Risk AssessmentHigh riskComparison recommended

AI FOIA Response Strategy Playbook

A federal agency received a FOIA request for all internal communications regarding a controversial policy decision. The request covers 3 years of emails across 14 senior officials. The responsive documents include deliberative process materials, law enforcement sensitive information, and personal information about private individuals.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A federal agency received a FOIA request for all internal communications regarding a controversial policy decision.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "FOIA Response Strategy".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • FOIA request letter
  • Preliminary document inventory (volume estimate by official and date range)
  • FOIA exemption applicability analysis (Exemptions 5, 7, 6)
  • Agency FOIA regulations and processing procedures
  • Requester profile (media organization with prior litigation history)

Attachments: Documents (Documents)

The Prompt

You are a federal FOIA officer developing a response strategy for a complex, politically sensitive FOIA request. I am attaching:

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

Produce:
1. Assess the volume and complexity: is a 20-day response feasible or should the agency invoke unusual circumstances?
2. Identify the applicable exemptions for each document category: Exemption 5 (deliberative process), Exemption 7(E) (law enforcement), Exemption 6 (personal privacy) — and assess each exemption's strength.
3. Assess the foreseeable harm standard: even if an exemption applies, can the agency withhold without articulating specific foreseeable harm?
4. Identify the litigation risk: what are the most likely legal challenges given this requester's history?
5. Tell me the production strategy: what to release, withhold, redact, and how to sequence the rolling production to manage political risk.

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

What to expect

  • Volume and timeline assessment
  • Exemption applicability matrix by document category
  • Foreseeable harm standard analysis
  • Litigation risk assessment
  • Production strategy with sequencing

Review before you act

  • Validate this output against source files before relying on it: Assess the volume and complexity: is a 20-day response feasible or should the agency invoke unusual circumstances?.
  • Validate this output against source files before relying on it: Identify the applicable exemptions for each document category: Exemption 5 (deliberative process), Exemption 7(E) (law enforcement), Exemption 6 (personal privacy) — and assess each exemption's strength.
  • Validate this output against source files before relying on it: Assess the foreseeable harm standard: even if an exemption applies, can the agency withhold without articulating specific foreseeable harm?.
  • Validate this output against source files before relying on it: Identify the litigation risk: what are the most likely legal challenges given this requester's history?.
  • 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 FOIA Response Strategy, 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 volume and timeline assessment; exemption applicability matrix by document category; foreseeable harm standard analysis; litigation risk assessment. 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.

GovernmentOversight and RecordsRisk AssessmentHighDocuments

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.