The FNMA AI Lender Letter kit, run as a Project + Skill

Set it up (with the kit)

1. 1 Turn on Code execution & install the Skill

   Settings → Capabilities → turn on Code execution. Then Settings → Customize → Skills → + → Upload a skill → pick fnma-ai-lender-letter-skill.zip → toggle it ON.

   Need to see exactly where these buttons are? Follow the screenshot-by-screenshot guide to installing a Skill.

2. 2 Start a new Project

   Name it FNMA AI Lender Letter. Open a new chat window in the Project and upload roughly 75 pages of policies and procedures (100-page limit per chat). Repeat until all your policies and procedures are uploaded to chats in your FNMA AI Lender Letter Project.

3. 3 Create your AI System Inventory

   In your FNMA AI Lender Letter Project, paste the prompt below into every chat you uploaded your P&Ps into:

   Inventory this batch for the FNMA AI lender letter.

   Running the prompt invokes the Skill, which has the FNMA AI Lender Letter regulatory requirements hard-coded in it. Repeat in a fresh chat for every batch until all are done.

4. 4 Reconcile — fill the gaps

   Step 3 automagically extracts any AI-relevant software, processes, and workflow found in the P&Ps you inventoried — and the Skill can research specific systems and software to understand their AI capabilities. Open a new chat and upload any documents, contracts, or vendor lists you know are applicable to the FNMA AI Lender Letter. Then paste:

   Consolidate the findings from all my inventoried batches into one working list. Then show me the gaps — including the AI the P&Ps can't show (embedded vendor AI, shadow/employee AI, tools added since the P&Ps were written). I'm giving you our vendor inventory, contracts, and app list in the project — cross-reference them, surface any system no P&P showed, and validate the owners. Work through the high-risk gaps with me, then save a reconciled working-inventory.md to the project folder.

5. 5 Let AI help you make your AI Governance Policy

   Open a new chat in the FNMA AI Lender Letter Project, then copy and paste the below:

   Build the master AI System Inventory, Risk Assessment, and AI Governance Policy from working-inventory.md in the project folder. List every open CONFIRM grouped by who I need to ask and what to ask. Save the master policy as a file in the project folder.

6. 6 Push your AI Governance Policy to your P&Ps

   Back in each chat that contains P&Ps → paste:

   Update these P&Ps to match the master AI policy in the project folder.

7. 7 Change log (Appendix A)

   New chat → paste:

   Make the Appendix-A change log for the master AI policy and every P&P we changed.

That’s the whole run: inventory each batch → reconcile (where your vendor list, contracts, and app list go in, and the undocumented AI gets caught) → one synthesis chat → realign each batch → change log. Every output is a working draft for your review — not legal advice.

Setting up the Project: a few rules that make it work

This structure is good general practice for keeping P&Ps current, and it’s especially strong on a job as broad as the FNMA AI letter. A handful of habits keep it clean:

1. If you can, one P&P (or themed batch) per chat. Keep each chat focused so it does a thorough job and emits a clean FINDINGS block. If a single P&P runs over ~100 pages, split it across multiple chats rather than starving the context.
2. Inventory first, in its own chats. Then a separate gap-analysis chat. Finish scanning all batches before you reconcile — the gap analysis needs the whole picture to tell you which systems no policy documented.