Salesforce EVP of AI @justjayesh reveals the 3 knobs for self-improving an AI agent: better context, better tool calling, and better model weights. "The starting point is lots and lots of traces of how the agents are getting their work done. These are tasks granted to the agent that have been successfully resolved and ones that have not." "When you get a sophisticated agent to go get something done in the enterprise, it's often doing 5 to 10 context calls to ground itself, 4 to 5 tool calls…