Jeff Bullas

Nice point — exporting into the LMS first is the real time-saver. Great practical tip: generate 5 items, paste into a spreadsheet, and test-import quickly. Let’s turn that into a repeatable process you can use every week.

What you’ll need

• An AI chat tool you like (Chat-based or API).
• A spreadsheet (Google Sheets or Excel).
• Access to your LMS quiz import (Moodle or Canvas). A small test course is ideal.
• A 5–10 question sample to start with — keep it tiny.

Step-by-step (do this now)

1. Choose your format: For Moodle use GIFT or Moodle XML if you want richer items. For Canvas, QTI is best — but both accept simple CSV if you follow a template.
2. Create a spreadsheet template. Suggested headers: type, question, option1, option2, option3, option4, correct, points, feedback, tags.
3. Ask the AI to generate 5–10 questions using that template (prompt below). Paste the AI output into the sheet and tidy wording.
4. Export a small CSV (5 questions) and import into the LMS. Read the import log, fix errors, repeat until clean.
5. Once clean, scale up: generate batches of 20–50, review for accuracy, tag by topic and difficulty, then import.

Example CSV row (copy-paste friendly)

type,question,option1,option2,option3,option4,correct,points,feedback,tags

MCQ,”What is the capital of France?”,”Paris”,”London”,”Berlin”,”Rome”,Paris,1,”Paris is the capital of France.”,geography

Common mistakes and quick fixes

• Problem: Special characters or smart quotes break imports. Fix: convert smart quotes to straight quotes and remove commas inside fields or wrap fields in quotes.
• Problem: Incorrect correct-answer formatting. Fix: Match exact option text as the correct field or use option letter if your LMS requires it.
• Problem: Image or math questions fail. Fix: Upload images separately to LMS and reference URLs, or use LMS-native equation editors rather than raw LaTeX in CSV.
• Problem: Import errors are vague. Fix: Import one question at a time to isolate the bad row.

Action plan — first 30 minutes

1. Create the spreadsheet template (10 min).
2. Use the AI prompt below to generate 5 MCQs and paste into the sheet (10 min).
3. Export CSV and do a test import in LMS (10 min). Read errors, fix, repeat once.

Copy-paste AI prompt (use as-is)

“Create 5 multiple-choice questions for [topic]. For each question, provide: type (MCQ), question text, four options (option1–option4), the correct option exactly as written, a 1-sentence feedback, and a short tag. Return results as CSV rows matching: type,question,option1,option2,option3,option4,correct,points,feedback,tags. Use points=1. Topic: [insert topic].”

What to expect

• First imports will need tweaks — that’s normal. Small iterations are faster than perfection up front.
• Once your template is solid, you’ll be producing reliable question banks quickly.

Tell me: Moodle or Canvas? And which question types matter most (MCQ, short answer, matching)? I’ll give a one-click-ready template for your LMS.

Nice—your checklist is spot on. I especially like the testing rule: change only one element at a time. That’s how you turn guesses into learning.

Here’s a compact, repeatable process you can use right now to get an irresistible Upwork or LinkedIn headline for any client.

What you’ll need:

• A one‑line summary of the client’s main outcome (what they deliver).
• One target audience (who benefits most).
• 2–3 distinctive skills, tools, or proof points.
• Preferred tone (friendly, authoritative, bold).

1. Craft a single outcome sentence: Combine outcome + audience + top skill. Example: “Reduce churn for subscription founders by improving onboarding flows.”
2. Use AI to generate options: Ask for 5 short headline variants (keep <120 chars). Pick two for testing—a clear, benefit‑led line and a personality/tone line.
3. Edit for scannability: Remove filler, use an active verb, name the audience, and state the benefit. Aim for 6–10 words.
4. Implement & measure: Run variant A for 2–4 weeks, then swap to B. Track profile views, invites, replies, and project invites.
5. Iterate: If neither moves the needle, change one element (audience, benefit, or tone) and repeat.

Copy‑paste AI prompt (use as a template):

“Write 5 LinkedIn headline options (each under 120 characters) for a [role] who helps [audience] achieve [benefit]. Use a [tone]. Include one headline that uses a measurable verb, one that asks a question, and one that shows a quick proof or tool. Keep them scannable and benefit‑led.”

Worked example:

• Input sentence: “Reduce churn for subscription founders by improving onboarding flows.”
• AI options might include: “Onboarding strategist for SaaS — cut churn & speed activation” and “Turn new signups into loyal users — onboarding for subscription apps.”

Common mistakes & fixes:

• Too many titles: Fix by keeping one role and one benefit.
• Vague buzzwords: Replace “expert” with a clear outcome.
• Over‑promising: Use conservative, demonstrable benefits or soft language (e.g., “help reduce” instead of “reduce by 50%”).

Quick action plan:

1. Gather the 4 items listed above.
2. Run the AI prompt and pick two favorites.
3. Push variant A for 2–4 weeks, swap to B, compare metrics.

Small experiments win. Start with one client, learn what wording nudges more replies, then scale the approach. Keep it simple, measurable and human‑first.

Spot on about weighting operational signals over noisy event blips. That single shift turns a busy alert feed into a focused, trustable “radar.” Let’s make it practical with a lean checklist, a simple scoring recipe, and a worked example you can run this week.

• Do
  • Weight billing intent and renewal context higher than event micro-swings.
  • Optimize for Precision@Top10% so CS spends time on the right 10%.
  • Return a score, top 3 drivers in plain English, and one recommended action.
  • Track alert acceptance (accept/decline) and tighten thresholds until acceptance exceeds 60%.
  • Validate labels against billing and use time-based splits to avoid hindsight bias.
• Do not
  • Let transcript sentiment stand alone; pair it with ticket recency and resolution time.
  • Mix future information into training (e.g., post-churn notes) — that’s data leakage.
  • Over-engineer features no one can explain; 8–12 clear signals beat 80 opaque ones.
  • Firehose alerts without ownership; every alert needs an owner and a next step.

What you’ll gather (add two high-leverage fields)

• Product usage: last login, sessions/week, core feature counts, 4-week trend.
• Support: tickets opened and unresolved, average resolution time, transcript snippets.
• Customer: plan tier, tenure, ARR/MRR, renewal date, account owner.
• Billing/intent: seat changes, downgrade quotes, failed payments, credit holds.
• CRM signals: owner changes, loss of executive sponsor, negative QBR notes.
• Labels: cancellation/downgrade dates validated against billing.

Step-by-step: the 5-signal “Churn Radar” you can deploy fast

1. Assemble a customer-week table with these simple features:
   • Inactivity days (since last login)
   • Usage drop % (vs prior 4 weeks) on 1–3 core features
   • Unresolved tickets and average hours-to-resolution (last 30 days)
   • Sentiment last 30 days (positive/neutral/negative) from transcripts
   • Renewal window flag (renewal in 30/60/90 days)
   • Billing intent flags (seat cuts, downgrade quote, failed payments)
   • Stakeholder risk (owner change, exec sponsor left)
2. Define the label you care about: churn or material downgrade within 30–60 days of the prediction week.
3. Create a rules score first (transparent and fast):
   • Billing intent flag = +35
   • Renewal in ≤30 days and usage drop ≥50% = +25
   • Inactivity ≥14 days = +20
   • 2+ unresolved tickets or avg resolution >48 hours = +15
   • Negative sentiment in last 2 tickets = +10
   • Stakeholder risk (owner/sponsor change) = +10

   Rank customers by total score and focus on the top 10%.

4. Train a lightweight model (logistic or small tree) using the same features. Compare Precision@Top10% to your rules. Keep whichever is higher and easier to explain.
5. Ship an operational feed daily: account, risk score, top 3 drivers in plain language, owner, and one-click playbook.

Insider trick: stage risk by lead time

• Red: 0–30 days to likely churn — concierge help, unblockers, discount authority.
• Amber: 31–60 days — value review, usage coaching, success plan.
• Green-watch: 61–90 days — nurture, training drip, adoption goals.

Worked example (how the alert reads to CS)

• Customer E — Risk 81
  • Drivers: renewal in 27 days; 58% drop in core feature; 2 unresolved tickets (avg 62 hours).
  • Recommended action: “Book a 20‑minute unblock call within 48 hours; escalate ticket P2; share a 2-step walkthrough for the core feature.”
• Customer F — Risk 63
  • Drivers: seat count down 15% last week; negative tone in last 2 tickets; owner changed.
  • Recommended action: “CSM-led value review this week; confirm new sponsor goals; propose right-sized plan with 30‑day success checklist.”

Common mistakes & quick fixes

• Leakage: including future notes or post-churn actions in training. Fix: lock features to data available up to the prediction week.
• One-size thresholds: SMB and Enterprise behave differently. Fix: set thresholds by segment and plan tier.
• Sentiment overreach: negative wording isn’t always risk. Fix: require negative sentiment + long resolution time.
• Alert fatigue: too many borderline flags. Fix: dual thresholds (red ≥70, amber 55–69) and cap daily alerts per CSM.
• Cold starts: new accounts lack history. Fix: use onboarding milestones (first value event, activation score) as early proxies.

Copy‑paste AI prompt (drop into your LLM to turn data into drivers and actions)

“You are a senior Customer Success analyst. I will paste a weekly snapshot per customer with fields: customer_name, renewal_days, last_login_days, usage_drop_percent_core_features, unresolved_tickets_count, avg_resolution_hours, transcript_snippets_last_30d, sentiment_last_30d (positive/neutral/negative), seat_change_30d_percent, billing_intent_flags, owner_change (yes/no), arr_tier, segment. For each customer: 1) assign a churn risk score 0–100, 2) list the top 3 drivers in plain English, 3) recommend one concise action a CS rep should take this week, and 4) classify lead time as Red (0–30d), Amber (31–60d), or Green‑watch (61–90d). Keep the output to 6–8 lines per customer.”

7‑day action plan

1. Pull 6–12 months of usage, support, billing, and CRM owner changes into a single table.
2. Compute the simple features above; define the 30–60 day churn label from billing.
3. Build the rules-based score; pick the top 10% list and sanity-check with CS leaders.
4. Train a small model; compare Precision@Top10% vs rules and choose the winner.
5. Draft three one-click playbooks tied to common drivers (inactivity, support friction, billing intent).
6. Launch a pilot: randomize half of the top-10% into outreach and hold out the rest.
7. Track acceptance rate, Precision@Top10%, time-to-first-action, and ARR saved; plan monthly retrain.

Bottom line: Keep the signals few and meaningful, tie them to renewal timing and billing intent, and ship a score with a next step. That’s how AI moves from interesting dashboards to saved revenue.

Nice call on starting simple and optimizing Precision@Top10% — that’s exactly where you get fast, usable wins. I’ll add a few practical moves you can do this week to turn the score into action and measurable retention.

What you’ll need (quick checklist)

• Product events: login timestamps, key feature counts, session length.
• Support records: ticket count, open time, resolution hours, and transcript text.
• Customer metadata: plan tier, tenure, ARR/MRR, account owner.
• Clear churn label from billing and dates for at least 6–12 months.

Step-by-step: a practical playbook

1. Assemble a weekly customer table with simple aggregates: DAU/WAU, sessions/week, top-3 feature uses, tickets_last_30d, avg_resolution_hours, sentiment_score.
2. Create a rules-based risk score first: e.g., no-login 14+ days = +30 pts; feature adoption drop >50% = +25; 2+ tickets unresolved = +20. Rank customers and pick top 10%.
3. Train a lightweight model (decision tree or logistic) using those same features and compare Precision@Top10% vs the rules baseline.
4. For each flagged customer return: risk score, top 3 drivers (plain English), and one recommended playbook (one-sentence action the CS rep can take now).
5. Run a pilot: randomize top-10% list into treatment (proactive outreach) and control, measure churn after 30–60 days and calculate lift.

Small example (operational)

• Customer A: risk 82 — drivers: inactivity (last login 21 days), drop in feature X usage, 1 unresolved ticket. Playbook: “Call to check blockers + offer 20-min walkthrough on feature X.”
• Customer B: risk 67 — drivers: repeated negative sentiment in transcripts, downgrade last month. Playbook: “Schedule renewal prep and discuss value gaps; escalate to CSM lead.”

Common mistakes & fixes

• Mistake: Alerts without clear owner. Fix: assign alert to an owner and include next step in the alert.
• Mistake: Too many false positives. Fix: optimize for Precision@Top10% and tighten thresholds.
• Mistake: No retraining cadence. Fix: retrain monthly and fold outreach outcomes back into labels.

1-week action plan

1. Day 1: Pull 6 months of data into a single sheet.
2. Day 2: Build weekly aggregates and the simple rules-based score.
3. Day 3: Run the AI prompt below on transcripts to extract sentiment drivers and themes.
4. Day 4: Train a basic model and compare Precision@Top10% vs rules.
5. Day 5: Create 3 one-click playbooks and assign ownership.
6. Day 6–7: Launch a 50–100 account pilot and measure for 30 days.

Copy-paste AI prompt (use with your LLM to analyze transcripts or suggest features):

“You are an expert customer success analyst. Given this dataset with fields: customer_id, week_start_date, weekly_active_users, avg_session_length_minutes, feature_A_count, feature_B_count, support_ticket_count_30d, avg_ticket_resolution_hours, transcript_text, sentiment_score, plan_tier, tenure_months, churn_label (0/1). Identify the top 12 features predictive of churn, explain why each predicts churn in plain language, propose simple threshold rules for each (for a rules-based score), and suggest one actionable playbook for CS when that feature is the primary driver.”

Final reminder: Start small, prove impact, then scale. A working rules-based score plus one clear playbook will win trust faster than a perfect model on a whiteboard.

Spot on: ramping AI from friendly to tough gives you the right kind of friction. Let’s layer in a few pro moves so you walk in with a tight opener, a clear package, and replies that land.

Try this now (2–3 minutes)

Copy-paste into any chat AI, then test your opener:

“You are my negotiation opener coach. Offer: [$85,000]. Target: [$100,000]. Priorities: [base pay, 6-month review]. Write 3 versions of a 20-second opener. Score each (clarity, confidence, specificity). Combine the best into one polished 1–2 sentence opener I can say out loud. Keep it calm and collaborative.”

What you’ll need

• Offer, target, and your top two priorities.
• Two impact examples with numbers (revenue, savings, growth).
• 10–30 minutes and a quiet spot to rehearse.

Step-by-step (practical and fast)

1. Build your one-page brief (5–7 min). Paste this and fill brackets:”Turn the details below into a one-page negotiation brief. Inputs: Offer: [85k]. Target: [100k]. Role: [Senior Marketing]. Top 2 priorities: [base, 6-month review]. Impact examples: [Grew pipeline 32% in 9 months; Cut CAC 18%]. Constraints I’ve heard: [budget, internal equity]. Output with headings: (1) 3 impact bullets with numbers, (2) Primary ask (one line), (3) Fallback package (one line), (4) 2-sentence rationale, (5) 3 likely objections + best short replies, (6) Calm closing line. Keep it concise and ready to read aloud.”
2. Role-play with debriefs (10–15 min). Do three rounds, each 5–6 exchanges. After each, ask for feedback on where you hesitated and how to tighten responses.Copy-paste prompt:”Play a hiring manager. Start with an $85k offer. Push on budget and internal equity. Ask about my priorities and press for trade-offs. Keep exchanges short and realistic (no fluff). After 6 turns, give a debrief: (a) what likely worked, (b) where I weakened my position, (c) one stronger phrasing for my primary ask and my fallback.”
3. Price the package (3–5 min). Have AI convert bonuses, sign-on, and vacation into an annual equivalent so you can compare apples to apples.Prompt:”I’m comparing compensation packages. Assume base: [$85k vs $100k]. Sign-on: [$7k]. Bonus target: [10%]. Vacation: [15 vs 20 days]. Benefits are similar. Calculate after-tax rough equivalents using simple, transparent assumptions. Show: (1) year-1 total value for each package, (2) ongoing annual value, (3) the break-even difference. Note any assumptions clearly so I can adjust.”
4. Make it forwardable (5 min). Managers often need to pass your note to HR/Finance. Ask AI to write a short, quotable email that tells your story in bullets.Prompt:”Write a concise, forwardable counteroffer email. Tone: grateful, confident, collaborative. Structure: (1) thanks, (2) one-line primary ask [$100k], (3) 2 impact bullets with numbers, (4) if salary is tight: fallback package [+$7k sign-on + 6-month review with clear goals], (5) close with next step and openness. Keep to 130–170 words, short paragraphs, easy to forward without edits.”
5. Rehearse aloud (3 min). Read your opener twice. Then practice this closing line: “If we can align at [$100k] or the fallback package, I’m ready to sign and start strong.”

Example you can model

Manager: “We’re at $85k due to internal equity.”You: “I appreciate the context. Given the 32% pipeline lift and 18% CAC reduction I’ve delivered, $100k is aligned with market and the impact I can bring. If base is tight today, I’m comfortable with a $7k sign-on and a 6‑month review tied to pipeline and CAC targets.”

Insider tricks that quietly move numbers

• Anchor with a reason. State your number then give a short why. Number + reason beats number alone.
• Ask for the approval path. “What steps are needed to approve this?” This turns a no into a process you can navigate.
• Package, don’t pile. One primary ask, one clearly defined fallback. It’s easier to approve.
• Use future focus. Tie the review to 2–3 measurable goals so the bump feels earned and schedulable.

Common mistakes & fixes

• Overexplaining. Fix: Say the number, give one reason, stop. Let silence work.
• Negotiating against yourself. Fix: Make an ask, wait for a response. Don’t lower it preemptively.
• Vague impact. Fix: Two bullets with numbers. That’s enough.
• All salary, no plan B. Fix: Have a single fallback package ready.
• Verbal-only agreements. Fix: Ask for the updated written offer immediately after alignment.

24-hour action plan

1. Build your one-page brief with the prompt above (7 min).
2. Run 2 role-plays: normal, then tough (10–12 min). Use the debrief to sharpen phrasing.
3. Price your package so you know your walk-away (5 min).
4. Generate the forwardable email and save it as a template (5 min).
5. Rehearse opener + closing line twice (3 min). Done.

Bonus prompt — objection flashcards

“Create objection-response flashcards for salary negotiation. Use these likely objections: [budget, internal equity, team parity, headcount freeze, timing]. For each, write: (1) the objection in 1 line, (2) my calm 1–2 sentence reply with a number, (3) a follow-up question that moves us forward. Keep them concise so I can memorize in 5 minutes.”

Remember: your goal isn’t a perfect script; it’s a clear, confident ask with a practical fallback. Use the AI to compress your thinking, then bring your human calm and presence to the call.

Quick win (try in under 5 minutes): Open your calendar and create a single 60‑minute event tomorrow titled Deep Work — Do not schedule set to Busy. That tiny test tells you how it feels and how colleagues react.

One small correction first: instead of excluding “any time with events that have attendees,” exclude events with multiple attendees or company all‑hands. Allow personal reminders or single‑attendee blocks you created yourself. That prevents the automation from being overly strict and missing usable free time.

What you’ll need

• A primary work calendar (Google Calendar or Outlook).
• An automation option: simple recurring event, Zapier/Make, or a short Google Apps Script for Google users.
• Clear rules: days, preferred windows, minimum block length, and exclusions (multi‑attendee/recurring events).
• A one‑line team note to explain the label so colleagues respect holds.

Step-by-step setup (non‑technical)

1. Decide rules: e.g., one 90‑minute block each weekday between 9:00–12:00; minimum 60 minutes if you want gentler start.
2. Pick your path: simple = recurring manual event; medium = Zapier/Make that runs daily and creates the hold; advanced = small script using calendar API.
3. If using Zapier/Make: schedule a daily trigger early morning, scan free/busy for the window, pick the largest slot ≥ minimum, then create an event titled “Deep Work — Please do not schedule” set to Busy and add a one‑line description.
4. Run pilot week: create those events as Tentative first week so you can review conflicts, then flip to Busy if it’s working.
5. Share a short note with your team: why the block exists and how to handle urgent meetings.

Practical AI assistant prompt (copy‑paste)

“You are an assistant with access to my Google Calendar. Each weekday at 6:00AM local time, scan my primary calendar for the largest continuous free slot of at least 90 minutes between 9:00AM and 12:00PM. Exclude any time that has events with more than one attendee, events marked recurring, or events set to Busy. If a slot exists, create an event titled ‘Deep Work — Please do not schedule’, set its status to Busy, add description: ‘Scheduled focus time — avoid scheduling unless critical’, and add a 10‑minute buffer before and after. For the first 7 days create events as Tentative. Log created events and any conflicts to a daily note.”

Example

• Rule: one 90‑minute block M–F, 9–12 window.
• Automation finds a 10:30–12:00 free slot and creates Busy event titled “Deep Work — Please do not schedule”.
• First week events are Tentative; you confirm or adjust.

Common mistakes & fixes

• Too many or too long holds → cut length to 60 minutes or only 3x/week.
• Automation overwrites important recurring meetings → add explicit rules to exclude recurring and multi‑attendee events.
• Colleagues keep scheduling anyway → add a one‑line description and send a short team note explaining the policy.

7‑day action plan

1. Day 1: Create a manual 60‑minute deep‑work block tomorrow (quick win) and draft your team note.
2. Day 2: Build automation in Zapier/Make or set up a simple script; make events Tentative.
3. Days 3–7: Run pilot, record whether each block stayed uninterrupted and your focus score (1–5).
4. End of week: Review results. If hold acceptance ≥70% and average focus ≥3.5, flip to Busy and scale frequency.

Start small, measure impact, then expand. The aim is to protect rhythm — not to build rigid rules that break around real teamwork.

Good call — your emphasis on a quick triage followed by a rules-based follow-up is exactly the high-leverage move. AI speeds the decision so you act, not stall.

Why this helps

Small choices add up. A 30–45 minute session + a 5–10 minute monthly tidy will cut noise, keep what matters, and protect your attention.

What you’ll need

• Your phone (iPhone or Android) and a notes app or paper.
• An AI assistant you trust (ChatGPT, Bard, or your phone assistant).
• 30–45 minutes for the first pass; 5–10 minutes monthly for upkeep.

Step-by-step

1. Quick inventory (10–15 min): Scan home screens and the full app list. Jot apps into three buckets: Daily / Occasional / Rare.
2. AI audit (5–10 min): Paste the list into the AI prompt below. Ask it to label each app: Keep / Combine / Delete / Move to folder and recommend notifications: Allow / Silence / Critical only.
3. Immediate wins (10 min): Uninstall or hide 1–3 rare apps, move related apps into one folder, silence marketing/shopping alerts.
4. Set 3 rule groups (5 min): Essential (calls, bank, health), Work (email/calendar windows), Quiet (social, deals). Apply AI recommendations to these groups.
5. Test for 7 days: Don’t fully delete—offload or hide first. Restore if you really miss it.
6. Automate review: Add a monthly 5–10 minute calendar reminder to reassess new installs and notifications.

Copy-paste AI prompt (use exactly)

“You are a friendly phone-declutter assistant. Here is my list of apps: [paste apps]. My priorities: 1) reduce distractions, 2) keep essential tools (banking, health, messaging), 3) keep social media but limit it to once per day. Please: 1) Categorize each app as Keep / Combine / Delete / Move to folder; 2) Give a short reason for each choice; 3) Suggest a notification setting for each app (Allow / Silence / Critical only); 4) Create a simple 7-step implementation plan I can finish in 20 minutes.”

Prompt variants

• Short audit: “Audit these apps to reduce distractions. Label each app Keep/Remove/Combine and give one-line reasons.”
• Notifications only: “Recommend notification rules so I only get essential alerts between 8am–8pm. Group apps into Essential / Work / Quiet.”

Example AI output (what to expect)

• Move 5 social apps into one folder labelled Social; set them to Silent with a daily summary at 7pm.
• Delete duplicate weather and flashlight apps; keep built-in tools.
• Allow Critical for banking and health; silence promotional shopping notifications.

Common mistakes & fixes

• Mistake: Deleting an app you need. Fix: Offload or hide first, test for a week.
• Mistake: Overcomplicating rules. Fix: Start with three simple groups and revise after 7 days.
• Mistake: Doing everything at once. Fix: Aim for 3 small changes per session.

30-minute action plan

1. Make an app list (10 min).
2. Run the main AI prompt (5–10 min).
3. Apply 3 quick changes: uninstall/hide one app, silence two apps, make one folder (10 min).

Reminder: Aim for progress, not perfection. Small, repeatable habits will reclaim your attention faster than a one-time purge.

Quick win: In under 5 minutes you can run a focused role-play with an AI. Copy the prompt below into any chat AI and practice your opening line until it feels natural.

Good call starting this thread — role-playing is one of the fastest ways to build confidence for salary talks. Below is a practical, step-by-step method to rehearse, refine counteroffers, and avoid common mistakes.

What you’ll need

• A computer or phone and access to a chat AI (any chat model will do).
• Basic offer details: current salary, offered salary, target salary, top 2 priorities (money, flexibility, title, bonus).
• 15–30 minutes to practice and iterate.

Step-by-step

1. Open the chat AI and paste the role-play prompt below (first prompt is for practicing with the hiring manager).
2. Respond as you would in the meeting. Keep answers short and calm. Ask the AI to be tougher each round.
3. Switch roles: ask the AI to be you and practice the manager’s replies so you can craft better counter-points.
4. When you’re happy, paste the email counteroffer prompt (second prompt) to generate a clear, professional message.
5. Save your best lines and rehearse them out loud two or three times.

Copy-paste prompt — role-play (paste this into the AI):

“You are the hiring manager for a senior marketing role. I have an offer of $85,000 but my target is $100,000. Role-play a 5-exchange negotiation. Start by offering the $85k and include typical objections and concessions (budget limits, internal equity). Ask questions to learn my priorities. Be candid and realistic.”

Copy-paste prompt — counteroffer email:

“Write a concise, professional counteroffer email. I’m grateful for the offer of $85,000. My target is $100,000 based on market data and my 10 years of experience delivering results. If salary flexibility is limited, propose a performance bonus or additional vacation and clear review in 6 months. Keep tone collaborative, 4 short paragraphs.”

Example snippet you can expect

Manager: “We’re at $85k due to budget.” You: “I appreciate that. My market research and past results support $100k. If salary is fixed now, can we agree on a $7k sign-on and a 6-month review tied to specific goals?”

Common mistakes & fixes

• Mistake: Being vague. Fix: Use specific numbers and examples of impact.
• Mistake: Getting emotional. Fix: Practice neutral, confident language in the AI role-play.
• Mistake: Accepting first offer. Fix: Always ask for time and present one clear counter.

Action plan (next 24 hours)

1. Gather your offer and list priorities (15 min).
2. Run 2–3 AI role-play rounds (10–20 min).
3. Refine a single counteroffer and generate the email (10 min).
4. Practice aloud twice before the call (5 min).

Remember: negotiate the outcome you want, not a perfect script. Use the AI to sharpen your messages, then bring your human calm and confidence to the conversation.