PlanningHigh riskComparison recommended

AI Playbook for Legislative Testimony Preparation

A state agency director has been called to testify before a legislative oversight committee regarding a program that experienced a $12M cost overrun and a 14-month schedule delay. Media coverage has been hostile. The hearing is in 10 days.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A state agency director has been called to testify before a legislative oversight committee regarding a program that experienced a $12M cost overrun and a 14-month schedule delay.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Legislative Testimony Preparation".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Program status report and cost overrun analysis
  • Media coverage summary (past 3 months)
  • Legislative committee's stated questions
  • Agency's internal root cause analysis
  • Legal counsel's guidance on testimony risks

Attachments: Documents (Documents)

The Prompt

You are a communications and policy specialist preparing a state agency director for hostile legislative testimony. I am attaching:

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

Produce:
1. Analyze the cost overrun and schedule delay: what were the actual causes, which were within the agency's control, and which were external?
2. Identify the hardest questions the committee will ask and develop honest, accurate, non-defensive answers.
3. Develop the director's opening statement: take responsibility for what went wrong, explain what was learned, and present a credible recovery plan.
4. Identify the answers that create legal liability and how to answer truthfully without those admissions.
5. Tell me the 3 most important messages the director must leave with the committee and how to return to them regardless of how hostile the questions get.

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

What to expect

  • Cost overrun root cause analysis
  • Hard question anticipation with honest answers
  • Opening statement draft
  • Legal liability avoidance guidance
  • 3 key messages and bridging technique

Review before you act

  • Validate this output against source files before relying on it: Analyze the cost overrun and schedule delay: what were the actual causes, which were within the agency's control, and which were external?.
  • Validate this output against source files before relying on it: Identify the hardest questions the committee will ask and develop honest, accurate, non-defensive answers.
  • Validate this output against source files before relying on it: Develop the director's opening statement: take responsibility for what went wrong, explain what was learned, and present a credible recovery plan.
  • Validate this output against source files before relying on it: Identify the answers that create legal liability and how to answer truthfully without those admissions.
  • 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 Legislative Testimony Preparation, 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 cost overrun root cause analysis; hard question anticipation with honest answers; opening statement draft; legal liability avoidance guidance. 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.

GovernmentPolicy and GrantsPlanningHighDocuments

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.