Lurkee
I built a monitoring pipeline that collects website changes, identifies differences and uses structured AI analysis to produce prioritized findings and reports. The product connects the analysis pipeline with dashboards, alerts and billing.
The system behind the interface.
A changed page is not automatically useful intelligence. The product needs to separate noise from meaningful signals without hiding the source evidence from the operator.
Architecture choices that shaped the product.
Hashing and diffs establish what changed before an LLM is asked to explain why the change may matter.
Severity and findings use typed schemas so the result can drive alerts, reports, and filters instead of becoming an unbounded paragraph.
Routine analysis can use a lower-cost model while stronger reasoning is reserved for findings that cross a severity threshold.
What I developed.
- Scheduled collection with content hashing and unified change detection
- Structured severity classification before reporting and alerts
- Operator-facing history, report, billing, and system-health workflows
The resulting system.
An end-to-end monitoring pipeline with structured analysis, reports and an operator dashboard.
Read the engineering guide to research and report automation ↗
Relevant to your project.
If your team checks competitor websites manually or receives too many change alerts, I can develop a monitoring workflow around your sources, evidence and reporting needs. Lurkee demonstrates scheduled collection, change detection and structured analysis with a dashboard.
Explore development services ↗
Read the guide to adding an AI agent to an existing SaaS ↗
Read the guide to competitor monitoring without noisy alerts ↗