AI-assisted candidate sourcing, Boolean search, and profile summaries

I have spent nearly three decades in talent acquisition, and one thing has always stayed true.

Recruiting works best when the systems behind it work.
Clear intake. Strong sourcing strategy. Clean workflows. These are the pieces that make the work feel doable instead of chaotic.

In healthcare especially, I have seen how easy it is for recruiters and sourcers to feel overwhelmed when roles are complex, pipelines are thin, and tools do not always keep up. I have also seen how the right process can change everything.

This is the space I love working in.
Intake. Sourcing strategy. Outreach. The small systems that create big wins.

I am also a strong believer in using AI to support the work we do. Not to replace recruiters, but to help us think more clearly, write more effectively, and move faster when it matters most. I use AI every day to build sourcing plans, draft outreach, clean up job postings, and bring structure to the parts of recruiting that often feel messy.

If you care about:
 building better sourcing systems
 improving intake
 modernizing how we approach hard-to-fill roles
 using AI without feeling overwhelmed
 making the day-to-day work feel lighter

You are in the right place.

I will be sharing more of what I have learned over the years. Practical strategies, prompts, sourcing ideas, and lessons that come from real experience in the trenches of healthcare recruiting.

If this resonates, I would love to connect and learn from your work too. Here is to building better systems together.

Don’t always trust AI... This is my AI‑generated caricature.
In its defense… I gave it data, not context.

And that’s the lesson, especially in recruiting.
AI can source, screen, summarize, and suggest.
But it can’t replace judgment.
It can’t read nuance.
And it definitely can’t build relationships.
Only you can make yourself replicable! Learn how to work with the tools, not handing them the keys.
AI doesn’t replace recruiters.
Recruiters who know how to use AI replace inefficiency.
Use the tool.
Be the differentiator.

I DID IT. I AUTOMATED MY RECRUITING BACKEND WITH CLAUDE CODE.
And ironically, it made me more confident in the future of recruiting, not less.

I recently learned about the "doorman fallacy". When automatic doors were introduced, many hotels assumed they would no longer need doormen. They believed the job was simply opening the door. What they failed to recognize was that the visible task was not the value. The value was the relationship. The doorman greeted guests by name, built familiarity over time, hailed cabs, carried luggage, and created a sense of trust and hospitality that no automated door could replicate.

That framing has been sitting with me because over the last two days I have nearly automated my backend recruiting workflow using Claude Code. I built systems that identify candidates in my vetted network, surface them to me for open roles, screen my inbox to determine who else I should be speaking with from the VC talent community, who I have not followed up with, and draft succinct notes pulled from my extensive candidate notes explaining to founders why specific matches from our network make sense. It is far from perfect. It is scrappy, occasionally messy, and could be significantly optimized. But it works, and it will only get better as the models improve. As a talent partner supporting an entire portfolio, that speed matters. More importantly, it means I am spending less time clicking through profiles one by one and more time going deep with founders, hiring teams, and our candidates.

This reinforced something I have believed for a long time. The mechanical parts of our jobs are not the reason we have them. Searching, tagging, sorting, summarizing, and writing repetitive emails were necessary steps, but they were never the moat. The moat is trust built between humans. It is a founder calling you first because they need someone in their corner, not just in their inbox. It is a candidate being honest with you because they know you will be honest back. It is pattern recognition that only exists because of years of real conversations with real people who chose to let you in. The moat is not what you do. It is who you are to people.

As a recruiter, if you define your role by opening the door, automation feels threatening. If you define your role by building the relationship, automation is leverage.

I Built a Full Hiring Automation System And It Changes Everything for Recruiters

Most organisations are still hiring the way they did 10 years ago manually sourcing profiles, reading every resume, sending copy-paste messages, and scheduling endless intro calls.

I designed a system that flips that entirely.

Here's how an end-to-end AI-powered hiring automation pipeline works — and why your recruiting team needs it NOW 👇

🔍 STEP 1 — Smart Sourcing (300–400 Profiles Per Role, Per Day)
I built the system to auto-generate Boolean search queries based on must-have skills, job titles, and dealbreakers — then pull 300–400 matching profiles daily from LinkedIn and Naukri directly into your ATS/CRM. No manual hunting. No missed talent.

🧠 STEP 2 — AI-Powered Screening (2-Layer Filter)
Every resume is parsed into structured data — skills, experience, companies, education, and seniority level — then scored using a two-layer approach I designed:
✅ Layer 1: Rules-based filtering (removes candidates missing must-haves instantly)
✅ Layer 2: AI Scorecard (GPT-4o / Claude) — evaluates skill match, project relevance, career stability and flags risk signals like job-hopping or skill gaps, with written reasoning and quoted evidence from the resume.
Recruiters only see candidates who are actually qualified.

✉️ STEP 3 — Personalized Outreach at Scale
Forget generic InMails. I integrated AI to draft hyper-personalized messages referencing each candidate's specific skills, current role, and standout projects — then run multi-step follow-up sequences automatically. Reply classification (Interested / Not Now / Wrong Person) is handled by AI so your team spends zero time sorting inboxes.

🎤 STEP 4 — Async AI Interviews (Before a Recruiter Ever Joins)
I added an async interview layer where interested candidates receive a chat or video interview link they complete on their own time. The system transcribes responses, scores competencies, flags weak answers, and pushes a full recommendation (Proceed / Hold / Reject) into the ATS — before a single recruiter minute is spent.

🛠️ The Tech Stack I Used
ATS/CRM: Greenhouse / Lever
Workflow Orchestration: n8n → Airflow
Data: Postgres + S3 + Pinecone (Vector DB)
AI Layer: GPT-4o / Claude + embeddings
Parsing: Affinda, Sovren, DaXtra
Outreach: Lemlist, Reply.io, Apollo
AI Interviews: HireVue or custom-built with Twilio + Whisper + LLM


The result? Recruiters stop doing administrative work and start doing what they're actually great at — building relationships and making great hiring decisions.

This isn't the future of hiring. It's happening right now.

🎥 Watch the full video breakdown above to see how each piece connects.

If you're in HR, Talent Acquisition, or building recruiting tech, drop a comment or DM me. Happy to share the full system design.

♻️ Repost if you think every recruiting team should see this.

“Will AI take over recruitment?”

I get asked this a lot.... and I’ve thought about it… a lot.

Can AI source candidates better than me in some ways?

Sure. It can scan faster. Parse resumes. Spot surface level matches.

It takes a lot of prompting to get AI to truly understand the roles I work on.. why certain experience correlates.. to know which “nontraditional” background translates.

And that’s before we even get to the real differentiator.

Being a person is something only a person can do...

It’s hearing the hesitation in someone’s voice when they say, “Yeah… I think the interview went.. pretty well.” It’s knowing when to pause, dig deeper, and ask the question between the lines.

Also.. as much as I love my Chat… mine can be verrrrrry validating. A little too agreeable. Sometimes a bit of a "confirmation bias cheerleader".

✨ My chat thinks you should allllll want me to be your recruiter 😉 ✨

However, in recruitment, that agreeableness.. is dangerous. This job isn’t about being told you’re right. It’s about challenging assumptions, pressure testing motivations, and protecting both sides of the hire ... even when it’s uncomfortable.

AI is a powerful tool. I use it. I respect it. I’m glad it exists.

But trust, intuition, judgment, and real human connection? That’s not getting automated anytime soon.

And until it can hear what isn’t being said… I’m not worried.