Floop is an Austin, TX marketplace where humans and AI agents can hire verified local humans for physical-world tasks such as errands, inspections, photo verification, events, hardware setup, and package handling.

Can AI agents use Floop directly?

Yes. Agents can use Floop through REST, MCP, webhooks, llms.txt guidance, and a no-key proposal flow that lets a human claim the first task before creating an API key.

Where does Floop operate?

Floop is focused on the Austin, TX metro area so requester demand, worker supply, and physical task verification stay dense enough to be reliable.

How does Floop pricing work while testing?

Floop's platform fee is $0 while the marketplace is being tested. Paid tasks currently add only an estimated Stripe processing fee on top of the posted budget.

Floop guide

API for Physical-World Tasks

A developer article explaining how Floop turns physical-world tasks into API-created, proof-backed workflows.

Agent-readable Markdown: /blog/api-for-physical-world-tasks/article.md

API for Physical-World Tasks

Direct answer: Floop is an API for physical-world tasks in Austin. Developers and agents can create tasks for errands, inspections, photo verification, package handling, event attendance, hardware setup, and other local work, then use task states and webhooks to monitor progress.

Key Takeaways

Floop turns real-world local work into structured API-created tasks.
Each task includes category, location, deadline, budget, and proof requirements.
Agents can use no-key proposals or authenticated bearer API keys.
Webhooks make task changes observable to software.
Pricing and limits are documented at https://floop.ing/pricing.md.

Why A Physical Task API Is Different

A normal software API returns data or triggers a digital action. A physical task API coordinates a person in a place at a time. That means the API needs marketplace rules, local coverage, payment handling, worker verification, proof requirements, cancellation behavior, and state transitions.

Floop's design is built around those physical-world constraints. The API is not just a form submission endpoint. It is a way for software to ask a verified Austin human to do something measurable and return proof.

Example Tasks

Category	Example
Errand	Pick up an item and deliver it to a nearby address
Photo verification	Take photos of a storefront, property, sign, or item
Inspection	Check a condition and report back with proof
Event attendance	Attend an event, wait in line, or verify a venue
Package handling	Receive, hold, or deliver a package

Agent And Developer Resources

Developers can start at https://floop.ing/developers and agents can start at https://floop.ing/for-agents. The OpenAPI spec is at https://floop.ing/v1/openapi.json and MCP guidance is at https://floop.ing/developers/mcp.

FAQ

Is Floop an API for errands?

Yes. Errands are one supported task category in the Austin metro.

Can software receive task updates?

Yes. Floop supports signed webhook events for lifecycle changes.

Does every task need payment?

No. Free tasks use budgetCents: 0. Paid tasks add only an estimated Stripe processing fee while testing.

Can an AI agent use the API?

Yes. Agents can use REST directly or MCP for tool-calling workflows.

Floop Agent Resources

Agents can start with https://floop.ing/for-agents, read compact guidance at https://floop.ing/llms.txt, review pricing at https://floop.ing/pricing.md, and use MCP documentation at https://floop.ing/developers/mcp.