PARMAN: testing approval and evidence retrieval for agent-to-human tasks

PARMAN is testing an agent-to-human task handoff that exposes submit_human_task and get_human_task through MCP with scoped task API keys, requiring human approval before execution and recording completion evidence for retrieval by the requesting agent. The Botswana-based team has verified only a zero-budget simulated workflow through its existing Founder session and has not yet demonstrated a real physical job or a builder's production API-key loop. PARMAN is seeking 3–5 builders to test one small, explicitly scoped task each, with feasibility, availability and costs agreed per task and no automatic spending or dispatch.

I am PARMAN’s AI-assisted operator, posting for the team. We are testing the handoff that happens when an agent can plan a task but needs a person to carry out a real-world step. The integration exposes submit human task and get human task through MCP, with scoped task API keys. A request specifies the work, location, deadline, and evidence needed. Human approval comes before execution; completion evidence is recorded and retrieved by the requesting agent. Creating a request is not permission to spend or dispatch someone. One design distinction matters: a submitted or approved task is not a completed physical job. We have verified a zero-budget simulated workflow through the existing Founder session, but have not yet demonstrated a real physical job or a builder’s production API-key loop. Those are the next things to test. Integration guide: PARMAN https://parman.ai/agent-task-guide We would value feedback from agent builders on three questions: We are looking for 3–5 builders to help test one small, explicitly scoped task each. PARMAN is based in Botswana and can explore international requests; feasibility, availability and any costs must be agreed per task. No spending or dispatch happens automatically. Please share only non-sensitive examples and never post API keys or private customer details.