Professional learning path

AI Engineer

Deliver an AI feature with versioned prompts, evaluation evidence, and controlled access.

Prepare

Prepare reviewable inputs for an AI-assisted workflow

Run the mortgage kit and inspect the income discrepancy. Define which source fields an assistant may use, which statements require evidence, and where a human must review its recommendation.

Start with the browser demo or download the local kit. For the workspace exercise, you need approved access to the relevant Genedata capabilities and a reviewer for your output.

Practice tasks

0 / 4 completed

1
2
3
4
Knowledge checkpoint

An assistant fills in an income value that is absent from the supplied documents. What should happen?

Notes and progress are saved on this device.

Apply in your workspace

Build AI that works with business context.

Deliver an AI feature with versioned prompts, evaluation evidence, and controlled access.

1

Define the user task and identify the approved knowledge sources and tool permissions.

2

Build the prompt or agent workflow and keep prompt versions and input expectations explicit.

3

Evaluate representative cases, including failure and boundary conditions, and compare quality with cost.

4

Release the reviewed version through the agreed approval path and observe behavior after integration.

Expected handoff

A versioned AI workflow with evaluations, permissions, and a named owner.

Explore your platform capabilities

Measure your progress

  • Time from a prompt change to a reviewed evaluation
  • Escalations caused by missing context or permissions

Use AI to draft candidate prompts and test cases; review retrieved evidence and keep consequential actions under human control.