What ICM looks like at scale: 372 pages in 3 days

Update from the floor at eMerge Americas 2026 in Miami.

Before I drove down, I built every exhibitor at this conference their own custom landing page. One person, 3 days, 372 unique sites, each one tuned to a specific company's stack, brand, and AI posture.

Forget the logo-swap template thing. Each page is real research. Every site has:

A Big-4-grade read on the company (filings, leadership moves, where AI actually shows up in their stack)

Their brand kit pulled live from their own site (logo, color palette, typography, voice)

A specific thesis on where Eduba fits inside what they already have

Matching case studies from our book of work, routed by vertical

Our 60/30/10 rule applied to their stack, showing exactly where traditional code, rule-based logic, and AI each belong in their environment

My Calendly at the bottom

When I walk up to a booth, I already know the company. They already have a page. The conversation starts three beats ahead of where it normally starts.

———

The part nobody is talking about yet.

372 pages is the headline. The bigger unlock was what came after.

Once every exhibitor had a page, I fed the whole list back through the folder system and had it score each company across a tiered rubric I wrote: deal size fit, stack readiness, decision-maker presence on the floor, vertical match to active Eduba case studies, and signal strength from their recent moves.

Out came three tiers:

Tier 1 (hit first, hit hard): companies where the thesis is strongest and the buyer is likely walking the booth

Tier 2 (warm pass): worth a 5-minute stop, drop the page link, follow up

Tier 3 (skip or graze): acknowledge, move on

Then I asked it to build me a walking game plan. Booth numbers, floor map, tier order, clustered by physical location so I wasn't walking the same aisle twice. Morning route, afternoon route, with buffer built in for the Tier 1 conversations that were going to run long.

I walked in on day one with a printed route and a stack of pages ready to send mid-conversation.

———

Here's what I actually want you to hear.

I didn't grind this out. I ran it through a folder system Jake designed.

This is the thing he keeps repeating about abstraction layers. The layer below agents. The layer where context becomes a first-class asset instead of something you stuff into a prompt.

He calls it Interpretable Context Methodology. ICM. It's the core of everything we build at Eduba and everything we teach in this community.

In practice: you organize the workspace so reference material, contracts, templates, and per-company outputs all live in known, deliberate places. Every generation step reads from known locations and writes to known locations. Voice rules, routing logic, case-study inventory, skip list, tiering rubric, floor map, the 60/30/10 framing applied per company. All of it sits in a layer above the generation.

The architecture won't let the model drift.

What comes out reads like the prospect's own marketing team built it. The tier list reads like a seasoned BDR wrote it. The walking route reads like a conference vet planned it. Same folder system, three different outputs.

———

About the 60/30/10 on every page.

Every single landing page shows the prospect their own stack through the 60/30/10 lens. 60% traditional code. 30% rule-based logic. 10% AI.

That framing changes the booth conversation completely. Most vendors walk up selling more AI. We walk up showing them where AI actually belongs, and where it probably shouldn't go. It reframes us from "another AI consultancy" to "the people who understand when not to use it."

Half the conversations at Tier 1 booths pivoted the second they saw that section.

———

Pick any and go look:

Delta Air Lines: https://delta-air-lines.eduba.io/ (updated live after Delta's MD of HR Innovation gave his talk. The page quotes his actual words and maps them to ICM.)

Amazon: https://amazon.eduba.io/

Google Cloud: https://google-cloud.eduba.io/

Second Front (defense software delivery): https://second-front.eduba.io/

JPMorgan Chase: https://jpmorgan-chase.eduba.io/

Scroll any of those to the 60/30/10 section and you'll see what I mean.

Or browse all live sites: https://github.com/Eduba-io

———

Why this matters for you.

If you're building with AI and still feel like you're gluing prompts together, that's the signal. The abstraction layer you need doesn't exist yet for your workflow. Build the layer first. The output gets better, faster, and more yours. Then the same layer powers the next thing, and the next.

372 pages. A tiered hit list. A floor plan. 60/30/10 applied to every stack in the building. One folder system.

———

A few housekeeping notes:

This is why I've been quiet in the community this week. Heads down on the build, then heads down on the floor. I still have tomorrow at the conference to work the Tier 1 list, then I'm back in the DMs Saturday morning to catch up with everyone.

I'm walking through the whole build on High Tea this week. Folder structure, the tiering rubric, the voice contracts, the prompt that generated the walking route, how 60/30/10 gets applied per company, the lessons from running it live on a conference floor. Bring questions. If you've been trying to figure out how to apply ICM to your own sales motion or conference prep, this is the session.

41 comments