Team wires MCP-connected AI agents to auto-reject ~98% of job applications
AnuranBuilds · x · 2026-10-31
A team shared how they screen job applications: every open role draws hundreds to thousands of applications, and roughly 98% felt like a waste of time to review manually.
They define a "low-signal application" scoring rubric: irrelevant credentialism like college/GPA flexing (20-25%), no proof of work such as missing GitHub projects or stale portfolios (30-40%, most common), short-term intent (15%), and tunnel vision against generalist work (10%).
In practice, they connect applications arriving via email or browser to internal AI agents through @getalchemyst's MCP, letting agents filter out anything crossing a "junk" score threshold. Notably, they don't screen for skills — past a minimum threshold, skills are easiest to build; what's hard is thinking while chasing a problem and ambition to grow.
Related event: Startup Reveals AI Agent Resume Screening Pipeline(2 posts)→
More from coding & agent
- 7 free Claude Skills that fix the cookie-cutter look of AI-generated pages — socialwithaayan · 2026-10-31
- Tibo's 28 Days of Shipping: 8 Resets in 28 Days Reveals AI Coding Tool Instability — heypearlai · 2026-10-31
- Developer ships one AI-built micro app per day with Opus 5.5, launches a full collection on TikTok in under a month — ilumine_ai · 2026-10-31
- Codex now lets you take a photo mid-session on mobile — Dimillian · 2026-10-31
- Retro funding redesign: prediction markets cut reviewer load by only judging challenged projects — devanshmehta · 2026-10-31
- Using dot, Grok bot, or Claude Duet to watch a cluster is a surprisingly effective SRE strategy — sloppenheimer · 2026-10-31