Show how you work with AI.

Practise engineering decisions with AI. Get a private growth report on how you frame problems, question suggestions and explain your choices.

Read task materials and work through your approach in a guided text conversation.

Try a scenario See a sample report

Work at your own pace · Pause and continue

How the reports work

Illustrative example · invented run

01 / Read, question, explain

Review an AI suggestion

Interviewer

A structured checkpoint

Would you accept this change?

Explain what you checked and what you would check next.

Your answer…

Submit checkpoint

Scenario artifact

Read-only task materials

Does the shorter condition behave the same way?

Illustrative Python snippet

# Before
def count_before(items):
    if items is not None:
        return len(items)
    return None

# AI suggestion
def count_after(items):
    if items:
        return len(items)
    return None

Workbench

AI assistant

Assistant

The shorter condition preserves the existing behaviour.

You

The empty list used to return 0. This version returns None. I would check None, [] and a non-empty list before accepting it.

Message the workbench…

02 / See the evidence

Growth report

Private

AI Output Review

Adequate

Evidence

The empty list used to return 0. This version returns None. I would check None, [] and a non-empty list before accepting it.

What to develop

Turn the cases you named into checks with expected results.

This example shows reasoning and proposed checks. It does not show an executed test.

SHYWAI records evidence of thinking: what you ask, what you question and how you explain your decisions. AI is welcome. Your contribution is the focus of the report.

Why it's built this way

Make your reasoning visible while you practise. SHYWAI gives you a structured engineering situation, an AI assistant and room to explain your choices. Afterwards, return to specific moments in your report and choose one thing to practise in your next task.

How it works

Work at your own pace. You can pause and continue later from your cabinet.

1
Read the scenario and work through it with AI. Discuss the supplied materials in text. An Interviewer guides you through checkpoints; some scenarios also include a stakeholder to question.
2
The process is recorded. Your prompts, the assistant's replies and your answers are logged for analysis. No camera, microphone or screen proctoring.
3
Read your private growth report. Observations, qualitative assessments and suggestions help you reflect on this run and choose what to practise next. There is no overall numerical score.

What the report looks at

Problem Framing: How you clarify the goal, constraints and missing information.
AI Collaboration: How you give the assistant context, set boundaries and steer its work.
AI Output Review: How you question suggestions and check them against the supplied materials.
Debugging & Verification: How you form hypotheses and describe checks that could confirm or reject them.
Communication & Ownership: How you explain choices, trade-offs and what you remain responsible for.
Risk & Production Readiness: What risks and real-system constraints you notice in this scenario.

Sample growth report

Example only: an invented candidate and an invented run, cut down to one dimension. A real report covers all six dimensions, each with a label, the evidence and what to develop. It also has a Start here section when the reviews name priorities, and a summary from each review.

Example, not a real run

AI Output Review

Adequate

Continuing the illustrative conversation above.

Evidence

The empty list used to return 0. This version returns None. I would check None, [] and a non-empty list before accepting it.

What to develop

Turn the cases you named into checks with expected results. The record shows your proposed checks; it does not confirm that you ran them.

What you can share

Choose up to four available moments from a completed run to publish. Each has a short description and a quote checked against your recorded messages. It is a selected view, not your full report. No scores, no verdicts, and you can revoke it at any time.

Example, not a real page

Completed Illustrative AI review · 2026-10-14

Compared an AI suggestion with the empty-list case.

In their own words

The empty list used to return 0. This version returns None. I would check None, [] and a non-empty list before accepting it.

How to read the evidence

The report starts from the recorded run. AI reviews interpret it and can disagree; you can read their reasons. Quotes on a public page and in the report's Process notes are checked against your recorded messages. The quotes cited under each dimension are chosen by the reviews and are not checked the same way. A checked quote helps you trace an observation, but does not make a conclusion correct. Use the report to reflect on a specific decision and discuss it with another person.

How the reports work and what they can tell you

What we don't do

Not an AI detector: using AI well is the point, not a violation.
No proctoring: no camera, microphone or screen capture.
No ranking: we do not recommend or rank people for employers.
Nothing is published without your consent. Your answers are processed by third-party AI models; see how we handle your data.

AI is allowed, ownership remains yours.