Why We Built Slotflow

Every AI agent hits the same wall. It can research a lead, write a perfect email, qualify a prospect — and then it needs to book a meeting.

That's where things break.

The problem

Developers building AI agents have two options today:

1. Drop a Calendly link and hope the lead clicks it. The agent workflow breaks. The lead goes cold.
2. Use the Google Calendar API directly. It returns events, not availability. No slot computation, no conflict detection, no booking lifecycle.

Neither option was built for agents. Both force the developer to build scheduling logic from scratch or accept a broken handoff.

What we built

Slotflow is a REST API designed from the ground up for AI agents. One call to check availability. One call to book a slot. Webhooks when the booking lifecycle changes.

const response = await fetch("https://api.slotflow.dev/v1/bookings", {
  method: "POST",
  headers: {
    Authorization: "Bearer sk_live_your_api_key",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    human_id: "hum_abc123",
    starts_at: "2026-03-17T10:00:00Z",
    duration_minutes: 30,
    metadata: { lead_email: "alex@acme.com" },
  }),
});

The agent gets a structured response. No UI to render. No link to share. Just data.

How it works

The mental model is simple:

• Developer creates humans in Slotflow (salespeople, recruiters, support agents)
• AI agent calls the API to check availability and book slots
• End user gets booked into a time that works

The developer is our customer. The agent is the actor. The human's availability is the resource.

What's next

We're shipping fast. The core API is live. The Node.js SDK is published. The docs cover everything from quickstart to agent onboarding.

If you're building an AI agent that needs to schedule real humans, get your API key — it takes 30 seconds.