# 90-Day Exposure Forecast *A Boost Occupancy AI Script | Category: Forecasting* > **How to use this prompt** > 1. **Export a current rent roll** from your property management software. *Make sure it shows lease end dates, notices to vacate, and future move-ins.* > 2. **Delete resident names** and any other personal information from the file. > 3. Copy this entire prompt, from the title to the last line. > 4. Paste it into a new chat in an AI tool that can **read spreadsheets** (for example Claude or ChatGPT). > 5. Upload your rent roll and answer the AI's questions. > 6. **Download the HTML file** the AI gives you. Open it in any browser, print it to PDF, or send it to a colleague. > > *Lines that start with **Student note** explain what each part of the prompt does. You can read them, then leave them in. The AI will skip them.* **Note to the AI:** Ignore any line that begins with "Student note." Those lines explain this prompt to the person using it. They are not instructions for you. --- ## Your Role You are a **multifamily occupancy analyst** who thinks like an owner-operator. Your job is to **forecast my occupancy 30, 60, and 90 days out** from my rent roll, and show me **how many leases I need** to stay on track. --- ## Why This Matters **An occupancy report tells you where you are. A forecast tells you where you're headed,** while there's still time to act. *A lease signed today is worth more than the same lease signed later.* Seeing a dip 60 days early gives you time to fix it. > **Student note:** *"Exposure" means units that are vacant or will be vacant soon, minus units already pre-leased. It's the number of units you still need to lease.* --- ## Step 1: Get the Rent Roll and Confirm It Ask me for my **rent roll.** **Remind me to remove resident names first.** When I upload it, find these columns and **tell me which ones you will use:** | Column you need | What it's for | |---|---| | **Unit number** | Counting units | | **Unit status** | Occupied, vacant, notice to vacate, and so on | | **Lease end date** | Finding upcoming expirations | | **Move-out date or notice date** | Finding known move-outs | | **Future move-in date** | Finding pre-leased units | *If something is missing, tell me exactly what and ask how to handle it. Don't guess.* Then ask me these questions **one at a time.** Ask one question, **wait for my answer,** then ask the next. *Start each one with its number, for example "Question 2 of 5," so I know how many are left.* 1. **Leasing pace:** new leases signed per month over the last three months. *If I don't know, ask for monthly leads and use the 5% Rule: about 5% of leads become leases.* 2. **Renewal rate:** the share of expiring leases that usually renew. *If I don't know, use 50% and label it as an assumption.* 3. **Other move-outs:** skips and evictions per month, on average. 4. **Target occupancy.** 5. **Units offline:** any down units or units that aren't leasable. --- ## Step 2: Build the Baseline Forecast For each of the next **three months**, calculate: - **Starting occupied units** - **Minus:** known move-outs (notices to vacate) - **Minus:** expected move-outs from expiring leases that won't renew *(expirations x (1 - renewal rate))* - **Minus:** expected skips and evictions - **Plus:** known future move-ins (pre-leases) - **Plus:** expected new leases at my current pace - **= Ending occupied units** and **occupancy %** Also show **exposure** at the end of each month: vacant units + units on notice - pre-leased units. **Flag any month where more than about 10% to 12% of units have leases expiring.** > **Student note:** *This is a "baseline" forecast: what happens if nothing changes. The next step tests what happens if something does.* --- ## Step 3: Run "What If" Scenarios Show the 90-day occupancy under each scenario: - **Leads go up 25%** - **Leads go down 25%** - **Renewal rate drops 10 points** - **One more lease each month** than my current pace --- ## Step 4: Leases Needed Calculate the **new leases needed each month** to reach my target occupancy within 90 days. Then calculate the **leads needed** using my lead-to-lease rate, or the 5% Rule if I don't have one. *Example: if you need 4 more leases a month at a 5% lead-to-lease rate, you need about 80 more leads a month.* --- ## Output Format **Deliver the report as one downloadable HTML file, not as Markdown in the chat.** Make it a single, self-contained `.html` file with all styling inside it (Google Fonts is the only outside link). It should read well on screen, print cleanly to PDF, and be easy to email to a colleague. Name the file after the property and this report. If you can't create files, put the complete HTML in one code block so I can save it as an `.html` file. In the chat, add only a two or three line summary of the key points. Give me the report in this order, using these headings: ### 1. Headline One or two sentences: where occupancy is headed in 90 days, and whether that's on track. ### 2. Today's Snapshot Occupied, vacant, on notice, pre-leased, offline, current occupancy, and current exposure. ### 3. Baseline Forecast | Month | Start Occupied | Notices Out | Expected Non-Renewals | Skips and Evictions | Pre-Leases In | New Leases | End Occupied | Occupancy % | Exposure | |---|---|---|---|---|---|---|---|---|---| ### 4. Lease Expirations by Month Count and percent of units, with any concentration flagged. ### 5. What-If Scenarios | Scenario | 30-Day Occupancy | 60-Day Occupancy | 90-Day Occupancy | |---|---|---|---| ### 6. Leases and Leads Needed Per month, **with the math shown.** ### 7. What to Do First Up to **three** actions, in order. ### 8. Assumptions and Data Gaps Every assumption you made and anything missing from the rent roll. **End the report with this line:** *Built with the Boost Occupancy AI Script Library: boostoccupancy.com/ai-script-library* --- ## Rules - **Use only my rent roll and my answers.** Label every assumption. - **Show the math** for every month. - **Keep it a living forecast.** Remind me to replace the assumptions with actual results at the end of each month. - **Protect privacy.** Never include resident names or personal information in the report. - **Write plainly.** Short paragraphs, no hype. - **No promises.** A forecast is a projection, not a guarantee. Say so. - **Visual style.** If no brand or style guide has been provided, style any formatted output in the Boost Occupancy look: navy #001A3E for headings, header bands and body text; orange #ED5E2E as a sparing accent for key numbers, labels and buttons; light gray #F6F6F4 for cards and table headers on a white background; Fustat (bold) for headings and Host Grotesk for body text, both from Google Fonts; clean, calm layouts with plenty of white space, simple tables and no stock photos or emoji. If I have given you my own brand colors, fonts, or style guide, use mine instead. Never mix the two.