Can we replace the LLM from the agentic orchestrator with a decision engine?. Of course…
This is a vibe coding post classified by AGK Intelligence as Agent infra & costs (a tool drop), kept by the Vibe Coding Radar because it carries real work, not commentary.
Can we replace the LLM from the agentic orchestrator with a decision engine?. Of course we can, and you will get 2x speed!!!. Same agent workflow, run twice at the same moment: same MCP server, same nine tools, same final answer step. Left: a language model decides every hop. 6 calls to Claude. Right: a decision model decides every hop. 1 call to write the answer. 15.07s vs 7.00s. 1,284 tokens vs 7,357. Opus judged both blind, on the decision path as well as the answer. Level on both. Click it yourself: https://race.embedding.in/ Doc at: https://studio.embedding.in/docs/web
Posted by Nandakishor m (8.8k followers) 3 days ago · 58 likes · 2.4k views · view the original post on X. Kept by the Vibe Coding Radar as Agent infra & costs. Tools mentioned: Orchestrator race.
More vibe coding work like this
- If you want to learn how to build self-improving harnesses, check out this paper. — @dair_ai
- Build an agent on @onkeiki to answer your customers while you sleep. — @orchid_hq
- how do you stop 20+ agents from colliding on the same client work? — @webjuice_ie
- Brilliant paper on optimizing agent environments. — @dair_ai
- Docker is one box. The coding agent can run in others, and switching is one line 🧰 — @marcelotryle
- Holy f*cking sh*t... everyone upgrades Claude and nobody builds the harness — @gippp69
- 1/9 — @TollyLabs
- As AI coding agents get more capable, knowing what they're doing becomes just as… — @EntelligenceAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:07 UTC. Full method.