See every AI agent
that visits your store.
See which AI agents visit, what protocols they use, where they drop off, and how much revenue you're missing.
$3,204/mo in recoverable revenue.
Moon Trail Outfitters had 2,847 AI agent visits last month. Most agents couldn't complete a purchase. Lens found why.
1,000 agent visits. 18 purchases. The gap between cart and checkout is where the money is.
ACP checkout endpoint missing
330 sessions reached cart but couldn't check out. Agents hand off to humans instead, where conversion drops to 2%.
Apply fixClaude visits 3x higher than purchases suggest
512 events, only 2 transactions. MCP endpoint returns incomplete product data. Claude retries 4.2x before abandoning.
Fix MCP schemaUCP endpoint spiked to 2.3s response time
Intermittent 503s degrading agent discovery. Caching the manifest path restores protocol score.
Cache UCPExplore the full dashboard.
Traffic charts, agent leaderboards, conversion funnels, revenue projections, session replay, protocol health, and 9 AI-generated insights. All from real demo data for Moon Trail Outfitters.
The full picture of AI agent behavior
Revenue opportunities, behavioral patterns, and protocol health across your entire storefront.
- TrafficWhich agents visit — ChatGPT, Gemini, Claude, Copilot — and which protocols they use
- JourneysFull session replay: where agents land, browse, and drop off
- RevenueAgent-attributed revenue, conversion rates, missed opportunities
- InsightsAI-generated priority fixes with revenue impact estimates
- AlertsScore changes, protocol drift, agent behavior anomalies
- PortfolioMulti-store monitoring — compare stores, prioritize interventions
Know exactly what each agent is worth.
Track revenue by agent, protocol, and session. See who converts, who abandons, and why.
Recoverable revenue across 5 fixable issues. Protocol gaps, missing schemas, and broken checkout flows are leaving money on the table.
Lens is included in every plan.
24-hour data window. No account required.
30-day history. AI insights. Revenue attribution.
90-day history. 10-store portfolio. White-label.
Works from CLI, API, and MCP
AI agents discover and invoke tools programmatically. Developers get the same access from the command line.
# Get Lens statuscurl https://agenticcom.ai/api/v1/lens/sites \ -H "Authorization: Bearer col_..." # Get agent traffic for a sitecurl https://agenticcom.ai/api/v1/lens/events \ -H "Authorization: Bearer col_..." \ -d '{"site": "my-store.com", "period": "7d"}' # Returns: agent_visits, sessions, protocols,# conversion_rate, revenue_attribution,# top_agents, drop_off_pointsInstall: npx -y @getcolter/cli · MCP: npx -y @getcolter/cli mcp --admin-tools
Common questions
How does Lens detect AI agents?
A lightweight JavaScript beacon on your store identifies AI agent traffic by user agent, referrer, and behavioral patterns. It distinguishes ChatGPT, Claude, Gemini, Perplexity, and 30+ other agents.
Does the beacon slow down my store?
No. The beacon is under 2KB, loads asynchronously, and has zero impact on page speed or Core Web Vitals.
What’s included in the free tier?
24-hour data window with basic agent counts. Pro gives 30 days of history, revenue attribution, insights, and alerts.
Can I see which products agents look at?
Yes. Lens tracks agent journeys at the page level — which products they browse, where they drop off, and which ones lead to purchases.
How does revenue attribution work?
Lens traces agent sessions through discovery, browse, cart, and checkout stages. Revenue is attributed to the agent that initiated the session, with confidence scoring based on data completeness.
Start with a free scan. Lens comes next.
Run Check (free), deploy Fix, then activate Lens to monitor real agent traffic.
Scan your store