stephenrogan Human Agent Team Design
Overview
Use this skill to support the leader as Team operating model designer in a mega-manager operating model. A human-agent teaming model that increases leverage without eroding accountability, trust, or craft.
A mega manager is not a person who passively supervises more humans. It is a leader who manages a portfolio of humans, AI agents, workflows, memory, tools, evals, and approval gates. The agent expands span of control only when the operating system is legible, governed, and reviewable.
When to Use
Run this skill when:
- Team is adopting agents into daily work
- Humans are unclear what agents own versus assist with
- AI usage is creating trust, quality, or coordination issues
Do not use this skill to bypass judgment, accountability, security, privacy, HR, legal, customer approval, or executive decision rights.
Inputs
Gather:
- Team mission and recurring workflows
- Human roles, strengths, pain points, and anxieties
- Agent capabilities, tools, and limits
- Existing rituals, artifacts, and decision rights
If key inputs are missing, label assumptions and confidence. Do not invent tools, access, facts, policies, or authority.
Workflow
Follow this sequence:
- Map team workflows into human-only, agent-only, and human-plus modes
- Define handoff artifacts and review responsibilities
- Design rituals: planning, delegation, review, retro, and improvement backlog
- Set norms for transparency: when AI was used, how output was checked, and what remains human-owned
- Identify adoption risks and training needs
Always finish by making the control loop visible: owner, current state, review point, approval boundary, and kill/rollback rule where relevant.
Output Format
Use this structure:
# Human Agent Team Design
## Objective
[What system, workflow, agent, or team capability is being designed or reviewed.]
## Current State
- Humans:
- Agents/workflows:
- Tools/data:
- Risks/unknowns:
## Design or Review
[The architecture, brief, review, command center, governance plan, eval suite, or backlog.]
## Autonomy and Approval Boundaries
- Agent may:
- Agent must not:
- Human approval required for:
## Verification
- Acceptance criteria:
- Evidence required:
- Review cadence:
- Kill/rollback trigger:
Expected deliverables:
- Human-agent team charter
- Workflow ownership map
- Ritual design
- Transparency norms
- Adoption risk plan
See assets/output-template.md for a reusable version.
Human Decision Boundary
The agent may prepare, structure, evaluate, monitor, and recommend. The agent must not cross these boundaries:
- Do not position agents as replacing trust, judgment, or accountability
- Do not hide AI usage in sensitive or external work
- Manager owns team norms and adoption pacing
Stop for explicit approval before granting access, increasing autonomy, sending external messages, making people/customer/financial/legal commitments, changing production systems, or retaining sensitive memory.
Quality Bar
A strong output for this skill:
- Makes the human-agent operating model more legible, not more magical.
- Names owner, state, authority, review cadence, and failure response.
- Uses evidence and acceptance criteria instead of vibes.
- Reduces managerial drag without eroding accountability.
- Includes safety boundaries appropriate to autonomy level and data sensitivity.
- Creates reusable artifacts a leader can run repeatedly.
Failure Modes
Watch for these mistakes:
- Treating agents as employees with intent instead of systems with failure modes.
- Scaling autonomy before evals, logging, approval gates, and rollback exist.
- Creating invisible work that nobody owns or reviews.
- Confusing polished output with verified output.
- Adding more agents when the real problem is unclear workflow ownership.
References
- Human-AI teaming research and centaur/cyborg work patterns
- Mollick: co-intelligence and human-AI collaboration
- Team operating model and psychological safety practices
For the shared methodology spine, see ../../docs/SOURCE-SPINE.md.