Issue No. 11 - August 18, 2026

I've been cheating on my AI tools. Not dramatically. Just shopping around.

For the last few weeks I've been deliberately splitting my work across different platforms. Strategy questions go to one. Creative work goes to another. Not because I made a formal decision to do it but because I started noticing the outputs felt different depending on where I asked. And once I noticed, I couldn't stop noticing.

This isn't a platform review. I'm not going to tell you which one wins at what, partly because I'm still figuring it out and partly because it changes. Almost daily. What I've been doing is consuming a lot of content about the differences, watching what people say each tool is actually good at, and then testing it against my own work to see if it holds.

The operative word is IF. Not when. I keep seeing frameworks that assume the right move is to build a multi-platform workflow. And it's certainly an option, but I'm not yet convinced for my specific work. The question I ask before I shift anything is whether the difference actually matters for this specific task. Sometimes it does. Sometimes I'm adding complexity because someone on LinkedIn made a convincing case.

When it does make sense to split the work, the gains are real. Better strategic output in one place, better creative execution in another. Even token managment. But then I hit the thing I keep running into. Context.

Every time I move work from one platform to another, I have to bring the context with me. The background on JB Sales. The voice. The project details. The decisions we've already made. And yes, there are skills and projects set up that can do some of the lifting. But the progress forward each working session does not transfer platforms automatically. And rebuilding and remembering which things have impact on others in another platform isn't just tedious. It's a reminder of something I think we underestimate.

Context isn't a setting. It's not a system prompt or a document you paste in. At its deepest level, context is the strategy itself. It's knowing which outcomes matter most right now, in what order, and why. It's the reconciliation of competing priorities that only you can do, because only you know what's actually at stake.

AI can help you think through it. It's genuinely useful for working through the tradeoffs, pressure-testing assumptions, exploring scenarios. But it can't hold the strategy for you. It doesn't know what you're willling to trade off. It doesn't feel the weight of the wrong call. Or the general 'gut' feeling you have after years and years of experience. That part is still yours.

This is what I keep coming back to when I'm evaluating a new platform or deciding whether to split my workflow. The tool is not the strategy. No matter how good the output is, the thinking that determines whether it's actually the right output has to come from somewhere else. From you. The platforms are getting better fast. That piece isn't changing.

So, I'll stay curious. I'll keep testing. I'll keep reading what people say each tool is good at and checking it against my own experience. But I'm not outsourcing the judgment about what matters. That's the part I can't afford to hand off.

Where this lands in the three buckets

Immediately actionable: Before you split work across platforms, write down the context each one would need. Not just background facts, but the strategic priorities behind the task. If you can't articulate those clearly enough to transfer them, the platform switch isn't your real problem.

Start thinking about: Where AI is genuinely helping you think through strategy versus where you've started treating its output as the strategy itself. Those are different things. The first is useful. The second is a slow way to lose the thread of what you're actually trying to accomplish.

Next phase: A lightweight way to document your working context, not just project facts but current priorities and the reasoning behind them. Something you can update as things shift, carry across platforms, and use as the anchor for every AI interaction. It doesn't have to be complicated. It just has to be yours.

Meghan Brenner is COO at JB Sales and founder of The Operator's Notebook. The Muddy Middle publishes every Tuesday.