How this dashboard was made
This dashboard was generated using Claude with access to the ArborXR + Insights MCP Server, by prompting:
"My senior leadership has asked for a report on how my VR training program has been going, and want to know what's working, what's not, so they can see the ROI of this VR program and investment. I want to generate a comprehensive dashboard to deeply understand all of these things, and more, that's interactable, informative, and polished to impress senior leadership. Not only do I want a full understanding of how my learners are performing, where they might need additional training, how they might be struggling, and when, so that I can improve the program, but I also want to be able to justify the ROI for further investment in VR. Please build that dashboard, with a light-mode styling."
One prompt, 90 days of Insights data — every chart below comes straight from the SDK's assessment, telemetry, critical-event, poll, and device streams.

FireSafe VR — Fire Extinguisher Certification Program

ArcticLine Industries  ·  Powered by ArborXR Insights  ·  Jan 20 – Apr 19, 2026 (90 days)  ·  Per-user authenticated sessions
Adoption is compoundingWeekly sessions jumped +62% after the Feb 19 training mandate and have held. Utilization is no longer the bottleneck — content depth is.
Content v1.3.0 lifted pass ratesThe Mar 21 content update (clearer extinguisher rack labeling) lifted certification pass rate by ~5 pts vs v1.2.x — measurable within two weeks via the SDK's version metadata.
Onboarding drop-off~8% of learners don't finish the tutorial walkthrough on the first try, concentrated at Grandview Hotel. Recommend a facilitator for first sessions there.

Weekly training sessions

Headset sessions per week · dashed lines mark the mandate email (Feb 19) and content v1.3.0 release (Mar 21)

Certification pass rate by week

Share of certification attempts scoring ≥ 80 · trend crosses the v1.3.0 release

Program funnel

Enrolled → tutorial → practice → certification attempt → certified

Pass rate by content version

Version-over-version comparison from super-metadata on every event

Every layer of the Insights SDK feeds this report

Data streams captured by FireSafe VR's deep integration
AssessmentsObjectivesInteractionsScenario levelsExperiencesCustom eventsCritical safety eventsSpatial dataTelemetryTimed eventsLogsIn-headset pollsCross-session storageDevice tagsPer-user identity
Remediation worksLearners who failed their first attempt improve by +19 points on average after targeted practice — the biggest gain of any cohort.
EMS trainees set the ceilingEMS / volunteer-firefighter trainees average ~94 with a 96% first-attempt pass rate — a useful benchmark for what "expert" looks like.
Hints predict struggleScores fall sharply up to ~3 hints per attempt, then plateau. Learners requesting 3+ hints are strong candidates for proactive coaching before their certification attempt.

Certification score distribution

Best score per learner · pass line at 80

Cohort outcomes

First-attempt pass vs eventual certification rate

Pass rate by attempt

Retakes convert — the program recovers most first-attempt failures

Hints used vs score

Each point is one certification attempt

Score gain, attempt 1 → 2

Average improvement among retakers, by cohort

Learner roster

Individual records via per-user authentication — search, sort, drill down (names are synthetic)
PASS technique is the weak skillOnly ~68% pass the Pull-Aim-Squeeze-Sweep objective (threshold 75). Sweep motion and step sequencing drive most failures — worth a dedicated micro-module.
"Know when to run" gap41% initially chose to fight the oversized warehouse fire and 33% engaged the ambiguous-smoke hallway instead of evacuating. Judgment scenarios need reinforcement, not just technique.
Grease fires confuse extinguisher choiceThe single most-missed interaction is selecting the wet-chemical extinguisher for the breakroom grease fire — 34% initially grab water or ABC.

Performance by certification objective

Five weighted objectives from the assessment tree · avg score and pass rate

Scenario difficulty

Avg level score and % making the correct fight-vs-evacuate call

Most-missed interactions

First-try failure rate across graded interactions

Median time to identify fire class

Timed-event data (time_to_fire_class_decision), by site
Violations are fallingSafety violations per 100 sessions dropped ~52% from the first month to the last — the clearest evidence the training changes behavior.
Server room drives wrong-agent errorsThe Class-C server room scenario accounts for nearly half of all wrong-agent violations (water/ABC on electrical). This is exactly the mistake that's catastrophic in real life — and it's being caught in VR.
Two site storiesAtlas Manufacturing cut wrong-agent violations ~60% after their safety lead reviewed weekly Insights reports with crews. Meridian Data Center spiked in week 6 when the new server-room scenario shipped, then recovered.

Safety violations per week, by site

EventCritical stream · stacked weekly counts

Violation types

90-day totals across the critical-event taxonomy

Violations by training scenario

Which situations trigger unsafe behavior

Violation rate per 100 sessions

Normalized for training volume — the leadership metric
Grandview is slower to decideMedian fire-class decision time at Grandview Hotel runs ~25% above other sites. High new-hire mix + no facilitator — recommend guided first sessions.
atlas-07 needs maintenanceOne Quest 3 at Atlas logs ~4× the frame-drop warnings of the fleet average. Auto-telemetry caught it before anyone filed a ticket.
Northstar runs a proctored program72% of Northstar Hospital certifications are proctored vs ~13% elsewhere — device tags + assessment metadata make compliance segmentation free.

Site comparison

Segmentation via ArborXR device tags — no app changes required

Sessions by headset model

Fleet mix from device tags

Device health — frame-drop warnings

Warn-level logs per 100 sessions · worst 10 devices

Device utilization

Avg sessions per headset over 90 days, by site
Payback in weeks, not yearsAt current volume the hardware investment pays back in ~5 weeks. Every learner after that is ~$194 cheaper than classroom delivery.
Time returned to operationsVR certification takes ~36 min vs a 2.5-hour classroom block — ~3,000 work hours returned per year at planned volume.
Risk reduction is the real prizeViolations caught and corrected in VR (wrong agent on electrical, failure to evacuate) are the incidents that cost six figures in real life. NFPA-average direct cost of a workplace fire incident exceeds $85k — model below assumes just one avoided every two years.

ROI model — adjust the assumptions live

Defaults reflect our program; edit any input and the model recalculates

Fully-loaded cost per certified learner

Delivery cost + wages for time away from work

Cumulative 12-month cost

VR line includes hardware up front — the crossover is the payback point

Learner confidence — before vs after

In-headset PollUser ratings (1–5), pre-training vs post-certification

"What was hardest for you?"

Post-session poll · confirms the PASS-technique skill gap independently

Learner sentiment

From in-headset exit polls
Would recommend (NPS)
from 1–10 recommendation poll
Rated training 👍
87%
thumbs poll, 70% response rate
"AI instructor helped"
78%
shown after ai_instructor_consulted
Avg post confidence
up from pre-training
FireSafe VR is a fictional company with synthetic data. This dashboard was created in one conversation with the ArborXR Insights MCP.