Your AI Action Plan

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.

Clean pasted records before entering them

Use AI to turn messy copied notes into a clean table with consistent names, dates, categories, and missing-field flags.

Last verified 2026-04-20

Clean this data before I enter it into [SYSTEM]. Return a table with columns: [COLUMNS]. Standardize dates, names, categories, and phone/email formatting. Add a final column called Review needed for anything uncertain. Do not invent missing values.

Raw data:
[PASTE]

Use Zapier AI Data Entry for repeat form-to-database work

Route recurring submissions into a database automatically, then review exceptions instead of copying every field by hand.

Last verified 2026-04-20

Map this incoming form to my database fields. Required destination fields: [FIELDS]. Validation rules: [RULES]. Return a field mapping, transformations needed, and exception cases that should stop for human review.

Extract, validate, and update records with an exception log

Combine AI extraction with a review checklist so only clean records move forward and uncertain ones are easy to audit.

Last verified 2026-04-20

Extract records from this input and prepare them for [SYSTEM]. Return: 1. clean records table, 2. duplicate warnings, 3. missing required fields, 4. values that need human review, 5. a short change log.

Input:
[PASTE]

Create a data-entry QA playbook

Turn recurring record updates into a repeatable workflow with field rules, review triggers, and exception handling.

Last verified 2026-04-20

Create a data-entry QA playbook for [PROCESS]. Include: required fields, allowed formats, duplicate checks, sensitive-data warnings, examples of good records, examples of records to reject, and a final human review checklist.

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.

Turn raw notes into a weekly report

Paste metrics, wins, blockers, and next actions into AI to get a structured first draft you can edit quickly.

Recurring report drafting is a common low-risk AI workflow across office roles.

Last verified 2026-04-20

Write a weekly [TEAM / CLIENT / PROJECT] report.
Period: [DATE RANGE]
Metrics: [PASTE METRICS]
Highlights: [WHAT WENT WELL]
Risks or blockers: [WHAT NEEDS ATTENTION]
Next actions: [3-5 BULLETS]
Audience: [MANAGER / CLIENT / TEAM]. Keep it factual, concise, and easy to scan.

Ask for anomalies before writing the narrative

Use AI to spot unusual changes first, then write the report around the decisions those changes require.

Last verified 2026-04-20

Analyze this report data before drafting the summary.
Data: [PASTE TABLE OR METRICS]
Return: 1. Top 5 changes, 2. likely explanations, 3. questions to verify, 4. what should be highlighted, 5. what should not be overclaimed.

Spreadsheet export to decision memo

Export data from your system, use AI for synthesis, then store the final memo in your team workspace.

Last verified 2026-04-20

Turn this exported data into a decision memo.
Audience: [WHO WILL READ IT]
Data: [PASTE CSV OR TABLE]
Return: executive summary, key changes, likely causes, recommended action, risks, and a short appendix explaining assumptions.

Reusable monthly review system

Create a report template that compares periods, flags risks, and turns every monthly report into an action plan.

Last verified 2026-04-20

Create a reusable monthly review template for [ROLE / TEAM]. It should include: required inputs, KPI table, variance analysis, stakeholder narrative, recommended actions, risks, and a quality checklist before sending.

Copy last quarter's proposal deck and edit by hand

Most reps start a new proposal by duplicating the last proposal that closed, finding-and-replacing the logo and company name, rewriting the pain points, and hoping the pricing table still matches current list price. Legal's redline of the MSA is a separate thread. First-draft proposals routinely take a full afternoon.

Last verified 2026-04-20

Draft the proposal narrative with Claude from discovery notes

Paste the discovery-call notes, pricing constraints, and the buyer's stated priorities into Claude with a proposal-structure prompt. It produces a clean first draft: executive summary, problem statement, proposed solution, scope, pricing placeholder, timeline. The rep reviews for accuracy, plugs in quoted numbers from the CRM, and routes through deal desk / legal.

Last verified 2026-04-20

You are helping a B2B sales rep draft a proposal. Discovery notes and context: [PASTE]. Produce: 1) a 3-sentence executive summary in the buyer's own words, 2) a problem statement citing their stated priorities, 3) a proposed-solution section mapped to their priorities, 4) a scope/deliverables section, 5) a pricing placeholder I can fill in from CRM, 6) a one-paragraph risk/benefit framing. Use neutral, factual language — no superlatives, no fabricated metrics. Flag any customer claim I should verify before sending.

Combine Gong or Chorus call summaries with Claude to auto-draft proposals

Let Gong or Chorus transcribe and summarise the discovery call. Pipe the call summary plus the buyer's firmographic data into Claude with the proposal template. Claude produces a draft that references specific moments from the call ('you mentioned X renewal risk'). The rep reviews, fills CRM-sourced pricing, and routes for deal-desk approval.

Last verified 2026-04-20

Here's the Gong/Chorus discovery-call summary and the account firmographics: [PASTE]. Produce a proposal draft referencing specific call moments ('you mentioned X'), with: 1) 3-sentence exec summary, 2) buyer-priority-mapped solution section, 3) scope table, 4) risks with mitigations, 5) pricing placeholder table. Don't fabricate any quote, price, or call moment. Flag anything I should verify with the champion before sending.

Build a Claude API proposal-generator wired to Salesforce CPQ and the content library

For a mid-market sales org, set up a Claude API workflow that reads the opportunity record from Salesforce (stage, product selection, pricing), pulls approved content blocks from the library, and produces a first-draft proposal PDF with pricing pulled from CPQ. Deal-desk or sales-ops still signs off; the AI removes the blank-page tax for every rep. Every claim is template-constrained — no hallucinated metrics or references.

Last verified 2026-04-20

Scribble notes on a notepad and type a summary into Salesforce later

Most reps balance running the conversation with scribbling discovery notes. After the call they type a summary into the opportunity description in Salesforce or HubSpot — usually thinner than the conversation warranted, missing the objection nuance and competitive context that would help the next touchpoint.

Last verified 2026-04-20

Transcribe discovery with Otter.ai and let Claude produce a MEDDIC or BANT summary

Record the discovery call through Otter.ai (with consent). Paste the transcript into Claude with your chosen qualification framework (MEDDIC, BANT, SPICED). Claude extracts structured fields — pain, budget, decision criteria, decision process, identified champion — plus verbatim customer quotes for each. The rep pastes the structured output into Salesforce so the next touchpoint can pick up where the conversation ended.

Last verified 2026-04-20

Here is the discovery-call transcript: [PASTE]. Produce a MEDDIC summary: Metrics, Economic buyer, Decision criteria, Decision process, Identify pain, Champion. Under each field: a 1-sentence summary and a verbatim customer quote that supports it. Don't invent data — leave fields empty with 'not discussed' if the call didn't cover it. Then produce a 5-bullet next-step action plan.

Use Gong or Chorus with Claude to build a call-coaching loop

Let Gong / Chorus record, transcribe, and score the discovery. Pipe the call summary and objection list through Claude with your playbook to produce: structured fields for Salesforce, a next-steps email, a coaching note for the rep (what went well, what to try next time), and a three-sentence update for the sales manager's pipeline review.

Last verified 2026-04-20

Here's the Gong call summary + playbook reference: [PASTE]. Produce: 1) MEDDIC-style structured fields, 2) a next-steps email to the champion, 3) a 150-word coaching note for me (one thing to keep, one thing to change, one thing to try), 4) a 3-sentence update for the Monday pipeline call.

Run a Claude API discovery-coach that benchmarks calls against top-rep playbook

For a sales org, wire call transcripts into a Claude API worker that benchmarks each discovery call against the top-decile rep's playbook (question frequency, talk-listen ratio, pain-point depth). The bot produces a weekly coaching digest per rep and a monthly trend for the sales manager. Coaching guidance is a starting point; managers do the actual coaching. Consent requirements must be met before any call is recorded.

Last verified 2026-04-20

Keep a mental list of which deals need attention this week

Reps scroll through their pipeline in Salesforce or HubSpot each morning, eyeball which deals haven't been touched, and send a follow-up email. Stale deals age out; active ones get over-nudged. Without a clear cadence, attention goes to the loudest deal, not the most important.

Last verified 2026-04-20

Ask Claude to rank your pipeline and draft one follow-up per stalled deal

Export the pipeline CSV from Salesforce / HubSpot each Monday. Paste into Claude with last touchpoint notes and ask for: a ranked list of deals at risk of stalling, a specific next move per deal, and a first-draft follow-up email for the top five. The rep edits, sends, and updates CRM. One hour of triage replaces a whole day of reactive follow-up.

Last verified 2026-04-20

Here's my current pipeline export and last-touchpoint notes: [PASTE]. Produce: 1) a top-10 at-risk list with the specific stall reason per deal, 2) a recommended next move per deal (new contact, new angle, disengage, escalate to manager), 3) first-draft follow-up emails for the top 5 under 120 words each. Use neutral, customer-focused language. No false urgency.

Pair Outreach or SalesLoft with Claude-tuned personalisation

Use Outreach or SalesLoft sequences to handle cadence. Layer Claude on top of the first step of each sequence to rewrite the opening in the buyer's voice based on the latest account research and the rep's call notes. Personalisation at scale — without the generic 'I noticed your company's impressive Q3 momentum' phrasing that sinks open rates.

Last verified 2026-04-20

Here's the account research + last call note + standard sequence template: [PASTE]. Produce: 1) a personalised opening line that references something specific from the research or call (no fluff, no superlatives), 2) the rewritten first step of the sequence under 120 words, 3) a subject line test (A/B). Do not fabricate facts about the company.

Run a Claude API pipeline-health bot that nudges reps on stalled deals

Stand up a Claude API job reading Salesforce / HubSpot each morning to flag opportunities with no activity past your team's SLA, draft personalised follow-ups using the last call note and account research, and queue them in the rep's Slack for a single-click send. Never auto-send — the rep always reviews. The bot makes the pipeline self-surface.

Last verified 2026-04-20

Rely on informal win/loss conversations with peers

Many reps piece together competitive intel from hallway conversations, the occasional win/loss interview, and whatever battlecards product marketing last updated. The view is anecdotal, rarely weighted by deal size, and usually a quarter out of date.

Last verified 2026-04-20

Ask Claude to cluster win/loss reasons from closed-deal notes

Pull the closed-won / closed-lost deals from CRM with the reason codes and free-text notes. Paste them into Claude and ask for a themed breakdown: top competitive losses by competitor, top pricing objections, top product-gap themes, and one recommended action per theme. This gives product marketing something to chew on without burning a whole research cycle.

Last verified 2026-04-20

Here are the closed-won and closed-lost deals for the quarter with reason codes and notes: [PASTE]. Produce: 1) top 5 loss themes ranked by deal-value weight, 2) top 3 competitors by win-rate impact, 3) top 5 product-gap themes with direct quotes from notes, 4) one recommended action per theme for product marketing. Don't fabricate themes — cite the deals.

Use Klue or Crayon battlecards with Claude for deal-specific positioning

Subscribe to Klue or Crayon for continuously-updated competitor battlecards. Before each competitive deal, hand the battlecard and your specific deal context to Claude for a custom positioning brief: three differentiation angles that fit this buyer, two likely objections, and recommended responses with verifiable proof points.

Last verified 2026-04-20

Here's the Klue battlecard + my deal context (buyer priorities, stage, competitor present): [PASTE]. Produce a deal-specific positioning brief: 1) three differentiation angles that fit this buyer's priorities, 2) two likely objections with recommended responses, 3) three proof points I should have ready (customer references, case studies, data). Only use claims supported by the battlecard.

Build a Claude API competitive analytics layer across closed deals and call recordings

For a sales org, run a Claude API job that reads Gong / Chorus transcripts plus Salesforce closed-deal reason codes and produces a monthly competitive dashboard: win rate by competitor, top objections by segment, product-gap themes. Revenue ops owns the artefact; product marketing consumes it for the next release of battlecards. AI produces the data view — the strategy is still the org's.

Last verified 2026-04-20

Walk into negotiations relying on experience and the battlecard

Reps often prepare for negotiation calls by skimming the battlecard, checking the deal desk's approved discount levels, and relying on muscle memory. Objection handling is rarely written down in advance, which means the same objection gets handled differently by different reps.

Last verified 2026-04-20

Let Claude draft a negotiation brief from the deal context

Before a negotiation call, paste the deal context, pricing approvals, and likely objections into Claude. It produces a written negotiation brief: three concession options your client might accept, three that won't, two pressure points on the buyer, and a recommended opening. The rep walks in prepared — and keeps full control of the conversation.

Last verified 2026-04-20

I'm about to negotiate with [buyer] on [deal size + product mix]. Here's the context and what I'm approved to offer: [PASTE]. Produce: 1) three concession options they might accept (non-price first, then price), 2) three they likely won't, 3) two pressure points on their side (timing, budget cycle, competitive pressure), 4) a recommended opening in plain English. Don't give me a script — give me a checklist.

Combine Gong deal risk flags with Claude for a negotiation rehearsal

Use Gong Deal Intelligence (or Chorus Momentum) to surface deal risk signals from your call history — sentiment shifts, missing stakeholder, champion risk. Hand the risk summary to Claude with the deal context to produce a negotiation rehearsal: likely buyer asks, suggested rep responses, and the two moments where the rep should slow down and ask a question instead of answering.

Last verified 2026-04-20

Here's the Gong deal summary + risk flags + pricing context: [PASTE]. Produce a negotiation rehearsal: 1) top 5 questions the buyer is likely to ask, 2) recommended response to each (short, customer-centric, no jargon), 3) two moments I should slow down and ask a question instead of answering. Flag any risk that needs manager involvement before the call.

Run a Claude API negotiation-coach that produces personalised briefs before every competitive deal

For a sales org, set up a Claude API worker that — whenever an opportunity reaches negotiation stage and has a competitor flag — reads the call history, deal desk approvals, and Klue/Crayon battlecards, and produces a negotiation brief written directly into the Salesforce opportunity record. The rep reviews before the call; manager can coach from the same brief. The AI writes; the human closes.

Last verified 2026-04-20