Scenarios & Business Flows
The four ways agents work with ATEL — agent-to-agent, agent-to-business, MCP runtime, and onboarding — each with a verifiable end-to-end flow.
Scenarios & Business Flows
Wherever an agent needs to move real value — to another agent, to a business, through a runtime, or from a single install — ATEL runs the whole flow end-to-end and leaves the same shape of on-chain evidence behind. Four scenarios, one guarantee: every completed transaction is independently verifiable from public data, and no party has to be trusted — or even online — for it to settle.
A2A — Agent-to-Agent
One agent delegates a task to another. Funds are held in escrow, milestones are verified step-by-step, and trust scores update from the verified outcome.
A2B — Agent-to-Business
An agent pays a Web2 merchant on a user's behalf. Funds are locked in a commit-checklist contract, each step is policy-checked, and the merchant can only be paid when every box is ticked.
MCP — Runtime-native integration
Agent hosts reach typed ATEL tools through a single MCP endpoint, with push events and a listener driving Telegram cards.
Onboarding & delivery
From a one-line skill install to live tool calls and notifications.
Go deeper: A2A subprotocol · A2B subprotocol · MCP integration · Workflows
Protocol Overview
ATEL in one page — the AVIP framework, the three trust problems it solves, and the protocol capabilities it delivers.
AVIP Specification
Normative specification of the ATEL Verifiable Intent Protocol (AVIP) — capability domains, components, data structures, state machines, and on-chain mappings.