Review an AI plan through six questions covering evaluation examples, error targets, fallback behavior, regulatory risk, model choices, costs, and hiring. Produce a structured verdict with gaps to address and three concrete next steps.
中文简介正在准备中。当前显示英语简介。
/c-level-agents:caio-review [plan] — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, cost economics, or AI hiring. Use when shipping an AI feature without an eval set, choosing between API, fine-tune, and self-hosted, or classifying a use case under the EU AI Act.
安装前可以查看交给 AI 代理的指令内容。
Command: /c-level-agents:caio-review <plan>
The eval-demanding CAIO pressure-tests any plan that involves AI. Six questions before any AI feature ships, any multi-year vendor commitment, or any AI team expansion.
No eval set = no ship. Before any AI feature deploys, define the eval criteria.
Every AI feature has a failure mode. Plan for it.
Run ai_risk_classifier.py if any EU residents are affected OR domain is regulated.
Run model_buildvsbuy_calculator.py for the specific use case.
Run ai_cost_economics.py for the workload.
Map AI capability to specific role. Founders confuse AI engineer / ML engineer / research scientist.
# 1. Model selection check
python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-ai-officer-advisor/scripts/model_buildvsbuy_calculator.py use_case.json
# 2. Regulatory classification
python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-ai-officer-advisor/scripts/ai_risk_classifier.py use_case.json
# 3. Cost projection
python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-ai-officer-advisor/scripts/ai_cost_economics.py workload.json
# CAIO Review: <plan>
**Date:** YYYY-MM-DD
## The Decision Being Made
[one sentence — which CAIO decision: model selection | risk classification | economics | next hire]
## Eval Discipline
- Eval set committed: yes/no
- SLO defined: <metric> < <threshold>
- Fallback behavior: <one line>
## Model Selection (if applicable)
- Recommended: API / FINE_TUNE / BUILD
- 3-year TCO: $X (chosen path) vs $Y (alternatives)
- Breakeven: <volume>
## Risk Classification (if applicable)
- EU AI Act tier: PROHIBITED / HIGH / LIMITED / MINIMAL
- Conformity assessment required: yes/no
- US state triggers: [list]
- Required controls open: N
## Cost Economics (if applicable)
- Monthly cost at current volume: $X
- Breakeven for self-hosted migration: <volume>
- Migration cost if applicable: $X (3-6 months)
## Org (if applicable)
- Next hire: <role>
- Why this, not the alternative: <one line>
- Prerequisite hires in place: yes/no
## Verdict
🟢 SHIP | 🟡 SHARPEN | 🔴 BLOCK
## Next Steps
[3 concrete actions]
/c-level-agents:cdo-review — for any training-data implications/c-level-agents:gc-review — for AI vendor contracts, output liability, training-data licensing/c-level-agents:ciso-review — for prompt injection / jailbreak / training-data poisoning threat model/c-level-agents:cfo-review — for multi-year vendor or GPU commitment TCOcs-chro-advisor agent — for AI team hires (comp, ladder, leveling)/c-level-agents:decide — log the verdict/c-level-agents:freeze 60 — on multi-year AI commitmentscs-caio-advisorchief-ai-officer-advisor${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-data-officer-advisor/ (training data rights, data strategy)Version: 1.0.0
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Audit web applications for accessibility issues against WCAG 2.2 Level A and AA, the web accessibility standards. Get framework-specific code fixes, contrast checks, verification steps, and reports, with options for automated checks in development pipelines.
中文简介正在准备中。当前显示英语简介。
Plan A/B tests that compare page variations, from headlines to pricing layouts. Define a hypothesis, choose success metrics, calculate sample size and duration, and prepare launch checks and results reports to support decisions.
中文简介正在准备中。当前显示英语简介。
Create paid ad headlines and body copy tailored to each platform's character limits. Use existing performance data to develop variations, explore new messaging angles, and check copy for length, quality, and potential rejection risks.
中文简介正在准备中。当前显示英语简介。
Review code changes from three critical perspectives: production failures, maintainability, and security. Get a consolidated report that ranks findings by severity and provides merge guidance, helping examine assumptions that an ordinary self-review may overlook.
中文简介正在准备中。当前显示英语简介。
Audit and improve content intended for citation in AI answers. Review evidence, author information, and structure, generate revised content and structured metadata, and keep a local record of observed citations across AI services.
中文简介正在准备中。当前显示英语简介。
Create signed records for consequential agent actions such as deployments, deletions, and payments. Decide which actions need evidence, record the agent, action, target, and policy, then verify the resulting certificate offline to detect later changes.
中文简介正在准备中。当前显示英语简介。