The invisible team member
ChatGPT is the greatest fulltime, always-on personal assistant I’ve ever worked with. It operates at the level of a confirmed senior consultant. It can handle and properly use advanced frameworks — RAPID, 3 horizons, PESTEL, Creative Thinking, Business Model Canvas, TOM Canvas, Value Proposition Canvas, and plenty more — without flinching. The catch? You need to know how to talk to it.
Prompting is a craft. Either you frontload everything in an initial prompt, injecting your methods and tools as defaults, or you structure your thinking with care along the way. Precision matters. Sequence matters. And the framing? That’s half the job. Like coding — nothing new there — but it forces a level of discipline. Lose it, and you’ll get blunders, inconsistencies, or worse: something that sounds smart but is completely off.
Bend it, shape it, rewire it
The second thing that stands out after three months is how easily you can bend it to your will — and how absurd it can become if you’re not paying attention. It will happily change its mind if you tell it its reasoning is wrong. That’s not a bug, it’s a feature.
The cheat code? Ask it to discuss its own reasoning. Tell it to simulate multiple points of view — profiles you’ve defined in your initial prompt — and it will adapt its logic accordingly. That first prompt is critical. It lays the ground for how it responds, how it argues, and what “style of thinking” it defaults to. Set it right, and it becomes a much sharper tool.
Fake it like agentic AI
Right now, agentic AI is trending. Fair. But you can already simulate that with ChatGPT — if you take on the agentic part yourself. Build a structure. Don’t ask it to answer. Ask it to list possible angles. Then ask it to build a document out of those. Then expand each option. One by one. Kill bad paths, go back if needed, branch out if new info surfaces.
This way of working rewards tree-like thinking. If you’re wired like that, it clicks fast. If not, no problem — just have it write you a reminder and follow that method. Personally, I didn’t bother embedding the process into my initial prompt. I know how to run it. But it can work either way.
don’t think straight
I know some will default to linear thinking. That’s a valid approach, and it can work — to a point. But if you’re not exploring side paths, if you’re not simulating subject matter experts in a room, brainstorming from different angles, you’re missing what GPTs are built for. You’re flattening multi-agent potential into a narrow Q&A box. That’s not what this is for.
You want a metaphor? Call it controlled schizophrenia.
How fast can you think?
What else? Framework building, idea consolidation, capability projection, business planning — even for complex topics like strategic foresight, revenue growth management, business modeling — all become ridiculously fast. Not perfect, but fast and structured.
What would take you two or three weeks with experts can be mapped in minutes. You won’t land on a polished output — you’re not shipping this as is — but you will have identified all the dimensions. You’ll have a structured overview in 15 minutes, a decision-ready deep dive in an hour.
Then just wrap it in Word or PowerPoint — ChatGPT is terrible at that part, don’t even try — and you’re good to go. Add tailoring, audience calibration, and you’re ready to pitch.
Comparing notes with a team
Let’s be honest: ChatGPT, used right, is like working with a consulting team of five or six. Four juniors and two managers, maybe. It doesn’t replace even one of them individually — it can’t run solo. You can’t leave it alone, check back later, and expect gold. It needs ongoing pressure, iteration, framing. But the output — if you stay sharp and drive the process — is comparable to what that team would deliver together.
You need to stay in control, challenge the dead angles, pressure test the logic, ask for opposing views, factor in unknown unknowns. It requires backward thinking, layered reasoning, on-the-fly research, and yes — humility.
Consulting, scaled like SaaS
But if you’ve got that mindset — if you know how to run a P&L and you understand that the Business Model Canvas is a cheat code to unfold every strategic layer — then this becomes your multiplier. You can turn one team member into a six-person A-Team. You can scale your consulting work like SaaS scaled software.
It’s not about replacing expertise. It’s about giving that expertise exponential leverage.
That’s the game.
Leave a Reply