AI Agency Reorganization Impact Assessment Playbook
A Cabinet-level agency is planning a reorganization that would consolidate 4 program offices into 2. The reorganization requires Congressional notification, workforce restructuring, and a transition plan. The acting administrator wants to complete the reorganization before the end of the fiscal year — 5 months away.
When to use this playbook
- Use this playbook when the decision looks like the situation above: A Cabinet-level agency is planning a reorganization that would consolidate 4 program offices into 2.
- It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Agency Reorganization Impact Assessment".
- Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.
What you'll need
- Current organizational chart and staffing data
- Proposed reorganization structure
- Congressional notification requirements under applicable statutes
- Workforce analysis (at-risk positions, union agreements, competitive service rules)
- Prior agency reorganizations in comparable federal agencies
Attachments: Documents (Documents)
The Prompt
You are an agency management consultant assessing a federal agency reorganization plan. I am attaching: Work only from the attached source files. If a conclusion is not supported, say so. Produce: 1. Assess the legal authority: what Congressional notification is required, and are there statutory constraints on consolidating these offices? 2. Identify the workforce impact: how many positions are affected, which have RIF protections, and what are the union agreement constraints? 3. Assess the mission risk during transition: what program continuity risks arise and how are statutory requirements maintained? 4. Build the transition timeline: what must happen before notification, during notification, and in implementation to meet the 5-month deadline? 5. Tell me the top 3 risks to the reorganization succeeding on schedule and the mitigation for each. Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.
What to expect
- Legal authority and Congressional notification assessment
- Workforce impact with RIF and union constraints
- Mission continuity risk assessment
- Transition timeline with phase milestones
- Top 3 risks with mitigation strategies
Review before you act
- Validate this output against source files before relying on it: Assess the legal authority: what Congressional notification is required, and are there statutory constraints on consolidating these offices?.
- Validate this output against source files before relying on it: Identify the workforce impact: how many positions are affected, which have RIF protections, and what are the union agreement constraints?.
- Validate this output against source files before relying on it: Assess the mission risk during transition: what program continuity risks arise and how are statutory requirements maintained?.
- Validate this output against source files before relying on it: Build the transition timeline: what must happen before notification, during notification, and in implementation to meet the 5-month deadline?.
- Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
- Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
- Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.
Why compare models on this
For Agency Reorganization Impact Assessment, running the same attachments across independent models is useful because the hard part is classification and completeness, not fluency. The workflow is already designed to surface legal authority and congressional notification assessment; workforce impact with rif and union constraints; mission continuity risk assessment; transition timeline with phase milestones. Those are comparison artifacts — they only exist if more than one model runs. Models disagree on exemption applicability, IG finding risk, and how aggressive a budget narrative can be. Those disagreements belong with counsel and the authorizing official.
See governed multi-model AI on your own prompt
Compare GPT-5, Claude, and Gemini side by side, with human review and a decision record built in.

