AI Infrastructure Assistant
Your infrastructure,
one question away.
Ask about server health, investigate incidents, get optimization tips, or check security posture — all in natural language. The AI Assistant knows every server, service, domain, and alert in your infrastructure. Smart model routing delivers fast answers for simple questions and deep analysis when you need it.
2
AI models
<1s
Simple queries
$0.001
Per simple query
Auto
Model routing
Example Questions
What can you ask?
The AI Assistant understands your entire infrastructure context. Ask anything from high-level status checks to deep technical analysis. Here are some examples to get you started.
Status
"How is my infrastructure doing?"
Get a complete status overview with server health, active alerts, capacity warnings, and recent incidents. One question replaces checking five different dashboards.
Triage
"Which servers need attention?"
Get a prioritized list of servers with active issues, sorted by severity. CPU spikes, disk pressure, failed services, expiring certificates — ranked by urgency so you fix what matters first.
Root Cause
"Why is api.example.com slow?"
Root cause analysis with correlated metrics across the stack. The assistant checks server load, database queries, network latency, and recent changes to pinpoint the bottleneck.
Security
"Are there security risks?"
CVE scan results, expiring certificates, failed SSH logins, open ports, and outdated packages — all summarized with severity ratings and remediation steps.
Optimization
"Recommend optimizations"
AI-powered config tuning suggestions based on your actual usage patterns. Right-sizing recommendations, MySQL/PostgreSQL tuning, nginx optimization, and resource rebalancing across your fleet.
Timeline
"What happened last night?"
Incident timeline and resolution summary for any time period. See what alerts fired, which servers were affected, how issues were resolved, and whether any follow-up is needed.
Smart Model Routing
The right model for every question.
We automatically route your question to the right model — fast answers for simple questions, deep analysis when you need it. You never have to think about which model to use. The router classifies your intent and picks the optimal path.
Simple Questions → Haiku
Status checks, server lists, alert summaries, certificate expiry. Fast responses under 1 second at approximately $0.001 per query.
Complex Analysis → Sonnet
Root cause analysis, optimization recommendations, security audits, incident post-mortems. Deeper reasoning at approximately $0.02 per query.
Model Routing Example
"Which servers are online?"
Haiku"List active alerts"
Haiku"Why is db-prod-01 slow?"
Sonnet"Optimize MySQL on web-prod-02"
SonnetPlan Availability
AI Assistant by plan.
The AI Assistant is available on Starter plans and above. Query limits scale with your plan so you always have the capacity you need.
Free
$0/mo
Not included
Use AI Analysis with your own API key instead. The AI Assistant is available starting from the Starter plan.
Starter
$9/mo
20 queries/day
Perfect for daily status checks and quick troubleshooting. Covers most individual developer and freelancer needs.
Pro
$29/mo
100 queries/day
Designed for teams running production infrastructure. Enough capacity for multiple team members and complex analysis workflows.
Enterprise
Custom
Unlimited
No query limits. Priority model access with dedicated throughput. Custom model configuration and SLA guarantees.
Ask your infrastructure anything.
Start with the free plan and upgrade to unlock the AI Assistant. Natural language queries, smart model routing, and deep infrastructure context — all built in.