What does the Vercel integration require?

A Vercel Pro or Enterprise plan (Log Drains are not available on Hobby), plus an LLM Pulse Scale or Enterprise plan. Setup is configuration-only, with no code changes to your app.

How does endpoint verification work?

When you create the drain, Vercel sends a verification request to your ingest endpoint. LLM Pulse responds to the handshake automatically, so the drain activates without any manual steps.

Is the ingest endpoint secure?

Yes. Your ingest URL contains a unique secret token. You can rotate it at any time, and the previous URL keeps working for 48 hours so you can update Vercel without dropping logs.

Which plans include the Vercel integration?

Agent Analytics is included on Scale and Enterprise plans, with per-URL drilldown on Enterprise.

NEW ChatGPT Ads is live : track paid ad placements in ChatGPT Learn more

Agent Analytics Integration

Stream AI bot traffic from Vercel with Log Drains

Point a Vercel Log Drain at your LLM Pulse ingest endpoint and watch AI agents like GPTBot, ClaudeBot and PerplexityBot show up in real time, straight from your deployment's request logs.

Start Free Trial

14-day free trial

Cancel anytime

Features

Your Vercel request logs, decoded for the agentic web

Vercel records every request to your deployments. A log drain streams them to LLM Pulse, where AI agents are identified and aggregated.

Real-time streaming, zero polling

Log Drains push request logs to your unique LLM Pulse ingest endpoint as NDJSON the moment they happen. No exports, no batch jobs.

AI agents identified on arrival

Each request is matched against our AI bot catalog, covering GPTBot, ClaudeBot, PerplexityBot, OAI-SearchBot, Google-Extended, Bytespider, Amazonbot and more, then grouped by company.

Verified endpoint, rotatable secret

We answer Vercel's verification handshake automatically and your ingest URL carries a secret token you can rotate, with the old URL honored for 48 hours so nothing is lost mid-switch.

The traffic your analytics never sees

Bots don't execute JavaScript, so client-side analytics miss them. Request logs catch every agent that touches your frontend or API routes.

From Vercel to LLM Pulse in three steps

Generate an endpoint, create the drain, done.

Generate your ingest endpoint

From Agent Analytics, choose Vercel Log Drains and generate your unique ingest endpoint URL.

Create the Log Drain in Vercel

In your Vercel team settings, create a Log Drain with NDJSON format and paste the endpoint URL. Vercel Log Drains require a Pro or Enterprise Vercel plan.

Watch requests stream in

We verify the drain automatically and start identifying AI bots immediately. Totals, trends and company breakdowns update as logs arrive.

"After noticing rising visits from various LLMs in GA4, we needed visibility into those black boxes. LLM Pulse gave us the clarity to understand our brand's evolution and shape new strategies to boost our exposure."

Victor Hernández

Casa Batlló

Frequently Asked Questions

Common questions about the Vercel Log Drains integration for Agent Analytics.

: A Vercel Pro or Enterprise plan (Log Drains are not available on Hobby), plus an LLM Pulse Scale or Enterprise plan. Setup is configuration-only, with no code changes to your app.
: When you create the drain, Vercel sends a verification request to your ingest endpoint. LLM Pulse responds to the handshake automatically, so the drain activates without any manual steps.
: Yes. Your ingest URL contains a unique secret token. You can rotate it at any time, and the previous URL keeps working for 48 hours so you can update Vercel without dropping logs.
: Agent Analytics is included on Scale and Enterprise plans, with per-URL drilldown on Enterprise.

Stream your Vercel logs into Agent Analytics

Generate your ingest endpoint and create the drain in minutes. Live on Scale and Enterprise plans.