AI Diagnostics

How AI Analysis Works

  1. Your natural language query is sent to the agent
  2. Agent collects relevant ETW events based on query context
  3. Local correlation engine processes events, filtering out PII and proprietary information
  4. Correlated findings are packaged into a structured prompt with system context
  5. Prompt sent to Claude AI via CloudAPI
  6. AI responds with diagnostics, root cause, and recommendations

Example Queries

  • “Why is the SQL Server service failing to start?”
  • “What processes are accessing C:\ProgramData?”
  • “Show me all failed authentication attempts in the last hour”
  • “Why is the system slow right now?”
  • “What changed before the application started crashing?”

Query Pool System

TierMonthly QueriesCost
Data RetentionConfigurable duration that cloud-stored data (events, metrics, correlations, sessions) is kept before automatic purge. Free tier: 14 days. Paid add-on tiers extend to 90, 365, or 730 days. Billed per managed agent per month.
BYOKUnlimitedFree (your Anthropic key)
Professional1,000$39/mo
Business5,000$99/mo
Enterprise50,000$249/mo

What Consumes Queries

  • Live Session Question: 1 query
  • Multi-Agent Question: 1 per agent per question
  • Cross-Correlation: 1 additional per device
  • Alert AI Analysis: 1 per alert (cached 24 hours)

Shared across all org members. Unused queries do not roll over.

Inflection Root-Cause Analysis (RCA)

Every agent’s heartbeat is scanned for inflections — sudden metric movements like CPU spikes, memory drops, or disk-time surges. The dashboard surfaces unacknowledged inflections as Anomalies on each agent row. Clicking View anomalies opens a per-agent drawer where you can select one or more anomalies and click Analyze (RCA) to launch a focused AI investigation.

What RCA does

  • Brackets the timeline. The cloud takes the min/max timestamps of the selected inflections and pads ±60 seconds, then queries every captured event in that window from the agent’s event store.
  • Builds a focused prompt. The model receives the inflection list (metric, direction, before/after values, percentage change) plus events grouped by ProviderName, severity-tagged, and message-truncated. Up to 500 events are included to stay within token budgets.
  • Returns structured output. The response is split into three sections — Root Cause, Evidence, Recommendations — rendered as collapsible panels in a modal overlay. OS-tagged commands are suggested where evidence supports them (PowerShell on Windows, bash/systemctl/journalctl on Linux).

When evidence is thin

If the bracket contains zero captured events — for example, the inflection happened before the agent started shipping events, or capture was disabled during the spike — the model is told to reason from the inflection metric alone and to be explicit about the uncertainty. You’ll see a “Zero events in bracket” note in the Evidence section.

Cost & provider

Each RCA consumes 1 AI query from your workspace pool, just like a live-session question. The call routes through the same BYOK / platform-key resolver as the rest of the AI surface — if you’ve set a custom provider key in Settings → AI Settings, RCA uses it; otherwise the platform default is used. Token cost and elapsed time are surfaced in the modal footer.