Question 1

Is this a Sentry replacement?

Accepted Answer

No, they complement each other. Sentry monitors production errors for engineers. InsightRecorder captures sessions and logs across staging, dev, and customer environments, then governs and delivers them as fix-ready, audit-proof reports.

Question 2

Can I run my own LLM?

Accepted Answer

Yes. Triage runs against any OpenAI-compatible endpoint (OpenAI, Ollama, vLLM, Groq) or Anthropic, including local models inside your own VPC, with a documented no-train policy.

Question 3

Can the AI detect incidents in my logs?

Accepted Answer

Yes. On demand or on a schedule, the model scans a window of your ingested logs and flags the single most significant incident (DDoS, database connection-pool exhaustion, auth abuse, error spikes) with severity, confidence, evidence, and a recommended action. Findings are persisted, deduplicated, shown on the dashboard, and alerted to Slack, all running your own model.

Question 4

Where is the data stored?

Accepted Answer

Wherever you pin it. Per-tenant data residency (us/eu/ap) is enforced at the write path, and InsightRecorder ships as a single self-hostable binary so storage and inference can stay inside your boundary.

Question 5

Can I prove the audit log wasn't tampered with?

Accepted Answer

Yes. The audit trail is append-only and SHA-256 hash-chained with an external anchor, so any altered or removed row is detectable, even by a privileged database actor. Export to CSV/JSON is built in.

Talk to the team.