RecommendationHigh riskComparison recommended

AI Playbook for Agency Budget Justification Development

A federal agency's program office has a $240M budget request for the next fiscal year — an 18% increase over current year. OMB has historically cut requests above 12%. The program office has 60 days to submit its Congressional Justification and needs a compelling, defensible narrative.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A federal agency's program office has a $240M budget request for the next fiscal year — an 18% increase over current year.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Agency Budget Justification Development".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Current year budget and obligations data
  • Program performance metrics (prior 3 years)
  • OMB passback from prior year with cut rationale
  • Congressional committee priorities for this appropriations cycle
  • Comparable agency budget justification examples

Attachments: Documents (Documents)

The Prompt

You are a federal budget analyst developing a Congressional Justification for an 18% budget increase. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. Identify the performance evidence that most strongly supports the 18% increase: what outcomes have the additional funds produced?
2. Analyze the OMB passback: what concerns drove the prior year's cut, and how does this year's request address them directly?
3. Structure the CJ narrative: what order of arguments is most compelling to both OMB examiners and Congressional appropriators?
4. Identify the highest-risk line items: which elements of the 18% increase are most vulnerable to cut?
5. Tell me the fallback position: if OMB cuts to 12%, which program elements are protected and which are deferred.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

  • Performance evidence matrix
  • OMB passback response strategy
  • CJ narrative structure recommendation
  • High-risk line item defense plans
  • Fallback position at 12% cut with program impact

Review before you act

  • Validate this output against source files before relying on it: Identify the performance evidence that most strongly supports the 18% increase: what outcomes have the additional funds produced?.
  • Validate this output against source files before relying on it: Analyze the OMB passback: what concerns drove the prior year's cut, and how does this year's request address them directly?.
  • Validate this output against source files before relying on it: Structure the CJ narrative: what order of arguments is most compelling to both OMB examiners and Congressional appropriators?.
  • Validate this output against source files before relying on it: Identify the highest-risk line items: which elements of the 18% increase are most vulnerable to cut?.
  • 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 Budget Justification Development, 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 performance evidence matrix; omb passback response strategy; cj narrative structure recommendation; high-risk line item defense plans. 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.

GovernmentBudget and PerformanceRecommendationHighDocuments

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.