Jev Engineering gives agents a decision brain, 193x faster and 444x cheaper in tests
agihouse_org · x · 2026-09-21
The author argues the biggest leak in agent stacks is an expensive model sitting in loops answering yes/no questions, picking workers, and scoring relevance — calls that never needed generation.
- Architecture: request → structured state → Jev router → cheapest capable model → worker → relevance/approval checks → execution gate → tool
- Decision layers don't generate prose; they route, score, block, and approve — separating reasoning from decision-making
- Result: replacing 5–20 second expensive LLM calls with millisecond, near-zero-cost routing; up to 193x faster and 444x cheaper in tests
- Framed as the missing control layer for agents, with a full 10-step breakdown in the linked article
More from coding & agent
- Agent seller confesses: his 'flawless' four-month automation needed twice-weekly secret patches — Cold_Mud2650 · 2026-09-21
- Free DiffusionGemma endpoint returns sentence probabilities in ~230ms, OpenAI-compatible — victormustar · 2026-09-21
- Mozilla AI runs a local 30B model end-to-end to open a real bugfix PR, fully offline — mozilla-ai · 2026-09-21
- Dev demo: agent codes a game and generates all 3D assets itself via Hyper3D Rodin MCP — CodeByPoonam · 2026-09-21
- mcp-server-dns: Zero-config MCP server for DNS, WHOIS and domain checks — modelcontextprotocol · 2026-09-21
- Each MCP tool passes solo tests, but the agent's full workflow breaks on state passing — Stock-Pumpkin-8859 · 2026-09-21