Accelerating recruiting data analysis, natural-language hiring analytics, summaries, funnel audits, and recruiting data visibility

The best AI in the world is pretty much useless to an in-house team if it doesn't know your company, your hiring managers, or your actual pipeline.
Right now, most TA teams are stuck manually copying and pasting candidate profiles or req data into ChatGPT just to get a basic summary. It's a massive time suck.
So we fixed that. With Loxo MCP, you can now connect Claude or ChatGPT directly to your live Loxo database.
No more digging through filters or exporting spreadsheets. You can just ask plain-English questions like:
"Who has been sitting in 'Hiring Manager Review' for more than 3 days?"
"Give me a quick brief on this candidate before my screen."
"Where are the biggest gaps in our engineering pipeline right now?"
Real answers in seconds, using data only your company owns.
Check out the clip below to see how it works.

https://lnkd.in/dt8XkezQ

Today, we’re launching the Ashby MCP Server in Open Beta, available on all Ashby plans.

MCP gives AI tools a standard way to connect to external systems. With Ashby’s MCP Server, customers can make live recruiting context from Ashby available to MCP-compatible AI clients like ChatGPT, Claude, Cursor, and others, without building custom middleware or maintaining a bespoke integration.

Should recruiters use AI? Yes (with caveats).

But all the AI and tooling in the world doesn't change the fundamentals. AI doesn't make a bad process good. It makes it fast. And a bad process at scale is the worst version of hiring there is. Point it at a structured, consistent one, and it helps run that process for every candidate. Not speed. Not cleverness. Consistency.

A few things I believe after building this into a real talent function:

▪️ The recruiter stays at the centre. AI can make you faster and better informed. The human still makes the call and owns the outcome.

▪️ The constraint isn't which model is smartest. It's whether it can see the whole hiring story. Scatter it across email, Slack, and half-filled ATS notes, and your AI only ever reasons about the easy half.

▪️ Hiring is two kinds of work. Predictable work you automate. Judgment work AI assists with, but never decides.

▪️ The resume is an even weaker signal now. Both sides have the same tools. That's not a crisis, it's a forcing function for skills-based hiring. It strips away the lazy proxies and rewards the teams who already knew what "good" looks like and built a process to test for it.

I just hosted the first episode of the Pinpoint How-To Series on exactly this.

I walk through the five areas where this changed how I work: intake and role design, candidate management, recruiting content, reporting and insights, and interview prep.

It's 20 minutes, practical, and I share the three red lines I won't cross. Link in the comments.

Recruiting used to mean logging into your ATS, clicking through pipelines, manually sending follow-ups, pulling reports.

Now you just... ask.

"Find every candidate with an AI fit score above 70 and send them a follow-up."
"Generate my weekly hiring report."
"Move everyone who hasn't responded in 10 days to a nurture sequence."

Done. In seconds.

We just launched our MCP server, 130 tools that connect your 100Hires account directly to Claude or ChatGPT. Your AI can now read your pipeline and take real actions in it.

Recruiting hasn't changed this fast in a long time.

100Hires.com - Attract, Interview, and Hire the Best Candidates Faster by Using AI

New York, NY — May 7th, 2026: Greenhouse, the leading hiring platform, today announced the Greenhouse MCP (Model Context Protocol), a new capability that gives customers a governed way to connect AI tools directly to Greenhouse. Developed with input from customer design partners, including StubHub and Komodo Health, the Greenhouse MCP will be rolled out to customers starting in June.

But connecting powerful models to sensitive hiring data has been difficult to do safely. Many organizations want to automate and improve existing workflows, enable new kinds of actions across systems, and experiment with AI-assisted ways of working. Doing that outside the hiring system of record creates risk. The Greenhouse MCP is designed for exactly those goals, a standard, permission-aware way for approved AI tools and agents to connect to Greenhouse, inside the structure teams already rely on.

Here's 5 recruiting agents I use daily at Abnormal AI.

🔍 Outbound Sourcer: Thinks like a top recruiter and a top candidate at the same time. Reads the profile, infers what motivates them, writes outreach that actually lands. Not templates. Actual personalization at scale.
📝 Intake Agent: Stops bad reqs before they open. Pushes back on vague job descriptions and forces clarity on what "good" actually looks like. Less interview noise. Fewer late-stage surprises.
🎯 Debrief Synthesizer: Turns messy panel feedback into a clear hiring decision. Flags conflicting signals, catches bias patterns, and makes a recommendation. Hire, no hire, and why.
🦄 Recruiting Ops Automator: Finds where your process is quietly breaking. Time-in-stage, funnel drop-off, and offer slowdowns — surfaced automatically, no manual report needed.
🏆 Talent Brand Agent: Keeps your voice consistent across every candidate touchpoint. Same positioning, same tone, no drift. It also includes employee stories for the different job families.

The numbers across two quarters: 88% offer acceptance with a 46.6% InMail response rate — nearly 2x benchmark, up 22.6% since October.

That's what recruiting on systems looks like. Most teams have the same tools.

The gap is whether you're building or waiting.

I keep building things and then not knowing how to talk about them.

Not because they're complicated. Because every time I sit down to write a LinkedIn post, I realize the thing I want to say is actually 1,200 words long :)

So I'm putting it all in a new blog. I want us to share what we're building and to show that getting there isn't nearly as intimidating as it sounds. I started where most people start. I made a lot of mistakes. I lost track of time in my home office more than once. And I got somewhere I couldn't have imagined a year ago.

The first post is about the last year: starting with ChatGPT and job descriptions, learning to connect to data, joining Formation Bio, and eventually building tools with Claude Code that I use every single day that have fundamentally changed how I work.

Special shout out to those I've met along the way. Jason Miller , Joe Atkinson and the entire PromptMates community - it's been so fun to learn how to do this in talent together! If you're curious what that actually looks like inside a company that takes AI seriously, I hope you'll read it. https://lnkd.in/eiGPccRK

Most recruiters are leveraging AI in the wrong way and wonder why candidate experience is getting worse...

Over time, my hires are more or less evenly split between:
- Applications
- Referrals
- Sourced/headhunted.

The real time-killers remain painfully human:
- Reviewing 1000s of applications
- Rallying colleagues for referrals
- Sourcing & engaging passive talent

Once suitable and relevant candidates are in the funnel, they all get pre-screened and interviewed.

I use AI for:
✅ Summarising lengthy interview transcripts
✅ Sharing job, interview, team & culture details with candidates at scale
✅ Analysing my own hiring data

I DO NOT use AI for

❌ Reviewing or rejecting applications
❌ Engaging and messaging passive talent
❌ Conducting actual interviews

AI should elevate my experience as a recruiter, not replace my judgement or ability to interact with candidates.

Agree?

Everyone thinks AI in recruiting is about speed and efficiency. I can screen 10,000 more resumes now. I can manage 10 or 12 roles without being the bottleneck. AI will do the work I don't have time for.

That’s the wrong path.

When you think like that, you’re trying to remove yourself from the process. You’re looking at AI like it’s there to screen resumes, surface the top candidates, and call it a day. That’s what every sourcing product does.

And you can see where that leads. Just look at Eightfold. They’re now facing a class action, and The New York Times wrote about it. Their AI turned into a black box that started discriminating against candidates.

A lot of teams bought it chasing speed, not quality.

The real value isn’t in getting through more resumes. It’s in learning from the ones you already have.

Where are you sourcing wrong? What makes a quality hire in your pipeline? Which filters are hurting you instead of helping?

AI can answer those questions if you use it the right way. Give it your data and ask for patterns, not shortcuts. Let it help you find strategies, not do your homework.

You can move fast all you want, but that doesn’t always mean you’re finding better people.

Everyone is talking about AI in recruiting, but much of the conversation remains at a surface level, focusing on tasks like writing job descriptions or automating screening processes. The real opportunity for recruiters lies much deeper.

In recent months, I have been experimenting with AI in areas that traditionally consume the most time for recruiters: research, market intelligence, and talent strategy. Here are a few interesting use cases that have proven effective:

• Talent mapping in minutes: AI analyzes company ecosystems, competitors, and adjacent industries to identify non-obvious talent pools.

• Sales hiring intelligence: Quickly understanding which SaaS companies are scaling in specific regions and where strong enterprise sellers are likely to be found.

• Stakeholder advisory: Transforming raw hiring data into insights, including market compensation trends, talent availability, and realistic hiring timelines.

• Candidate insight synthesis: Summarizing lengthy interview notes and identifying patterns across candidates more efficiently.

AI is shifting the recruiter’s role from “process manager” to “talent advisor,” allowing recruiters to focus on what truly matters: people, potential, and impact.

I am curious to hear from others in talent acquisition: How are you using AI in your recruiting workflows today?