How does the CEO of an $8B company triage 120 LinkedIn comments without losing an afternoon?
A hiring post pulled in 120 comments asking to apply. Reading each profile, scoring each comment against the role's criteria, is a 2-6 hour job. I built an agent to do the first pass. Ranked the field in 4 minutes.
The scoring rubric
Five axes derived from the post itself, weighted by what the role calls for:
- technical_depth0-30 - engineering background, code-shipping role, builder track record
- ai_agent_experience0-25 - LLM work, n8n/Zapier/Make, agentic frameworks, RPA, AI automation
- systems_thinking0-20 - platform/infra/architect/founder/CTO roles, system design
- comment_substance0-20 - concrete work in comment (numbers, repos, demos) vs. vague
- velocity_signal0-5 - recent pivot into AI, public building, in-flight projects
These weights and definitions are tunable. Different criteria → different rankings. The agent runs the same way against any rubric you define.
What the commenter pool actually looks like
Top role keywords (qualified)
Top geographies
Top 10 candidates - anonymized
Identities, profile links, and full breakdowns sit in the private brief. Below shows score, tier, and the agent's reasoning so you can see how it's evaluating.
| # | Score | Tier | Why qualified |
|---|---|---|---|
| 1 | 62 | strong fit | 14-year full-stack engineer with hands-on LangGraph/LangChain multi-agent RAG systems, CKA, and production SaaS architecture experience. |
| 2 | 62 | strong fit | Production RAG pipeline builder with strong cloud infra/DevSecOps background, compliance experience in fintech, and a concrete technical article shared. |
| 3 | 58 | strong fit | Built a multi-agent system with LLM-as-judge, conditional retries, MCP tool layer - demonstrates real agentic architecture thinking. |
| 4 | 58 | strong fit | Production ML background at a bank, Google Build With AI Hackathon winner, and co-founded an LLM/agent startup on the back of it. |
| 5 | 54 | strong fit | Claims hands-on multi-agent orchestration platform with named agents, routing logic, memory, and self-correction running on owned hardware. |
| 6 | 52 | strong fit | 11+ years AI experience, architecting production agentic RAG systems at Shell serving 15K+ daily users with LangChain/LangGraph/CrewAI stack. |
| 7 | 44 | worth a look | Hands-on with n8n, LangChain, CrewAI, MCP servers, and Python; built his own agent-readiness platform RankedLM. |
| 8 | 42 | worth a look | Solid Technical Lead at AI-focused company (Harrison.ai) with multi-language backend depth and team architecture experience. |
| 9 | 42 | worth a look | Built and shipped a conversational AI chatbot for agentic payments on WhatsApp and automated a $200M+ OTC treasury workflow - concrete deliverables. |
How it was built
- Pull the public comments on the post + each commenter's public profile data
- Score each commenter against the 5-axis rubric using Claude Sonnet 4.6, structured JSON output per candidate
- Generate two briefs: named (private, sent on request) + anonymized (this page)
- Static site (Next.js + Tailwind), deployed on Vercel
Build included one tool pivot mid-way. Net: a CEO's 2-6 hours of focused review work compresses to ~$2 and 4 minutes of agent runtime, with the human still making the actual hiring decision.
The named ranking
The full named brief - top 25 candidates with profile URLs, full comment text, and per-axis breakdowns - is available on request. Happy to forward it over LinkedIn if it's useful.
Want to build this for your own team?
The same agent can score any LinkedIn post's commenters against any rubric you define - hiring, partnership outreach, event audience analysis, customer pre-screening.
Drop a comment on the LinkedIn post and I'll share the build walkthrough.