AI wants your data, but it can't handle the truth . . .

“We’ll just plug our data into ChatGPT.” Sure. Sounds easy. Rob thought so too, right up until he hit token limits, had to install Python, and discovered that even two megabytes of transcripts was too much for the world’s smartest models to handle. In this episode, Rob and Justin break down what happens when you try to use AI on your company’s internal data. Spoiler: it’s a lot more complicated than the vendors make it sound.

From semantic search to retrieval augmented generation (RAG), they unpack why the dream of “ask AI anything about your business” keeps falling short. You’ll hear why your Power BI model isn’t going anywhere, why structured data still needs old-school engines, and what it really takes to get value from your own information. Somewhere between a cautionary tale and a tech detective story, this one tells it like it is . . . unapologetically.

Run into the same situation? We’d love to hear about it! Give us a shout on LinkedIn and tell us how you overcame the limitations.

For a while, you could pretend AI was still a someday problem. Not anymore. Rob Collie and Justin Mannhardt are back, and this time they are tackling Model-Context-Protocol (MCP) and Multi-Agent Systems, two shifts that could finally put an end to the human copy-paste Olympics.

This isn’t about shinier tools. It is about AI that plugs in without the duct tape and starts doing the work without making you babysit. Rob and Justin dig into what’s real, what’s coming, and why "waiting to see" is no longer a strategy.

MCP is being called the USB-C of AI. Multi-Agent Systems are making AI check its own work, so you do not have to. Translation? The gap between "early" and "too late" is closing fast, and the status quo isn’t going to cut it much longer.

If you are tired of the hype but know you can’t sit this one out, this episode is the advice you have been waiting for. So, tune in and enjoy! If you like what you hear, don’t forget to leave us a review on your favorite podcast platform. Your feedback helps new listeners discover the show!

Also in this episode:

The Cybernetic Teammate

Déjà vu Cat | The Matrix

Sakiko Stickley joins Raw Data to share a story that is part inspiration, part revelation, and a whole lot of truth-telling. From the first moment she discovered Power Pivot, Sakiko did not just learn data. She lived it. She rewired reporting systems, survived micromanagers, and navigated the strange realities of big consulting firms, all while quietly proving that one person, one model, and a little bit of DAX can change everything.

In this episode, we get an inside look at how a passion for smarter systems can collide with corporate inertia, what it really feels like to challenge the status quo, and why Sakiko believes AI could someday outperform human leadership, not just in data crunching but in ethics and decision-making too. (Spoiler: She might be right.)

If you have ever felt like a lone voice in a world that clings to inefficient processes, Sakiko’s journey will feel like a kindred spirit calling from across the data universe. Listen in for a conversation filled with hard truths, breakthrough moments, and a reminder that true data people do not just build models. They build better futures.