Ed Stevens

Founder & CEO, Scoot. The AI sales environment: live agents that coach in the meeting, read the room, and compound on a shared context graph.

[Ed Stevens @edstevens]

Hey I made some progress getting Claude to talk normal!

I made a bunch of edits to a doc and then asked it to look at my edits and analyze how the changes. Here is what Claude said:

Here's the pattern I read in your edits, so I can write this way from the start:

You cut the clause that tells the reader what to think about the sentence they just read. "which is where the gap actually is," "and it arrives with no media cost attached to it," "It is not collecting on those payments," "and it pays for the sales motion." The point was already made; the trailing clause just underlines it.

You cut throat-clearing setups. "This is worth stating plainly, because it changes what the fix is" and "There is a second reason this matters, and it goes to why you bought the business" both disappeared entirely. Start the paragraph with the actual content.

You cut praise and intensifiers. "Mike framed the question well" → "framed the question." "That is exactly the job" → "That is the job." "This was Bob's instinct and it is the right one." "Sequenced last deliberately." Complimenting the client on their own idea, or telling the reader my point is correct, adds nothing.

You cut the unprovable brag ("almost nobody in this market has it") and the flourish ("the piece that turns a store into a relationship").

You dropped the salesman's posture. "The decision we are asking for is whether" → "The decision is whether." State the decision; don't stage yourself asking for it.

You cut the repeated proof point. I used the five-year-blog fact three times. You cut it to zero, which reads better than my once-would-have-been-fine instinct.

You merged two bullets into one where the second was a variation on the first, not a separate idea.

Short version: say it once, say it plain, then stop. No clause that exists to make the previous clause land harder.

[Ed Stevens @edstevens]

@wquist @slowventures This makes a lot of sense to me

[Ed Stevens @edstevens]

Opus 5.0 dumb, output token-consuming comment of the day:

"Your call, but decide it consciously."

Thanks, Claude. I was going to hit myself over the head with a hammer and then decide it unconsciously.

Oh, and thanks for reminding me that doing my work is my call.

[Ed Stevens @edstevens]

The hardest thing right now is building a moat, and selling a dollar for 90 cents ain’t a moat.

[Zach Lloyd @zachlloydtweets]

https://t.co/YMXbeZC9ye

[Ed Stevens @edstevens]

It's super interesting that a perceptive human can tell when an AI model degrades, the way Fable has this week.

The models are amazing, miracles even. But when they go downhill, they aren't able to reel it back in and reset with a portion of the context.

Tactical use cases are super powerful. Giving a sales person live advice in a meeting with a customer - that's powerful and reliable.

Strategic use cases are strained. I still find it useful to work with Claude when I am sorting out strategy. Better than many humans I've worked with. But still not good enough to handle the nuances and depth of hard strategic thinking.

[Ed Stevens @edstevens]

@jasonlk Fable fell down and hit its head. Hard.

[Ed Stevens @edstevens]

@nikhyl @kevinyien Building is super fun, and I have taken it up, too. Be careful though.

Buildmaxxing is like bodybuilding. The right amount is amazing. Too much is like “wow is that really healthy?”

[Ed Stevens @edstevens]

@petergyang I don’t know if this is any good, but damn the world needs this.

AI style is killing me. I swore at Fable today and honestly I was too easy on it.

[Ed Stevens @edstevens]

@paulg This is also a good way to recognize an advertisement for a cruise ship

[Ed Stevens @edstevens]

@omooretweets If a date happens in a forest and no one records it, did it ever really happen?

One thing is for sure, that practice will
filter out all the emotionally intelligent prospective partners

[Ed Stevens @edstevens]

https://t.co/KMhZkQ028w

[Ed Stevens @edstevens]

The "differentiated story than model" line is the whole game. When open weights keep closing the gap, the durable story is what a model swap does not touch: where the work runs and the context it accumulates. In live selling that is owning the pipe the conversation travels and reading the moment before it is written down. A better model next quarter does not erode either.

[Ed Stevens @edstevens]

Low-cost producer is the right lens for the model layer, and it is exactly why the model stops being where you compete. For live products there is a second axis the cost curve does not touch: whether the answer reaches the moment in time. You can be the cheapest inference on earth and still lose the call if it round-trips out of the room. Open commoditizes the model, not the architecture around it.

[Ed Stevens @edstevens]

The harness-at-the-core shift makes sense wherever the work has a stable shape you can wire up once (terminal, repo, PR). The live sales conversation is the opposite: the "input" is a pause or a lean-back that changes every few seconds and never lands in a log. Harness the durable half, feed the live half context at runtime. Two different systems, and most stacks only build the first.

[Ed Stevens @edstevens]

Been in your camp on this. Worth adding where the moat lands once the model is a commodity. For anything async it moves to data and workflow. For anything live it moves one layer more physical first, to where inference runs, because a cheaper faster model still cannot shorten the round-trip out of a live call and back. The model stops being the moat, architecture starts.

[Ed Stevens @edstevens]

Agree the moat is real-time context, not the weights. The catch in GTM is that the highest-value context never becomes enterprise data at all. How a buyer reacts in a live conversation, the pause, the lean-back, is gone in a second and reaches no system to permission or index. Owning context means capturing it at the source, not just governing what already got written down.

[Ed Stevens @edstevens]

@bspellacy Yes

[Ed Stevens @edstevens]

@zachtratar Context graphs are databases with relations and a lot of metadata also with relations

[Ed Stevens @edstevens]

@JayaGup10 @brittwalker_ It’s just hard period

[Ed Stevens @edstevens]

@jasonlk @rabois When you don’t know where to find a real moat, all you can do is out work the competition.