Free
For teams getting started
$0 per month
- Up to 10 controllers
- Unlimited time · no expiry
- Public model cards readable
- iOS and Android app
- Audit log and PDF reports
- No AI features (those are in Complete)
AI included in Complete · Public model cards · Free 10 controllers
Your patrols generate data. Now they generate insight.
The first guard tour platform with anomaly detection, predictive routing, and explainable AI built in. No black boxes — every model has a public model card and a tunable confidence threshold.
Currently in beta with 12 deployments · 74% precision on missed-checkpoint detection · No cross-customer training.
Built in the open — every model auditable
- 4 production AI models
- Public model cards
- Human-in-the-loop
- EU-trained on EU data
- GDPR Article 22
- No cross-customer training
What 'AI guard tour' actually means here.
Three production models, two in development. Every output explained. Every threshold tunable. No magic.
Anomaly Detection v2.1
Isolation Forest + temporal LSTM. Flags patrols deviating from learned site patterns. 74-89% precision after 4 weeks of training data. Per-site model isolation.
Incident Classification v1.3
Fine-tuned RoBERTa. Auto-categorizes incident reports into 47 standard categories. 91% precision out of the box. EN, ES, FR, PT, DE, IT supported in production.
Predictive Routing v1.0
Constrained optimization with learned weights. Suggests checkpoint order. Reduces average patrol time 8-14%. Production beta with 12 customer sites.
Every alert. Every prediction. Every classification. Always explained.
No 'the AI said so' answers in audit reports. Every output ships with the contributing factors, confidence score, comparable past cases, and a toggle to dive deeper.
Explainable AI
Per-alert explanations show contributing factors, confidence breakdown by factor, and 3-5 comparable past cases. Audit-ready exports include the AI reasoning chain.
Confidence visible
Every output ships with a confidence score. Tune thresholds per site (50% high recall / 75% balanced / 90% high precision). The dashboard shows precision/recall tradeoff for your settings.
Customer data isolation
Anomaly Detection trains a per-site model on your data only. Base classification models were trained on a curated public + synthetic dataset (documented in the model card). Your data never trains models for other customers.
Human-in-the-loop by design
AI suggests, humans decide. No automated decisions with operational impact. GDPR Article 22 compliant. Audit logs separate AI suggestion from human action.
Public model cards
Every production model has a public card with training data sources, evaluation methodology, known limitations, and bias evaluation. Read before you buy.
EU data residency option
Inference on AWS Frankfurt (eu-central-1) for EU customers. No cross-region transfers without explicit consent. Customer-managed keys on Complete plan.
Things we don't pretend to do.
We've seen the marketing. We're going to disappoint you in the right way. This list converts more procurement teams than any feature page.
No facial recognition
Privacy regulations + bias risks. Not on roadmap. We can integrate with your existing video analytics platform via webhook if needed.
No behavior prediction on individuals
No 'this guard might be tired' alerts. Our models work on patterns, not people. Individual scoring is incompatible with our principles.
No automated decisions with impact
Every alert requires human review before any operational action. GDPR Article 22 by design. The AI suggests; a human decides.
No cross-customer training
Your data trains your models. Period. Base models are trained on curated public + synthetic data, documented in the model card.
No 'AI generates incident reports'
Drafts, yes. Auto-submit, no. The human writes the final version, with the AI suggestion in the audit trail.
No agentic AI taking guard actions
Hard no. AI agents don't lock doors, page emergency services, or dispatch responders on guardtourai.com. Humans do.
Our 6 principles for AI in physical security.
Built on principles, not hype. Every principle has a measurable commitment.
Transparency
Every model has a public model card with training data, intended use and known limitations.
Human-in-the-loop
AI suggests, humans decide on any operational action. Always.
Customer data sovereignty
Your data trains your models, never others'. Per-tenant isolation, customer-managed keys on Complete.
Confidence visible
No 'trust me' outputs. Every prediction shows confidence and contributing factors.
Limit honesty
Published precision/recall on every release. False-positive rates exposed in your dashboard.
Right to explanation
Every flagged event explainable to operations and audit. No 'the model said so' in audit reports.
What 'AI' actually means at competitors.
We update this quarterly based on public docs. Vendor claims change — we ship corrections fast.
| AI capability | guardtourai.com | TrackTik | QR-Patrol | Silvertrac |
|---|---|---|---|---|
| Anomaly detection (deviation from pattern) | ||||
| Incident auto-classification with precision shared | ||||
| Predictive routing | ||||
| Public model cards | ||||
| Confidence scores in alerts | ||||
| Customer data isolation (no cross-training) | ||||
| GDPR Article 22 compliance | ||||
| Tunable confidence thresholds |
Anomaly detection (deviation from pattern)
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Incident auto-classification with precision shared
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Predictive routing
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Public model cards
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Confidence scores in alerts
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Customer data isolation (no cross-training)
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
GDPR Article 22 compliance
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Tunable confidence thresholds
- guardtourai.com
- TrackTik
- QR-Patrol
- Silvertrac
Best fits for AI patrol
Some verticals get an outsized return on AI patrol. These are the three with strongest fit.
AI included in Complete. No add-on tax.
Unlike vendors charging 'AI tax', AI features are part of Complete at no extra cost. If AI is core to product value, it should be in the base price.
Pro
Standard guard tour platform
$3.24 per controller / month
- Everything in Free
- Unlimited controllers and sites
- Geofencing anti-fraud
- Slack, Teams and WhatsApp alerts
- PDF reports auto-sent to supervisors
- No AI features
Complete
Full platform with all AI features
$10.80 per controller / month
- Everything in Pro
- Anomaly Detection v2.1
- Incident Classification v1.3 (6 languages)
- Predictive Routing v1.0
- Tunable confidence thresholds per site
- Customer-managed keys + EU data residency
Pricing matches our hub at patroltech.online/pricing. USD figures fluctuate with daily FX from EUR base. Final amount calculated at checkout. No regional markups.
AI-specific FAQ
Is the 'AI' here actually AI, or just rules and dashboards?▼
Three production models use machine learning: Anomaly Detection (Isolation Forest + temporal LSTM), Incident Classification (fine-tuned RoBERTa), Predictive Routing (constrained optimization with learned weights). Each has a public model card with training data, architecture, and evaluation. Two more in development. We don't call dashboards 'AI'.
Will my patrol data train models for other customers?▼
No. Customer data is isolated per tenant. Anomaly Detection trains a per-site model on your data only. The base classification models were trained on a curated public + synthetic dataset (documented in the model card). We never use your data to improve products for other customers.
What if the AI is wrong?▼
Every output ships with confidence score and explainable factors. Confidence thresholds are tunable. AI suggests — humans decide on any operational action. False-positive rate is exposed in the dashboard. We treat AI errors the same as production bugs: postmortems, public changelog, model retraining.
How does this work with GDPR Article 22 (no automated individual decisions)?▼
By design. No automated decisions with legal/significant impact on individuals. AI flags + suggests; humans approve. Audit logs separate AI suggestion from human action. We have a Data Protection Impact Assessment template available under NDA.
Can I tune the confidence threshold?▼
Yes, per site. Default 75% confidence for anomaly alerts. Adjust 50% (high recall, more false positives) to 95% (high precision, may miss subtle anomalies). The dashboard shows precision/recall tradeoff for your settings based on past 30 days.
How long until the AI gives useful results?▼
Anomaly Detection needs 4 weeks of patrol data per site to baseline pattern. Incident Classification works from day 1 (pre-trained model). Predictive Routing needs 6 weeks of historical incidents for site-specific risk scoring. Until baselines are ready, the dashboard transparently shows 'Learning phase: X weeks remaining'.
Do you use OpenAI / Anthropic / Google APIs?▼
Currently no. All production models are self-hosted (open weights or trained from scratch). LLM-based incident drafting (in-development for Q4 2026) will use Anthropic Claude via private API with no data retention contract. Disclosed in changelog when shipped.
Where can I report AI errors or concerns?▼
We run a public AI Issues tracker. Anyone — customer or not — can submit observed errors, ethical concerns, or feature gaps. We respond within 5 business days. Critical bias/safety issues get priority triage within 24h.
See it on your data.
Drop your work email and we'll send the technical walkthrough link plus a sandbox model card.
No credit card · GDPR-compliant · No cross-customer training · Unsubscribe in one click.