---
name: al-555-start-the-day-with-who-s-actually-house-hunting-have-your
description: "What buyers view, save and search in an agent's home search app often says more about their real plans than what they said at the first meeting, but few agents dig through app dashboards every morning. On Oct 30, 2026, HomeStack announced HomeStack MCP, which connects ChatGPT, Claude and other compatible assistants to an agent's branded home search app. Its example morning routine: ask which clients were most engaged in the past week, ask what a client like 'Sarah' has been looking at, have the AI build a collection of five matching listings with a note on why each fits, and prepare it to share, with the agent's review and confirmation where required. It is available on HomeStack Pro and Enterprise accounts (Plus can add it). Agents on other platforms can do a manual version from their CRM or IDX activity export. Use when the user wants help with home search app engagement signals (sales) for a small business."
---

# Start the day with who's actually house hunting: have your AI check which clients were most active in your home search app this week, what they keep viewing and saving, and prepare a matching shortlist for each

What buyers view, save and search in an agent's home search app often says more about their real plans than what they said at the first meeting, but few agents dig through app dashboards every morning. On Oct 30, 2026, HomeStack announced HomeStack MCP, which connects ChatGPT, Claude and other compatible assistants to an agent's branded home search app. Its example morning routine: ask which clients were most engaged in the past week, ask what a client like 'Sarah' has been looking at, have the AI build a collection of five matching listings with a note on why each fits, and prepare it to share, with the agent's review and confirmation where required. It is available on HomeStack Pro and Enterprise accounts (Plus can add it). Agents on other platforms can do a manual version from their CRM or IDX activity export.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Client
- CHECK

## Instructions

Do the task below with the user's inputs in place of each [bracket].

1. Connect your home search app or CRM to your AI if it has a connector (e.g. HomeStack MCP), or export last week's client activity (logins, listings viewed, saved, searches, price range) as a CSV.
2. Ask your AI: "Which [10] clients were most active in the last 7 days? For each, summarise what changed: new areas, price range moving up or down, homes viewed more than once, new saved searches."
3. For your top 3: "Based on what [client] has actually been viewing and saving, find [5] current listings that fit, and write one line for each on why it could suit them. Mark anything you're unsure about as [CHECK]."
4. Then: "Draft a short, personal text for each client mentioning the pattern you noticed ('you've looked at a lot of homes with big yards') and the shortlist, ending with an easy question about a viewing."
5. Check each listing is still active, review and send the messages yourself, and note who replied so you can see which signals actually mean someone is ready to move.

## Safety checks (share these with the user)

- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: HomeStack MCP, ChatGPT, Claude, CRM, Follow Up Boss
- Based on this real-world example: https://www.homestack.com/blog/introducing-the-supercharged-homestack-ai-your-app-your-data-your-ai
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-555-start-the-day-with-who-s-actually-house-hunting-have-your-ai/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/