Should your agent workflow use a protocol at all?

Описание и применение

Решение о применении протокола в работе агента требует оценки сложности задачи через git‑сигналы, а не через самовосприятие. Протокол Agateon вычисляет уровень церемонии (тонкая, стандартная, полная) и блокирует задачи, если заявленный уровень ниже рассчитанного.

Задача

Deciding whether to add an orchestration layer to an agent workflow can be costly if done incorrectly – too much process wastes agent time, too little leads to incomplete work.

Результат

In a sample of 37 tasks, the protocol added a median of 21 hours of calendar time but only 3 real gate blocks, demonstrating that gates rarely stop work but provide coverage of hidden failures.

Рабочий процесс

• 1. Stage changes for the task
• 2. Run agate-risk-score.py to compute tier and evidence lines
• 3. Declare desired ceremony depth (thin/standard/full) in task metadata
• 4. Gate checks declaration against computed tier – blocks if too low
• 5. Execute task phases, generating artifacts and logs
• 6. Review gate outcomes and retry if necessary

Доказательства

The risk score exists because ceremony depth used to be self‑reported, and self‑reported complexity drifts toward whatever the agent thinks you want to hear.

Источник

Across 37 tasks in agate-workspace/tasks/: median wall‑clock span ~21 hours, 13 commits, ~6,700 phase artifact lines.

Источник

Of 119 gate runs recorded, 115 ended in the pass code for that phase, 3 exited 1 – real blocks.

Источник