Welcome to The Hero 🗞️. This is approximately a 2.5-minute read.

Most recruiting teams run 10+ tools…

But they only use about 30% of each.

And every single one requires you to open it, click through it, copy something out, and paste it into the next one.

That's not a tech stack. That's a to-do list with monthly fees.

Here's what changed:

AI agents can now plug directly into your tools - read the data, take action, and move to the next step.

No clicking.

No copying.

No pasting.

But only if you let the tools in.

That means the tool needs an open connection - a way for software to talk to other software without a human in the middle. If your tool doesn't have one, your agent can't touch it. It just sits there waiting for you to click.

A recruiter using an ATS opens roles, adds notes, and moves candidates between stages by hand - whereas an agent running that same ATS does all of that automatically - and uses it as the starting point for sourcing, outreach, scheduling, and reporting.

Same tool.

Completely different value.

The full breakdown is just below - don’t miss it! 😉

Here are some of the best links I’ve found since last time I emailed you: 

10 Proven Employee Retention Strategies for 2026 and Beyond. (link)

2025 Retention Report: Employee Turnover Insights and Trends (link)

The State of Job Descriptions: Trends, Best Practices & AI-Powered Optimization (link)

10 Tips for Using Inclusive Language in Job Descriptions (link)

The Best AI Recruiting Tools for 2026 (link)

AI in Recruiting (2026): What to Automate and What Not To (link)

2026 Recruiting Trends: What's Shaping the Year Ahead (link)

Can your agent plug into it and use it without you?

If yes - that tool goes from "saves me 20 minutes" to "runs a whole workflow while I sleep."

If no - you're still the one doing the work.

Every tool below passed that test for us.

Not because of the interface.

Not because of the demo.

Because the agent can read it, write to it, and act on it.

{{rp_personalized_text}}

The layer that connects everything else.

Free, open-source, 68K+ GitHub stars.

Without it, the list above is just software.

With it, the agent coordinates across all of them automatically.

The brains - both of them.

Claude for deep thinking, writing, and complex workflows.

ChatGPT for running every report, follow-up, and daily action.

Don't pick one - use both.

The candidate intelligence layer. 

Sourcing, profile data, interview memory, scorecard signal. 

The new MCP lets Openclaw query interview data directly. 

This is so the agent knows what roles are live, what's paused, who the client is, what the comp is, etc.

Any ATS will work, we use RF.

Way more than a scheduling tool.

Configure your agent uses it to know when to stop sourcing (five screens booked? Pause), when to refill, and where delivery is actually converting into hires.

The outreach engine.

Unlimited inboxes, and built-in warmup.

Finding great candidates means nothing if your messages land in spam.

Their agent reads replies, pulls insights, and messages candidates back - no manual follow-up and you can create sub-sequences.

The labor pool LinkedIn doesn't reach.

Trades, operations, manufacturing, skilled labor - Indeed owns this.

And the difference between an agent reviewing 2,500 applicants and a human doing it is the single biggest time-save in the entire setup.

The new recruiting stack isn't about collecting tools…

It's about picking the ones your agent can actually run.

The agent reads the calendar, queries the ATS, mines the data, sends the outreach, books the screen, and reports back.

You show up for the conversation.

Automate the process.

Protect the human layer.

There are a few ways:

Or you can just reply to this email.

I reply to absolutely everyone who writes me back 🙂