Salesforce EVP of AI @justjayesh reveals the 3 knobs for self-improving an AI agent:…
This is a dev post classified by Jev as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
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 to go get the job done. All of this needs to be part of the traces." "Improvement can happen in one o
Posted by MTS (508.7k followers) 2 days ago · 15 likes · 7.2k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Hallmark has been installed 50k+ times! — @nutlope
- Your AI coding agents need a workflow, not more babysitting. — @DanKornas
- Register by October 7 and save >> https://bit.ly/4vkntyD — @linuxfoundation
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.