Your AI Action Plan

Draft a clear client reply from bullet points

Turn messy internal notes into a professional client message with the right tone and next step.

Client-message drafting is one of the easiest repeatable AI workflows for service roles.

Last verified 2026-04-20

Write a client message from these notes.
Client context: [CONTEXT]
Goal: [UPDATE / ASK / EXPLAIN / FOLLOW UP]
Notes: [PASTE NOTES]
Tone: professional, warm, and concise.
Include: clear answer, next step, owner, and deadline if relevant.

Create templates for your five recurring client moments

Build reusable prompts for status updates, requests, delays, explanations, and follow-ups.

Last verified 2026-04-20

Create five client-message templates for my role: status update, request for missing info, delay explanation, decision explanation, and follow-up. Each template should include placeholders, tone guidance, and a checklist for facts I must verify before sending.

Client context, draft, and QA checklist

Use AI to combine client context with a draft, then run a final check for tone, accuracy, and missing details.

Last verified 2026-04-20

Use this client context and draft to prepare a final message.
Context: [PASTE]
Draft: [PASTE]
Check for: factual accuracy, unclear promises, missing deadlines, tone risks, and next step. Return the revised message plus a send/no-send checklist.

Client communication style guide

Create a role-specific guide that keeps AI-drafted client messages consistent, careful, and easy to review.

Last verified 2026-04-20

Build a client communication style guide for [ROLE / COMPANY]. Include: approved tone, banned phrases, claims that require review, escalation triggers, examples of good messages, and a checklist before sending AI-assisted messages.

Ask for trends and outliers in plain English

Paste a small table or summary and ask AI to identify what changed, what looks unusual, and what needs review.

Last verified 2026-04-20

Analyze this data for trends, outliers, and practical next steps. Return: 1. top 5 findings, 2. possible explanations, 3. questions to verify, 4. recommended next actions. Do not assume causes without evidence.

Data:
[PASTE]

Use Copilot in Excel for spreadsheet insights

Ask questions about tables, formulas, filters, summaries, trends, and outliers inside the spreadsheet where the data already lives.

Last verified 2026-04-20

In this workbook, analyze [TABLE/RANGE] and answer: What changed most, what looks unusual, which rows need attention, and what chart or pivot would best explain the result?

Analyze in Sheets, explain in AI, write the memo

Use spreadsheet AI for calculations and charts, then use a writing model to turn the findings into a decision-ready explanation.

Last verified 2026-04-20

Use these spreadsheet findings to write a decision memo. Include: headline insight, supporting numbers, likely drivers, caveats, recommended action, and what data should be checked next.

Findings:
[PASTE]

Build a recurring analysis checklist

Create a role-specific checklist that makes every weekly or monthly analysis consistent, auditable, and easier to delegate.

Last verified 2026-04-20

Create a recurring analysis checklist for [DATA TYPE]. Include: required inputs, cleaning checks, metrics to calculate, outlier rules, interpretation questions, caveats, and the final memo format.

Draft the scheduling email and agenda together

Use AI to write a concise scheduling message that includes purpose, time options, prep request, and agenda.

Scheduling messages are a common repetitive communication task across support, sales, HR, and admin roles.

Last verified 2026-04-20

Write a scheduling email for [MEETING PURPOSE].
Participants: [WHO]
Time options: [OPTIONS]
Duration: [LENGTH]
Prep needed: [PREP]
Tone: [FRIENDLY / DIRECT / FORMAL]
Include a 3-bullet agenda and a clear reply request.

Use Calendly to remove back-and-forth

Pair a booking link with an AI-written context note so the meeting gets scheduled and framed in one message.

Last verified 2026-04-20

Write a short message that shares my booking link and explains the purpose of the meeting.
Booking link: [LINK]
Purpose: [PURPOSE]
Who should attend: [ROLES]
What to prepare: [PREP]
Keep it under 120 words.

Booking link, intake questions, and prep brief

Collect context before the meeting and use AI to turn responses into a prep note for everyone involved.

Last verified 2026-04-20

Create intake questions for a [MEETING TYPE] booking page. Then write a prep brief template that summarizes the answers into: context, goal, risks, decisions needed, and agenda.

Meeting routing playbook

Create rules that determine which meetings should happen, who attends, what prep is required, and what can be handled async.

Last verified 2026-04-20

Build a meeting routing playbook for [TEAM / ROLE]. Include: meeting types, when to book vs handle async, required attendees, intake questions, agenda templates, prep checklist, and follow-up owner.

Draft any email in 30 seconds with a single prompt

The most widely adopted AI habit in professional work. Start with one reusable email prompt.

Common first-step workflow for knowledge workers using AI.

Last verified 2026-04-20

Write a [TYPE - cold outreach / follow-up / proposal / status update] email.
From: [YOUR ROLE] at [COMPANY]
To: [RECIPIENT ROLE] at [THEIR COMPANY]
Context: [1-2 sentences of background]
Goal: [what you want them to do]
Tone: [professional / friendly / direct]
Length: [short = 3 sentences / medium = 1 short paragraph / full = structured email]

Build a personal prompt library for your 5 most common email types

Save your top prompts in Notion or a doc. One click, personalized output every time.

Last verified 2026-04-20

Write a weekly marketing performance report.
Period: [DATE RANGE]
Metrics to include: [list your KPIs]
Highlights: [what went well]
Issues: [what underperformed and brief reason]
Next week priorities: [3 bullet points]
Audience: [manager / team / client]
Tone: factual, no fluff. Use bullet points for metrics, short paragraphs for narrative.

Turn messy notes into client-ready updates

Capture rough bullets, let AI structure them, then save the final version back into your team workspace.

Last verified 2026-04-20

Turn these rough notes into a clear [EMAIL / STATUS UPDATE / REPORT].
Audience: [WHO WILL READ IT]
Purpose: [DECISION, UPDATE, REQUEST, OR ESCALATION]
Raw notes:
[PASTE NOTES]

Return:
1. Suggested subject line
2. Short summary
3. Main message in my tone: [DIRECT / WARM / EXECUTIVE]
4. Action items with owners and dates
5. Risks or open questions

Train Claude on your writing style once

Feed Claude 3-5 examples of your best emails. It learns your voice and tone so drafts need less editing.

Last verified 2026-04-20

I'll share 3 examples of emails I've written. After reading them, identify:
1. My typical sentence length and structure
2. Words or phrases I use often
3. My tone (formal / casual / direct / warm)
4. Things I never say

[PASTE EMAIL 1]
[PASTE EMAIL 2]
[PASTE EMAIL 3]

Now write a [TYPE] email using my style. Here's the context: [CONTEXT]

Ask for a sourced research brief

Use AI to create a first-pass overview with citations, then verify the sources before acting on the findings.

Sourced research briefs are a common first step for professionals replacing manual web scanning.

Last verified 2026-04-20

Create a research brief on [TOPIC] for [AUDIENCE]. Include: current landscape, 5 key facts, 3 risks, 3 open questions, and source links for every claim that affects a decision.

Separate evidence from interpretation

Ask AI to label what is directly supported by sources and what is an inference, so your recommendation stays defensible.

Last verified 2026-04-20

Review this research draft. Split it into: source-backed facts, reasonable inferences, unsupported claims, and questions to verify. Then rewrite the summary so unsupported claims are removed or clearly caveated.
Draft: [PASTE DRAFT]

Research, compare, and turn findings into a recommendation

Chain source gathering, comparison, and memo writing so research becomes a usable recommendation instead of a pile of links.

Last verified 2026-04-20

Research [OPTIONS / VENDORS / TOPIC], compare them against [CRITERIA], and produce a recommendation memo. Include a table, tradeoffs, risks, source links, and the decision I should make if the priority is [COST / SPEED / QUALITY / RISK].

Build a repeatable research intake template

Standardize scope, sources, criteria, and decision format so every new research request starts cleanly.

Last verified 2026-04-20

Create a research intake template for [ROLE / TEAM]. It should capture: decision to support, scope, time period, must-use sources, sources to avoid, comparison criteria, output format, approval owner, and caveats required before sharing.

Write listing copy from a blank MLS form

Most agents start a new listing by opening the MLS input form, pulling photos and spec sheets from the seller packet, and writing the public remarks field line by line. Quality varies and junior agents often rely on template files copied from older listings, which means fair-housing risk (steering language, protected-class references) is reviewed only at the broker-of-record level.

Last verified 2026-04-20

Draft listing remarks with Claude using a seller-intake prompt

Paste the seller intake notes, square footage, and feature highlights into Claude with a structured prompt that asks for three listing-copy variations (short MLS remarks, full description, social caption). Claude returns clean copy; the agent edits for voice, removes any language that could be read as steering or that references protected classes, and pastes the final version into the MLS. Keep seller personal data out of the prompt.

Last verified 2026-04-20

You are helping a U.S. real estate agent draft MLS listing copy. I will paste property facts below. Produce: 1) a 3-sentence MLS public-remarks blurb under 250 characters, 2) a 120-word full description, 3) a 200-character social caption. Use factual, neutral, feature-focused language. Do NOT use phrases that reference family status, race, religion, national origin, disability, age, or that imply neighbourhood demographics (e.g. 'safe neighbourhood', 'perfect for families', 'walk to church'). Do not fabricate features that are not in my input. Flag any claim you can't verify. Property facts: [PASTE]

Generate listings end-to-end with Zillow Showcase / Restb.ai plus Claude polish

Use Zillow Showcase (or Restb.ai's MLS image AI) to auto-tag property photos, extract room-level features, and produce the first draft of listing copy from photos plus public record data. Import the draft into Claude with the fair-housing prompt above to rewrite for voice, remove any compliance-risk phrases, and produce three social variations. Final copy gets a fair-housing scrub by the managing broker before MLS publish.

Last verified 2026-04-20

Rewrite the following listing draft in [AGENT VOICE: warm/professional/luxury]. Remove any phrases that reference protected classes or imply neighbourhood demographics. Keep all factual features. Output: 1) polished MLS remarks, 2) a 120-word description, 3) an Instagram caption, 4) a one-line Facebook headline. Draft: [PASTE]

Run a Claude API listing-copy engine with built-in fair-housing guardrails

For a high-volume team, stand up a Claude API worker that pulls structured property data from the brokerage CRM (Follow Up Boss, kvCORE, CINC), calls Claude with a fair-housing system prompt, runs a second Claude pass as an adversarial fair-housing reviewer, and writes the resulting copy back into the MLS vendor's listing input. Block publish when the second pass flags steering risk; route those listings to the managing broker for manual review. Treat all outputs as drafts subject to broker sign-off.

Last verified 2026-04-20

Fill state-approved forms by hand inside zipForm or dotloop

Agents start from state-association-approved forms (e.g. C.A.R., TREC, NYSAR) inside zipForm Plus or dotloop, hand-key buyer/seller info, contingency dates, and financing terms, and then route for electronic signature. Mistakes in dates, escalation clauses, or disclosure riders are caught by the transaction coordinator or managing broker — not the agent drafting the form.

Last verified 2026-04-20

Use Claude to pre-fill contract intake and produce a clause-review brief

After receiving a buyer or seller intake, paste the facts into Claude and ask it to produce: (1) a filled checklist for every field on the state-approved form, (2) a plain-English summary of contingency dates and disclosure triggers, (3) a flagged list of unusual terms that need attorney or broker review. Drop the summary into zipForm, but type every field by hand into the state-approved form itself. AI never touches the form directly — that keeps the agent clearly within state UPL rules.

Last verified 2026-04-20

I am preparing a [state] residential purchase agreement. Here are the deal facts: [PASTE]. Produce: 1) a field-by-field checklist matching the standard [state association] purchase agreement, 2) a plain-English summary of all contingency dates and disclosure triggers, 3) a flagged list of any unusual terms or clauses that need attorney or managing-broker review before I put them on the form. Do NOT generate legal language or redraft the contract — just prepare me to fill the state-approved form.

Integrate SkySlope or dotloop with Claude to produce transaction-coordinator-ready packets

Connect SkySlope Forms (or dotloop with its AI checklist) to a Claude workflow: once the buyer/seller intake is saved, Claude generates the transaction-coordinator packet (key dates, contingencies, disclosure triggers, outstanding tasks), a draft client-facing summary email, and a compliance checklist tied to the state-approved forms. The agent reviews, the TC or managing broker verifies contract terms, and the signed forms flow back into the compliance audit trail.

Last verified 2026-04-20

Here is the transaction intake [PASTE]. Produce: 1) a TC-ready packet with critical dates (inspection, appraisal, financing, closing) and rider list, 2) a client-facing plain-English summary email, 3) a compliance checklist referencing the state-approved form names for [state]. Flag anything that needs attorney review or deviates from standard practice.

Run a Claude API contract-review layer that flags deviations from state-approved forms

Build a Claude API workflow that takes a draft purchase agreement or lease (PDF in, text out), compares it clause-by-clause against the state-association approved template, and produces a deviation report: added clauses, missing disclosures, date inconsistencies, non-standard financing terms. Treat every output as a draft subject to attorney or managing-broker review; never auto-approve or auto-send. Use it as a pre-check before the agent pushes the contract to signing.

Last verified 2026-04-20

Hand-log each lead and note into the CRM after every call

Agents log new leads, call notes, and pipeline-stage changes manually in Follow Up Boss, kvCORE, CINC, or BoomTown at the end of the day — or in between showings on their phone. Fields get skipped, duplicate contacts accumulate, and follow-up sequences trigger from partial data. Pipeline reports are only as good as the last hour the agent sat down at their desk.

Last verified 2026-04-20

Dictate call summaries into Claude and paste them into the CRM

After each buyer or seller call, dictate a 30-second voice note. Send it through Claude with a prompt that produces a structured CRM update: contact fields, pipeline stage, next task, and suggested follow-up timing. Copy the output into Follow Up Boss / kvCORE so every record has a consistent schema. Keep client full name, SSN, and financial detail out of the dictation — use initials.

Last verified 2026-04-20

You are helping a real estate agent keep their CRM clean. I just finished a call and will paste the voice-note transcript below. Produce: 1) contact update (first name, last name initial, phase: lead/active buyer/active seller/under contract/past client), 2) 3-sentence call summary, 3) next task with a due date, 4) suggested follow-up cadence (daily/weekly/monthly/quarterly). Transcript: [PASTE]

Use BoomTown or Follow Up Boss AI assist alongside Claude for pipeline review

Turn on the CRM's built-in AI features (BoomTown's AI assistant, Follow Up Boss's Smart Lists, or kvCORE's Smart Campaigns) to auto-nurture leads and surface stale follow-ups. Each Monday, export the pipeline CSV into Claude and ask for a triage: top 10 deals most likely to close this month, top 10 leads at risk of going cold, and three coaching moments to bring into the team meeting.

Last verified 2026-04-20

You are my weekly pipeline coach. I'll paste my CRM export below. Rank: 1) top 10 deals most likely to close this month with a one-line reason each, 2) top 10 leads at risk of going cold with the exact next action, 3) three patterns across my pipeline (e.g. leads I never call back, stalled financing contingencies, stale past-client touchpoints). Data: [PASTE]

Run a Claude API pipeline-hygiene bot against the brokerage CRM

For a team brokerage, set up a daily Claude API job that reads the CRM via API, identifies duplicate contacts, stalled deals past their contingency windows, and leads whose last touch exceeds the brokerage's service-level policy. The bot posts a Slack digest to each agent and updates a shared Google Sheet for the team lead. The agent still makes every client call — the bot just flags where attention is needed. Keep PII out of the prompts wherever possible.

Last verified 2026-04-20

Track contingency dates on a personal spreadsheet or notepad

Many agents track escrow, inspection, appraisal, financing, and closing dates on a per-deal spreadsheet or a yellow pad. When deadlines shift (extensions, inspection responses, rate locks), they update multiple systems by hand: the CRM, the transaction platform, the buyer/seller, and the managing broker. Missed or duplicated updates are the single largest source of commission disputes and E&O claims.

Last verified 2026-04-20

Ask Claude to turn an accepted offer into a day-by-day closing timeline

Paste the key dates from the accepted offer (acceptance, inspection window, appraisal deadline, financing contingency, closing date) into Claude. It produces a day-by-day timeline with reminders for the agent, the buyer, the lender, and the TC — plus suggested text-message templates for each milestone. The agent drops the timeline into dotloop tasks and copies the templates into the CRM.

Last verified 2026-04-20

I just had an offer accepted. Here are the key dates: [PASTE]. Produce: 1) a day-by-day timeline from today through closing with every contingency, inspection, appraisal, financing, and closing milestone, 2) a list of reminders for me, the buyer, the lender, and the TC with timing, 3) four short text-message templates (inspection scheduled, inspection done, appraisal done, clear to close). Use factual, calm, professional language. Flag any date inconsistencies.

Sync dotloop or SkySlope timelines into Claude for weekly broker reports

Once dotloop or SkySlope is the source of truth for every deal, export the open transactions each Monday and pipe them through Claude. It produces a deal-by-deal status brief for the managing broker (dates met, at-risk dates, extensions), plus a client-facing weekly update for each active buyer/seller. Broker sign-off still sits with a human; the AI just compresses the writing work.

Last verified 2026-04-20

Here is this week's open-transaction export [PASTE]. Produce: 1) a one-line status for each deal (on-track/at-risk/blocked, with the specific date or blocker), 2) a client-facing weekly update for each buyer/seller in plain English (no legal advice), 3) a short broker-facing risk summary naming the three files most likely to need managing-broker attention.

Run a Claude API deadline-watcher that pages the TC on at-risk contingencies

For a high-volume team, set up a Claude API job that reads the dotloop/SkySlope API nightly, identifies contingencies within 48 hours of expiry with no update, and pages the TC and the listing agent via Slack or SMS. The bot also produces a daily 'deals at risk' digest for the managing broker. Treat the output as a prompt for human action, not an action itself — never auto-email clients, never auto-extend contingencies.

Last verified 2026-04-20

Walk into the negotiation with notes from memory and recent comps

Many agents prepare for an offer/counter-offer call by flipping through their CMA, the inspection report, and the seller's disclosure — and relying on experience to guide what to offer or concede. Concession strategy, comp anchoring, and fallback positions often aren't written down, so the brokerage can't review or coach them after the fact.

Last verified 2026-04-20

Let Claude draft a negotiation brief from the CMA and seller position

Paste the CMA, inspection findings, and the current offer/counter-offer stack into Claude. Ask for a written negotiation brief: three anchoring points, three concession ideas the client would likely accept, two pressure points the other side may have, and a recommended opening counter. The agent reads, adjusts, and keeps the final decision firmly theirs — the brief is a checklist, not a script. Negotiations are interpersonal work; AI prepares the ground, not the conversation.

Last verified 2026-04-20

I'm about to negotiate a [counter-offer/inspection response/price reduction] for my [buyer/seller] client. Here is the situation: [PASTE CMA, inspection findings, current offer stack]. Produce: 1) three anchoring points backed by the comps, 2) three concession ideas my client would likely accept and three they likely won't, 3) two likely pressure points on the other side, 4) a recommended opening counter in plain English. Do not write the actual call script — just prepare me.

Pair HouseCanary or RPR comps with Claude for an evidence-based brief

Pull the authoritative comp set and price estimate from HouseCanary or RPR, then feed the data into Claude with the deal context. Claude produces an evidence-based brief that cites comp addresses, adjustments, and a defensible price range. The agent walks into the meeting with both the data and the talking points and keeps full control of the conversation.

Last verified 2026-04-20

Here are the comps from [RPR/HouseCanary]: [PASTE]. Deal context: [PASTE]. Produce a negotiation brief that cites comp addresses and adjustments, gives a defensible price range (floor / likely / ceiling), suggests an opening counter with rationale, and lists two concessions my client could trade instead of price.

Build a Claude API negotiation-brief generator inside the team CRM

For a team brokerage, set up a Claude API workflow that, given a deal ID in the CRM, pulls the CMA, seller disclosure, and inspection report, and writes a standard negotiation brief template into the deal record. The brief becomes a coaching artefact: the team lead reviews it alongside the agent before every consequential call. AI doesn't negotiate for the client — it makes the brokerage's institutional knowledge visible.

Last verified 2026-04-20