Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.nebulaengage.com/llms.txt

Use this file to discover all available pages before exploring further.

Nebula gives recruiters and hiring organizations a structured way to assess how candidates actually behave in workplace situations — not how they say they would behave. Instead of relying on self-reported experience or interview performance alone, you can place every candidate inside the same simulated corporate environment, assign them the same scenario, and compare their responses to the same pressures. The result is a consistent, evidence-backed performance record that travels alongside a candidate’s application.

What Nebula measures

Traditional interviews test communication under optimal conditions. Nebula tests behavior under real workplace pressure — competing priorities, demanding stakeholders, ambiguous information, and decisions with consequences.

Workplace decision-making

How a candidate reasons through decisions in context, weighing trade-offs and committing to a course of action when information is incomplete or stakes are high.

Stakeholder management

How a candidate navigates relationships across authority levels — managing up, handling conflict, and keeping competing interests aligned under time pressure.

Communication style

How a candidate adapts their tone, clarity, and approach when communicating with different personas: executives, peers, direct reports, and external stakeholders.

Role readiness signal

An AI-generated narrative that summarizes the candidate’s overall suitability for a professional role, based on observed behavior across the full session.

The six skill categories

Every session report scores candidates across six professional skill categories. These scores are derived from observed behavior — not self-assessment.
SkillWhat it reflects
CommunicationClarity, tone, and audience awareness across all interactions
Decision makingQuality of choices at structured decision checkpoints
Stakeholder managementNavigating relationships, influence, and competing interests
Technical acumenDomain knowledge and how it’s applied within the scenario
LeadershipDirection-setting, accountability, and managing pressure
Time managementPrioritization, deadline handling, and workload discipline

How the assessment workflow works

1

Invite candidates to a session

Share a Nebula session link or access code with your candidates. Each candidate starts their own isolated simulation — the company world and scenario are loaded fresh for each individual.
2

Candidate completes the simulation

The candidate goes through AI onboarding, receives a role assignment and case study, and completes the simulation inside the virtual desktop workspace. They interact with personas, handle emails and tasks, and navigate decision checkpoints across the scenario.
3

Session report is generated automatically

When the simulation ends, Nebula generates a full session report without any manual review step. The report is available immediately and contains all the data you need to evaluate the candidate.
4

Reviewer accesses performance data

You review the candidate’s session report through the analytics interface. Every data point is grounded in specific, logged events from the simulation — not summary impressions.

What the session report contains

At the end of every candidate session, Nebula produces a structured report with the following outputs. Overall score — A 0–100 composite score reflecting the candidate’s performance across the full session, weighted across decisions made, communication quality, and stakeholder interactions. Skill scores — Individual scores for each of the six skill categories, showing where the candidate excels and where gaps exist. Decision patterns — A behavioral fingerprint drawn from how the candidate approached decision checkpoints throughout the session. Patterns reveal consistent tendencies: do they escalate early, avoid risk, defer to authority, or act without sufficient information? Evidence highlights — Specific moments from the session cited as evidence for the scores. These are direct references to what happened in the simulation, not generalizations. Readiness signal — An AI-generated narrative that synthesizes the candidate’s overall performance into a role readiness assessment. It surfaces judgment, professional maturity, and observable strengths or gaps. Strengths and improvement areas — A structured list of the candidate’s demonstrated strengths and the areas most in need of development, derived from the full session record.

Comparing candidates

Because every candidate who runs the same scenario inside the same company faces identical world conditions, scores are directly comparable across your applicant pool. You can rank candidates by overall score, drill into specific skill categories relevant to the open role, or use decision patterns to identify behavioral tendencies that matter most for your team.
All candidates face the same company world, the same domain, and the same scenario parameters. This standardization removes the variability that makes traditional interview comparisons difficult — you are comparing performance against a fixed, known challenge, not against different interviewers or question sets.

Advantages over traditional assessment

  • Replayable and auditable — every session is backed by a structured event log, so you can review what happened and why scores were assigned
  • Scenario-consistent — candidates are not assessed against different interviewers, question styles, or personal rapport
  • Behavioral, not self-reported — performance data comes from what candidates actually did, not what they claim they would do
  • Immediate output — session reports are generated automatically at session end, with no manual scoring or debrief required
  • Cross-candidate comparability — scores across the same scenario are directly comparable, making shortlisting more objective
For roles that require strong stakeholder management or communication under pressure, filter your session report review to those specific skill categories and cross-reference the evidence highlights. The evidence highlights show you the exact moments that drove the score — making it easy to discuss specific behaviors in a follow-up interview.

Responsible use of assessment data

Nebula session reports provide a structured, evidence-based view of candidate behavior. Using this data responsibly is your organization’s obligation. The following guidance applies.

Scores are one input, not a hiring decision

The overall score, skill scores, and readiness signal are inputs into your evaluation process — not replacements for human judgment. Do not use a Nebula score as the sole basis for advancing or rejecting a candidate. Scores should be weighed alongside interviews, work samples, references, and other contextual factors.
No automated assessment tool, including Nebula, should be used as the sole determinant of a hiring decision. Candidate scores must be reviewed by a qualified human decision-maker before any consequential action is taken.
Candidates should be informed before completing a Nebula simulation that:
  • Their session will be recorded and scored
  • The session report will be shared with the hiring organization
  • The report will be used as part of the evaluation process
Do not present a Nebula assessment as a generic “workplace exercise” without disclosing its evaluative purpose.

Bias mitigation and fair use

Nebula simulations are designed to be scenario-consistent — all candidates face the same company world and conditions. However, no assessment tool is free from potential bias. You should:
  • Evaluate candidates against the same scenario where possible
  • Avoid drawing conclusions from score differences that fall within normal variation
  • Not use skill scores as a proxy for demographic characteristics
  • Review evidence highlights directly rather than relying only on composite scores
  • Apply the same score thresholds and evaluation criteria uniformly across your candidate pool
If your organization uses Nebula scores in decisions covered by employment law (e.g., EEOC guidelines in the US, the Equality Act in the UK), consult legal counsel to confirm your use case is compliant.

Data retention

Session reports are retained by Nebula in accordance with its data retention policy. Your organization is responsible for complying with applicable data protection regulations (including GDPR, CCPA, or equivalent local law) when storing, processing, or sharing candidate session data you access through the analytics interface. Do not retain candidate session data beyond what is legally permitted or organizationally necessary.

Human review requirement

Every candidate session report reviewed for hiring purposes must be assessed by a qualified human evaluator. Automated shortlisting based solely on composite scores — without human review — is not a supported or recommended use of Nebula assessment data.

Auditability

Nebula’s structured event log provides a full audit trail for every session, including the specific decisions and interactions that drove each score. If a candidate disputes their evaluation or requests an explanation of their results, reviewers can trace any score back to the underlying session events. Retain records of which human reviewer assessed each candidate’s report and when.
The Nebula session report is designed to support structured, evidence-backed conversations — not replace them. The strongest evaluations use the report to anchor a follow-up interview, where reviewers can explore specific decisions and patterns with the candidate directly.