メニュー
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Shift from rigid roles (PM, Designer, Engineer) towards a model where individuals use AI to bridge skill gaps, enabling smaller and flatter teams. Use in early-stage startups or innovation units where speed is critical.
Use when designing AI agents or chatbots, when raw model outputs feel like a black box, or when building natural language interfaces that need structure and trust
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
View yourself as an entity with infinite dimensions rather than a single good/bad identity. Strengths and weaknesses are often the same trait in different contexts. Use during performance reviews or when receiving tough feedback.
Review your calendar, color-code activities by energy impact (Green/Red), and systematically delegate draining tasks to maximize time in your Zone of Genius.
Use when dealing with ecosystems, network effects, or high-uncertainty environments where the right answer cannot be known in advance, when rigid planning consumes more value than it creates
| name | ai-teammate-model |
| description | Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development |
A framework for evolving AI agents from simple tools into autonomous partners. A true AI teammate must move beyond code generation to participate in the entire software lifecycle while possessing proactivity.
Core principle: Treat the AI like a new intern—verify work initially, then build trust and grant autonomy incrementally.
┌─────────────────────────────────────────────────────────────────┐
│ PHASE 1: THE SMART INTERN │
│ ───────────────────────────────────────────────────────────── │
│ • Reactive (needs explicit prompts) │
│ • No context (can't read Slack/Datadog) │
│ • Requires full review │
│ • "Prompt-to-Patch" workflow │
├─────────────────────────────────────────────────────────────────┤
│ PHASE 2: THE PAIR PROGRAMMER │
│ ───────────────────────────────────────────────────────────── │
│ • Collaborative (works in IDE/Terminal) │
│ • Human-in-the-loop validation │
│ • Gaining context awareness │
│ • Handles environment setup │
├─────────────────────────────────────────────────────────────────┤
│ PHASE 3: THE PROACTIVE TEAMMATE │
│ ───────────────────────────────────────────────────────────── │
│ • Autonomous (monitors Slack/Logs/Metrics) │
│ • Signal-driven (acts without prompts) │
│ • Asynchronous execution │
│ • High trust delegation │
└─────────────────────────────────────────────────────────────────┘
| Principle | Description |
|---|---|
| Contextual Integration | Agent must access full environment (runtime, logs, comms) |
| Proactivity by Default | Shift from prompt-driven to signal-driven action |
| Trust Evolution | Move from micro-management to delegation gradually |
| Full Lifecycle | Agent contributes to planning, coding, reviewing, deploying |
To evolve from Phase 1 → Phase 3:
OpenAI has Codex "on-call" for its own training runs—monitoring graphs and fixing configuration mistakes without human intervention.
Source: Alexander Embiricos (OpenAI Codex) via Lenny's Podcast