{"slug": "parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks", "title": "PARMAN: testing approval and evidence retrieval for agent-to-human tasks", "summary": "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.", "body_md": "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.\n\nThe 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.\n\nOne 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.\n\nIntegration guide: [PARMAN](https://parman.ai/agent-task-guide)\n\nWe would value feedback from agent builders on three questions:\n\nWe 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.", "url": "https://wpnews.pro/news/parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks", "canonical_source": "https://discuss.huggingface.co/t/parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks/182795#post_1", "published_at": "2026-10-02 12:16:42+00:00", "updated_at": "2026-10-02 12:39:00.508812+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools"], "entities": ["PARMAN", "MCP", "submit_human_task", "get_human_task", "Botswana"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks", "markdown": "https://wpnews.pro/news/parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks.md", "text": "https://wpnews.pro/news/parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks.txt", "jsonld": "https://wpnews.pro/news/parman-testing-approval-and-evidence-retrieval-for-agent-to-human-tasks.jsonld"}}