Kodexa
1 / 11

The Knowledge
Engineer.

A role we keep performing without naming. What it is, what it does in the first three months, and where it sits in our platform and process.

What We Heard

"Without your help, we couldn't have worked out how to define the knowledge we needed to capture."

We hear a version of this on every engagement. The customer knows their work cold. They cannot say, on their own, which parts of that knowledge a system needs and in what shape. We do that part for them, and we've been treating it as setup rather than as the thing we're actually good at.

The Discipline

Getting the knowledge out is the work.

Reading the document is the easy part. The harder job is getting the knowledge out of people's heads and into a form a system can use. There's a name for that work, and it predates us: knowledge engineering. The old AI field called the bottleneck "knowledge acquisition," and the people who did it were knowledge engineers.

The tooling has caught up. The models are cheap and getting cheaper. That makes the elicitation the scarce skill, not the build. It's the one part of our delivery a customer cannot do without us.

Where It Fits

Our platform runs a cycle. Someone has to start it.

Studio · Define

Define the knowledge.

Data structures, validation rules, and extraction logic for the customer's documents and decisions.

The Knowledge Engineer's job
Workflow · Maintain

Maintain it over time.

Corrections, exceptions, and the customer-specific rules captured as the work runs.

Customer + platform
Knowledge · Apply

Apply it at scale.

The accumulated expertise runs autonomously, around the clock, inside the customer's tenant.

Platform

The platform maintains and applies the knowledge well. The first definition, getting the right knowledge into Studio in the right shape, is where customers stall. That's the slot.

The Role

A Knowledge Engineer embeds with a new customer to turn how their experts actually work into a knowledge model the platform can run, then hands it off and steps out.

They are not a project manager and not an integration engineer. Their craft is elicitation: sitting with the people who do the work, surfacing the rules that live in their heads, and encoding the judgment that makes the process correct, not just automated.

The Crux

Short-lived by design. Three months, then out.

The instinct with long customer work is to keep the expert embedded. That's how vertical AI companies become consulting firms with a software line item.

So we cap it. The Knowledge Engineer is a front-loaded role: heavy at the start, gone by the end of month three. They define the knowledge, prove it runs, train the customer to maintain it, and leave. What stays behind is the platform doing the applying and the customer doing the maintaining, neither of which needs us in the room.

If the role can't withdraw on schedule, the knowledge wasn't captured well enough. The end date is the quality test.

The First Three Months

What the engagement looks like.

Month 1 Elicit
  • Sit with the experts who do the work today
  • Surface the unwritten rules, exceptions, and routing logic
  • Assess real document samples, not idealized ones
  • Draft the first knowledge model
Ships: draft knowledge model
Month 2 Encode & prove
  • Build the model into Studio
  • Run it against live documents
  • Tune against the corrections experts make
  • Close the gap between extraction and decision
Ships: running pipeline
Month 3 Hand off
  • Train the customer's team to maintain the model in Workflow
  • Document the knowledge and the decisions behind it
  • Set the maintenance and exception process
  • Withdraw
Ships: customer owns it
What Compounds

Each engagement leaves an asset, not just a live customer.

The knowledge model a Knowledge Engineer builds for the first customer in a vertical is the starting point for the next one. The domain content carries over even when the customer doesn't.

Engagement
Embed, elicit, encode for one customer.
Vertical knowledge model
Entities, decision points, document patterns, edge cases for the vertical.
Next customer starts ahead
Template, not blank canvas. Weeks become days.

Engagements like this build IP instead of draining margin. The role pays for itself twice: once in the deal, once in the asset it leaves behind.

The Boundary

What stays human, and what the platform does.

Knowledge Engineer (human)

  • Understanding why the business handles documents the way it does
  • Deciding which knowledge to capture, with the customer's experts
  • Judgment on ambiguous, exception-heavy cases
  • Teaching the customer to own the model

Platform & agents

  • Assembling the pipeline and review UI from the model
  • Suggesting schema from sample documents
  • Running extraction, flagging low-confidence results
  • Applying the knowledge at scale, every run inspectable

As the agents absorb more of the mechanical setup, the human role narrows to exactly the irreducible part: the elicitation and the judgment. That's the part worth a person's time.

For Us to Decide

Open questions for the room.

We start with people because the knowledge starts with people. Someone has to get it out of their heads and into the platform. That someone is the role.