© 2026 Sales Bytes.
Prompt:
Act as my AI sales assistant. Based on my pipeline data below, give me a morning briefing:
{PASTE_CRM_SNAPSHOT}
Include:
1. Deals that need attention today (and why)
2. Follow-ups due today
3. Meetings prep notes for today's calendar: {TODAYS_MEETINGS}
4. One deal I should be worried about
5. One opportunity I might be missing
Format as a quick-scan bulleted brief I can read in 2 minutes.
💡 Why this works: Start every day with clarity. AI can be your briefing engine.
Prompt:
Help me build a lead scoring system for {YOUR_PRODUCT}. My ICP:
- Company: {ICP_COMPANY}
- Contact: {ICP_CONTACT}
Create a scoring model with:
1. Firmographic criteria (company attributes) — 40% weight
2. Behavioral signals (actions they've taken) — 35% weight
3. Engagement signals (how they interact with us) — 25% weight
For each criterion, assign a point value. Total possible score: 100. Define thresholds: Hot (80+), Warm (50-79), Cold (below 50).
💡 Why this works: Scoring leads prevents you from spending equal time on unequal prospects.
Prompt:
Create a weekly sales report from my raw data:
This week:
- Calls made: {CALLS}
- Emails sent: {EMAILS}
- Meetings held: {MEETINGS}
- Proposals sent: {PROPOSALS}
- Deals closed: {DEALS_WON}
- Pipeline added: {NEW_PIPELINE}
- Pipeline lost: {LOST}
Format as a clean report with:
1. Key metrics vs. target
2. Win/loss ratio trend
3. Activity-to-pipeline conversion
4. Top 3 achievements
5. Top 3 areas for improvement
6. Focus for next week
💡 Why this works: Automate your reporting. Spend the time selling instead.
Prompt:
Here are 5 replies I received to my cold outreach:
{PASTE_REPLIES}
For each reply:
1. Classify it: Interested / Objection / Not Now / Not Interested / Referral / Auto-Reply
2. Draft an appropriate response
3. Suggest the next action in my CRM
Prioritize interested replies first. For objections, use the acknowledge-redirect framework.
💡 Why this works: Batch-processing replies with AI saves 30+ minutes daily for active prospectors.
Prompt:
Convert these raw meeting notes into a structured CRM update:
{PASTE_RAW_NOTES}
Format as:
- Deal stage update: {current → recommended}
- Key decision-makers identified
- Pain points confirmed
- Next steps (with dates)
- Competitive intel gathered
- Risk flags
- Close date estimate
- Deal amount update
Also draft the follow-up email based on these notes.
💡 Why this works: Stop rewriting notes twice. AI formats them for your CRM and drafts the follow-up in one step.
Prompt:
Here's a list of companies I'm targeting:
{PASTE_COMPANY_LIST}
For each company, enrich with:
1. Likely tech stack for their size and industry
2. Estimated revenue and employee count
3. Key decision-maker titles to target
4. One personalization hook (recent news, job posting, product launch)
5. Recommended outreach angle
Format as a table I can paste into my spreadsheet.
💡 Why this works: Enrichment is tedious but necessary. AI handles the bulk, you verify the details.
Prompt:
Write a section of our sales playbook for the {STAGE} stage. Our product: {PRODUCT}. Target buyer: {BUYER}.
Include:
1. Objective of this stage
2. Key activities and their sequence
3. Questions to ask
4. Red flags to watch for
5. Exit criteria (when to advance to next stage)
6. Email templates for this stage
7. Common mistakes to avoid
💡 Why this works: A documented playbook means new reps ramp in weeks, not months.
Prompt:
Build my prospecting plan for next week. My targets:
- Quota: {QUOTA}
- Current pipeline: {PIPELINE}
- Gap to fill: {GAP}
- My conversion rates: {RATES}
Give me:
1. How many prospects to contact and through which channels
2. Which accounts to prioritize
3. Daily activity targets (calls, emails, LinkedIn)
4. Time blocks for prospecting vs. deal work
5. A specific goal for each day
Make it realistic for a {HOURS}-hour work week.
💡 Why this works: Prospecting without a plan is just random activity. Plan each week deliberately.
Prompt:
Here are the last 10 objections I received this month:
{PASTE_OBJECTIONS}
Analyze patterns:
1. What are the top 3 recurring themes?
2. At what stage do most objections appear?
3. Are these product objections, timing objections, or trust objections?
4. What does this tell me about my messaging or targeting?
5. Recommended adjustments to my pitch, targeting, or sequence
Be honest about what I might be doing wrong.
💡 Why this works: Objection patterns reveal messaging problems. Fix the root cause, not just individual responses.
Prompt:
I've compiled data from my last 20 competitive deals:
{PASTE_WIN_LOSS_DATA}
Analyze:
1. Win rate by competitor
2. Patterns in wins (what we did right)
3. Patterns in losses (what they did better)
4. Deal stages where we win vs. lose most often
5. Recommendations for improving our competitive positioning
6. Specific talk tracks that won deals
Format as a report I can share with my team.
💡 Why this works: Systematic competitive analysis beats gut feelings every time.
Prompt:
Here's a transcript from my sales call:
{PASTE_TRANSCRIPT}
Analyze:
1. Talk-to-listen ratio (was I talking too much?)
2. Key pain points the prospect mentioned
3. Buying signals I might have missed
4. Moments where I should have asked a follow-up question
5. Action items mentioned (explicit and implicit)
6. Draft the follow-up email based on this call
Be specific. Reference exact quotes from the transcript.
💡 Why this works: Call recording without analysis is just storage. AI turns recordings into coaching.
🔄 Platform tip: Claude handles long transcripts exceptionally well.
Prompt:
Build my quarterly territory plan:
- Territory: {TERRITORY}
- Quota: {QUOTA}
- Current accounts: {ACCOUNTS}
- New logo target: {TARGET}
- Expansion target: {EXPANSION}
Create:
1. Account prioritization (tier A/B/C with criteria)
2. Monthly targets and milestones
3. Weekly activity plan to hit targets
4. Account-level strategies for top 5 accounts
5. Risk mitigation for quota attainment
6. Resources I need from marketing, SE, leadership
💡 Why this works: Reps who plan their territory outperform reactive reps by 30-50%.
Prompt:
I ran an A/B test on my cold emails. Here are the results:
Version A: {SUBJECT_A}
- Open rate: {OPEN_A}
- Reply rate: {REPLY_A}
- Meeting rate: {MEETING_A}
Version B: {SUBJECT_B}
- Open rate: {OPEN_B}
- Reply rate: {REPLY_B}
- Meeting rate: {MEETING_B}
Sample size: {SIZE} emails each.
Analyze:
1. Is the winner statistically significant at this sample size?
2. What made the winner work better?
3. A hypothesis for the next test
4. Recommended iteration for Version C
💡 Why this works: Testing without analysis is just guessing. Let AI interpret your results.