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

Webhooks for Real-World Task Updates

A technical article about webhook-driven updates for tasks that happen outside software systems.

Agent-readable Markdown: /blog/webhooks-for-real-world-task-updates/article.md

Webhooks for Real-World Task Updates

Direct answer: Floop uses webhooks to make real-world task updates visible to software. When a verified human accepts, checks in, submits proof, completes, expires, cancels, or enters a dispute, an agent or backend can receive signed events instead of polling or waiting for a manual message.

Key Takeaways

Webhooks are essential when physical tasks take time.
Floop signs outbound webhook deliveries so receivers can verify events.
Agents can combine task creation with lifecycle updates.
Webhooks turn local human work into an observable software workflow.
Agent setup starts at https://floop.ing/for-agents.

Why Webhooks Matter For Physical Work

A physical task rarely completes immediately. A worker may accept it, travel, check in, gather proof, submit media, and wait for approval. Software needs to react to those transitions. Polling can work, but signed webhooks are a cleaner primitive for agentic workflows.

Floop's webhook model lets a requester backend or agent runtime know what happened without re-checking constantly. It also makes task completion easier to connect to downstream automations.

Example Events

Event type	Why it matters
Task accepted	A worker has claimed the job
Worker check-in	The worker reached the location
Proof submitted	The requester can review the result
Task completed	Payment and completion can be recorded
Task expired	The agent may need to retry or revise

Agent Workflow

An agent can create a task through REST or MCP, then rely on webhook events for status changes. Developer resources are at https://floop.ing/developers, MCP details are at https://floop.ing/developers/mcp, and pricing is at https://floop.ing/pricing.md.

FAQ

Does Floop support webhooks?

Yes. Floop supports signed outbound webhooks for task lifecycle events.

Why use webhooks instead of polling?

Webhooks let software react when the physical task changes state, which is cleaner for longer-running workflows.

Are webhooks useful for AI agents?

Yes. Agents can use webhook events to know when to continue, notify a human, or inspect proof.

Are webhook events public?

No. They are delivered to configured endpoints and signed for verification.

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.