to 15 tools per agent is too many.
- Tool count can affect , token use, and cost.