Founder shares full AI resume-screening pipeline with prompt: MCP agents, junk scores, dedup rules
AnuranBuilds · x · 2026-10-31
The founder of Alchemyst AI shared the full pipeline the company uses to screen job applications with AI agents. Each role draws hundreds to thousands of applications, and even manual review found 98% were low-signal.
Pipeline and criteria:
- Applications (email or browser) are connected to internal agents via MCP, which filter out anything crossing a "junk" score
- Low-signal weights: irrelevant credentialism (20-25%), no proof of work (30-40%, most common), short-term intent (15%), tunnel vision / no generalist work (10%)
- Hiring philosophy: skills are easy to build past a threshold; thinking while chasing a problem is what's hard
Full screening prompt included: the agent acts as a technical hiring analyst, restricted to India-based 2025/2026 graduates, defaults to the last six months of applications, must collect 100 distinct applicants before applying exclusions for "latest 100", dedupes emails and inspects full threads/follow-ups/attachments, and marks ambiguous cases "Needs verification" instead of guessing.
Related event: Startup Reveals AI Agent Resume Screening Pipeline(2 posts)→
More from coding & agent
- 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
- optimAIzr ships VS Code extension to track Claude Code usage, caches and limits — stichstichstich · 2026-10-31
- Pass/Fail Beats 1-5 Ratings for Agent Regression Tests, Argues Practitioner — intellectronica · 2026-10-31