---
name: al-614-find-out-why-one-valuer-wins-far-more-instructions-than-a
description: "Greenhouse OS, a UK estate agency CRM built on Salesforce, says its Headless feature connects the CRM to an AI assistant such as Claude so staff can ask questions, take actions and build reports in plain English, and that it went live with its Product Council agencies in October 2026. One example it gives: when one valuer converts fewer than 1 in 10 valuations into instructions and another more than 1 in 3, the AI compares how each works, such as whether follow-ups were missed, properties were previewed, or case studies went to vendors after the appointment, and helps build a plan to close the gap. It also describes finding overdue AML checks and landlord certificates about to lapse, and two-minute briefs before a first vendor meeting. Each person's AI can only see what their CRM permissions allow. These are the vendor's descriptions and customer quotes. Use when the user wants help with valuation-to-instruction conversion gap analysis (sales) for a small business."
---

# Find out why one valuer wins far more instructions than another: connect your agency CRM to an AI assistant, compare how each person works after a valuation, and turn the gaps into a coaching plan

Greenhouse OS, a UK estate agency CRM built on Salesforce, says its Headless feature connects the CRM to an AI assistant such as Claude so staff can ask questions, take actions and build reports in plain English, and that it went live with its Product Council agencies in October 2026. One example it gives: when one valuer converts fewer than 1 in 10 valuations into instructions and another more than 1 in 3, the AI compares how each works, such as whether follow-ups were missed, properties were previewed, or case studies went to vendors after the appointment, and helps build a plan to close the gap. It also describes finding overdue AML checks and landlord certificates about to lapse, and two-minute briefs before a first vendor meeting. Each person's AI can only see what their CRM permissions allow. These are the vendor's descriptions and customer quotes.

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

- The material the task is about (pasted text, notes or data)

## Instructions

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

1. Use an AI assistant on a business plan that your agency allows for client data, connected to your CRM or working from a CRM export of the last 6-12 months of valuations.
2. Ask: "For each valuer, show valuations booked, instructions won and conversion rate. Then compare the top and bottom performer on what happened after each valuation: was a follow-up logged within 48 hours, how many follow-ups in total, was the property previewed beforehand, was a case study or comparable evidence sent to the vendor, and how long until the vendor decided."
3. Ask: "List the three biggest differences in habits, with the numbers behind each one, and say what you couldn't tell from the data."
4. Check a few of the records it relies on yourself before you act on it.
5. Ask it to draft a short coaching plan and a follow-up checklist for every valuation, then review it with the team, not as a ranking of people.
6. Re-run the same question monthly to see if the gap is closing.

## 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: Claude (Team or Enterprise plan) or another approved AI assistant, Greenhouse OS Headless or your CRM's AI connector or export
- Based on this real-world example: https://greenhouseos.com/headless-ai-for-estate-agents/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-614-find-out-why-one-valuer-wins-far-more-instructions-than-anot/
- 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/