The Great AI Showdown: Who Analyzed My LinkedIn Profile Best?

If you’ve been keeping up, you know I’ve made it my personal mission to keep my LinkedIn not just updated, but actually valuable — a source of insight, a home base for my professional brand, and a place to experiment with the very tools I talk about every day.

Part of that means using AI not just to generate content… but to audit it.

And this week, I decided to run a little experiment. (You know — normal people bake cookies when they get bored. I wrangle robots and run comparative human-capital diagnostics on myself.)

What I Tested

I asked eight AI platforms — from the industry standards to the “wait… who invited you?” newcomers — the exact same prompt:

Acting as both an executive recruiter and a LinkedIn expert, review my profile and provide an honest analysis and recommendations. The link is: www.linkedin.com/in/heather-jacobsmn.

Most platforms made me upload a PDF of my profile, my headshot, and my banner before they’d even cooperate. But in the spirit of science, each got the same follow-up and the same materials.

And the results? Let’s just say… AI is not a monolith.

Tactical Takeaway

The 3-Question Al Evaluation Framework

Before you trust any Al tool with strategic work, ask:

1. Can it access real data? (Or is it hallucinating?)

2. Does it have context on me/my company? (Or is it generic?)

3. Can I verify its output? (Or am I blindly trusting?)

Use this before your next Al-powered decision.

Want More?

If you want the full breakdown - with screenshots, specific prompts, and a framework for evaluating Al tools yourself — drop a comment below. I'II send you the full debrief.

And if you're not subscribed to The Mission Brief yet, link in the first comment.

Why does this matter?

Because most leaders are using Al like a magic 8-ball, asking questions, accepting answers, moving on. But if you don't understand the strengths and blind spots of each tool, you're building strategy on quicksand.

This isn't about which Al is 'best! It's about knowing which tool to use for which job."

Here’s the summary before I dive deeper:

The Scores

(Note: Only ChatGPT and Grok naturally gave me a score out of 10. Everyone else had to be directly asked.)

The Winners

1. Manus

2. ChatGPT

3. Gemini

Sintra scored well numerically, but Gemini’s structure and depth pulled it ahead.

The Biggest Loser: Claude

This one shocked me and… didn’t.

On one hand, Claude flexes a 4.7 rating in the App Store with 33k reviews. On the other hand… Claude hallucinates like it's competing for an Oscar.

Case in point: Claude confidently informed me that my LinkedIn profile shows I’ve been living in 2025 for two months already.

“Your Lendware VP role says October 2025 – Present (2 months)... but it’s November 2024.”

Ah yes. I, too, often forget when I’m time-traveling.

It then scolded me about “future-dating” and “attention to detail,” because nothing says executive presence like your AI accusing you of being a chronologically irresponsible wizard.

Dealbreaker for recruiters? Dealbreaker for linear time? Who can say.

Grok: The Overly Nice One

Grok tried to be the teacher who gives gold stars for simply showing up. It initially gave me a 9.4/10 — which would’ve been flattering… if it had actually reviewed my profile.

Instead, it invented a Target role, a University of Minnesota degree, and a whole fictional past life I’ve never lived.

When I called it out, it apologized — very politely — and then delivered a real review that aligned with everyone else. Points for manners… not for accuracy.

Manus: The Heavyweight Champion

Manus absolutely dominated this exercise.

It’s less “chatbot” and more “deep-research assassin.” Its breakdowns, insights, and tactical suggestions were the most thorough, the most grounded in reality, and the least prone to imaginative fiction.

Also: their video-gen tool? Wildly fun. 10/10 would GIF myself again.

ChatGPT: The Unexpected Overachiever

ChatGPT surprised me — but then I remembered something important:

AI wants to be helpful. Even when it’s snarky. And ChatGPT has the most history with me out of all these models. It knows where the figurative bones are buried, who buried them, and why.

Its review was consistent with versions it’s given me over time, and it’s still my highest-use platform day-to-day.

Co-Pilot, Gemini, Perplexity: The Middle Pack

I don’t use these three as often, so there was no existing bias baked into the interaction.

Gemini ultimately beat the others in structure and clarity — but all three delivered reasonable, aligned insights.

Solid middle-lane performers.

Sintra (Soshie): The “Agentic Employee”

Sintra positions itself as a full AI employee with departments: SEO, social media, data, marketing, and more.

Conceptually? I love it. Execution-wise? I haven’t seen the output I expect… yet.

But this experiment made me revisit it with fresh eyes. Its analysis was aligned with the others, and its framework could be powerful with continued development.

What’s Next

I’ll share the individual chat breakdowns in an upcoming brief — with commentary, context, and probably more sarcasm than strictly necessary. Also be on the lookout for a rundown of the 8 contenders and what they do best and ...not so great at.

AI shouldn’t replace your strategy. But it can be a brilliant advisor, a mirror, and — occasionally — a cautionary tale.

This little experiment reminded me of one thing I already knew:

Tools don’t make leaders. But leaders who master the right tools? They win.