aaron

Nice call: keeping AI as an assistant, not a controller, is the single best way to keep a productivity system minimal and sustainable.

The problem: most people add apps and rules until the system itself becomes the bottleneck. That wastes time and erodes discipline.

Why this matters: the goal is predictable outcomes — done work that advances priorities — not an impressive task database. Minimal systems reduce decision fatigue and increase follow-through.

Short lesson: start with one capture place, one calendar, one daily rule (3 priorities), and an AI that compresses triage. You’ll tune rules, not tools.

Checklist — do / do not

• Do: capture everything in one place, enforce a 3-priority daily cap, block calendar time for important work.
• Do: run a 10-minute daily triage with AI and a 20-minute weekly review.
• Do not: keep multiple task apps, over-schedule your day, or skip pruning for 90+ days.

Step-by-step (what you need, how to do it, what to expect)

1. What you’ll need: one capture app or notebook, one calendar, a chat-style AI you can prompt, and a 3-priority rule.
2. How to set up: consolidate captures, sync calendar, program a daily 10-minute prompt to AI for triage, and create a 20–30 minute weekly review slot.
3. How to use: capture instantly, run AI triage each morning, move chosen items into calendar blocks, run focus sessions of 25–60 minutes, save 1–2 sentence summaries via AI after each session.
4. What to expect: first 2–4 weeks of friction as you tune time blocks; then steady reduction in decision time and higher completion rates.

Metrics to track (KPIs)

• Daily priority completion rate (target: 80%+ of 3 priorities).
• Average time spent in daily triage (target: ≤10 minutes).
• Weekly completed tasks vs. planned tasks (target: 70%+).
• Stale items archived per 2-week prune (target: ≥20% of backlog pruned).

Common mistakes & fixes

• Keeping many apps — fix: consolidate to one capture and one calendar immediately.
• Ignoring summaries — fix: enforce the 1–2 sentence AI summary after each focus session; use them in weekly review.
• Overloading the day — fix: honor the 3-priority rule and make remaining items optional buffer tasks.

Worked example

Scenario: You need to prepare a quarterly report, reply to 12 emails, and coach a team member. Capture: you jot these items into your capture app. Morning triage: AI suggests breaking the report into a 90-minute outline session + two 45-minute drafting blocks, marks 6 urgent emails to answer (5–10 minute batch), and schedules a 60-minute coaching slot. You accept, AI creates calendar blocks, you work in focused sessions, record short summaries, and the weekly review shows the report 80% complete.

1-week action plan

1. Day 1: Consolidate capture into one place. Set calendar rules (no meetings during first priority block).
2. Day 2: Create AI triage prompt and use it for your morning session; schedule 3 priorities into calendar.
3. Day 3–5: Run focused sessions, save 1–2 sentence summaries. Track completion rate daily.
4. Day 6: Weekly review with AI; prune items older than 90 days.
5. Day 7: Adjust one rule if metrics show miss (e.g., change focus block length).

AI prompt (copy-paste)

“I have these new capture items: [paste items]. I have 4 hours available today in two blocks (90m morning, 150m afternoon). Apply my rules: pick up to 3 priorities based on deadline and impact, break large tasks into next actionable steps, and return a calendar schedule with durations (minutes) and a 1-sentence goal for each block. Also flag any items older than 90 days for pruning.”

Your move.

Cut the noise, ship the work: a long email thread becomes a short, owned list in 10 minutes. The difference between “summary” and “shipped” is a two-pass AI extraction, tentative owners, and a 48-hour confirmation window.

The real problem: Summaries are easy; commitments are not. Threads bury asks, duplicate requests, and fuzzy deadlines. If you don’t convert language into ownership, the work stalls.

Why this matters: Clear owners and dates reduce reply-all churn, speed decisions, and cut rework. Do this right and you’ll see fewer follow-ups, faster cycle times, and cleaner accountability.

What I’ve learned: A two-pass AI flow beats a one-pass summary. Pass 1 extracts candidates. Pass 2 normalizes, dedupes, adds priorities, and outputs a spreadsheet-ready list. Pair that with “tentative owner + confirm/reassign in 48 hours,” and you move from vague asks to delivered outcomes.

What you’ll need:

• Cleaned thread (keep one-line sender + timestamp for each message; remove duplicate quoted text).
• Participant roles (1 line per person: name, role, area).
• A simple spreadsheet or task list (columns: Owner, Task, Due, Priority, Dependencies, Status).
• Any AI assistant you trust (email client, cloud, or local/private model).

Two-pass method (practical steps and what to expect)

1. Prep (3–5 min): Clean the thread; keep sender/timestamps. Draft a roles list (e.g., “Kara – Finance lead; Leo – Product manager; Maya – Marketing”). Expect cleaner AI output and fewer misassignments.
2. Pass 1 – Extract (1–2 min): Run the prompt below to pull all potential actions, decisions, and open questions. Expect 80–90% capture; some items will be rough.
3. Pass 2 – Normalize (1–2 min): Feed Pass 1 output back to the AI to dedupe, set priorities, suggest due dates, and produce a CSV-style list you can paste into a sheet. Expect a tidy, scannable list.
4. Human check (3–5 min): Adjust any wrong owners or unrealistic dates, add dependencies, and tag 3–5 High-priority items.
5. Follow-up mail (2–3 min): Send one short note listing items with tentative owners and a 48-hour confirm/reassign request. Expect quick confirmations and reassignments on unclear tasks.
6. Track & nudge (ongoing): Paste the CSV into your sheet, add Status (Not started, In progress, Done). Nudge anything unconfirmed after 48 hours.

Copy-paste AI prompt (Pass 1 – Extraction)

Here is a cleaned email thread plus a list of participants and their roles. Extract three lists: 1) Action Items, 2) Decisions Made, 3) Open Questions. For each Action Item, provide: Owner (most likely; mark as Tentative if unclear), Task (one sentence, start with a strong verb), Suggested Due Date (tentative if not explicit), Priority (High/Med/Low), Dependencies (if any), and Source (sender + timestamp). Keep it concise and complete. Then list any ambiguities or missing info that would block execution.

Copy-paste AI prompt (Pass 2 – Normalize + CSV)

Using the extracted lists below, remove duplicates, merge overlapping tasks, and standardize wording. Output the final Action Items as CSV lines with headers exactly: Owner, Task, Due, Priority, Dependencies, Source, Notes. Keep Owner as a single name and mark Tentative if needed. Keep 7–10 items per page if long. Also summarize in 3 bullets the top dependencies and the 3 highest-risk items.

Follow-up email template (drop in your thread)

• Subject: Actions and confirmations — [Thread topic]
• Body opening: “Below are the actions from the thread. Owners are tentative; please confirm or reassign within 48 hours.”
• List format: “Owner — Task — Due — Priority (Confirm/Reassign)”
• Closing: “Reply with ‘Confirm’ or ‘Reassign: Name’. If a date is off, propose a new one.”

Insider tricks that improve results

• Role mapping upfront: Add a one-line role per person; it dramatically reduces owner errors.
• Set due-date defaults: If no date is stated, use a policy: “Small tasks (<30 min) due next business day; others by EOW.” The AI can apply this rule consistently.
• Decision log: Ask the AI to list “Decisions Made” separate from “Actions.” Prevents backtracking.
• Dependencies first: Have the AI flag blockers; sequence High-priority items that unlock others.

Metrics to track (make the win visible)

• Owner confirmations within 48 hours (target ≥90%).
• Average time to close per item (baseline week 1; aim for -20% by week 3).
• Reply-all volume on the thread after the follow-up (target -50% in two weeks).
• Read-to-action ratio: number of actions completed per 100 emails read (target +30%).

Common mistakes and fast fixes

• Mistake: AI summary with no owners. Fix: Always require Owner — Task — Due — Priority; allow Tentative + 48-hour confirm.
• Mistake: Vague verbs (“look into”). Fix: Replace with concrete verbs (Decide, Send, Schedule, Confirm, Draft, Approve).
• Mistake: Unrealistic dates. Fix: Apply due-date defaults; invite owner to counter with a feasible date.
• Mistake: Sensitive content in external tools. Fix: Redact or use an internal/local assistant.

1-week action plan

1. Day 1: Run the two-pass method on two live threads; send the follow-up with 48-hour confirm/reassign.
2. Day 3: Update the sheet with confirmations, adjust owners/dates, and note any recurring ambiguities.
3. Day 4: Tweak prompts (tighten verbs, add role lines) and set due-date defaults in your template.
4. Day 5: Repeat on three new threads; start tracking KPIs (confirmations, reply-all reduction, time-to-close).
5. Day 7: Review KPIs vs baseline; keep what works, drop what doesn’t, and standardize the template for your team.

Give the AI structure, force ownership, and time-box confirmations. That’s how you turn threads into results.

Your move.

Hook: Want ad creative that converts without overthinking? Use AI to generate volume, then be the editor who turns ideas into measurable winners.

The problem

Most teams either waste time staring at a blank page or spray-and-pray with untested creative. AI fixes the blank page — but without a process you’ll drown in variants and miss what actually moves the needle.

Why this matters

Volume + focused testing = faster learning. Produce dozens of clean, platform-ready options, test the highest-potential pieces, then scale what proves out. That reduces wasted ad spend and shortens the path to a profitable campaign.

My single biggest lesson

AI isn’t a replacement for judgement — it’s a multiplier. The best results come when AI feeds a disciplined brief and a tight test plan.

Checklist — do / do not

• Do: create a 60–90 second brief (objective, audience, 3 benefits, tone, limits).
• Do: generate 20–30 variants and reduce to 6–8 for testing.
• Do: human-edit claims and compliance before launch.
• Do not: run full budgets on untested winners.
• Do not: assume every AI claim is legally safe.

Step-by-step (what you’ll need, how to do it, what to expect)

1. Gather inputs: objective, audience (age, location, one pain point), 3 benefits, tone, asset placeholders, platform constraints.
2. Use a single AI prompt to generate: 15 headlines (<=30 chars), 10 body lines (15–90 chars), 5 visual directions, and 5 short video scripts (15–30s).
3. Score outputs for relevance (1–5) and novelty (1–5). Pick top 6–8 combos and human-edit for brand + legal.
4. Format to specs: Facebook/IG (short hook + CTA), Google RSA (multiple 30-char headlines + 90-char lines), Display (overlay text + visual direction).
5. Test: run 3 creatives (1 variable at a time) for 7–10 days on small budgets, then pause losers, double down on winners.

Metrics to track (KPIs)

• CTR (engagement signal).
• Conversion rate (lead or sale).
• CPA or Cost per Lead/Sale.
• ROAS (if e-commerce).
• Creative fatigue: impressions-per-click deterioration over time.

Common mistakes & fixes

• Mistake: testing too many variables. Fix: isolate headline OR image.
• Mistake: skipping legal review. Fix: flag claims in the brief and remove absolutes.
• Mistake: poor brief = poor results. Fix: include real audience insight and 1 performance example.

Worked example (quick)

Product: cordless kettle, 30-day money-back. Audience: busy professionals, 30–55, UK.

• Sample headlines: “Boil in 90s”, “Save 10 mins each morning”.
• Body lines: “Quiet boil, fast pour.”
• Visual direction: “Close-up steam pour; overlay ‘Ready in 90s’ — warm kitchen, morning light.”

Copy-paste AI prompt (use and adapt)

Write 15 ad headlines (max 30 characters each), 10 short body lines (15–90 characters), 5 image directions, and 5 scripts for 15–30s videos for Facebook and Google Search. Product: cordless kettle. Objective: sales. Audience: busy professionals 30–55, UK, who want faster mornings. Benefits: boils in 90 seconds, cordless pour, 30-day money-back guarantee. Tone: friendly, confident. Include notes next to any claim that requires verification (e.g., “verify boiling time”). Provide platform notes for Facebook (short emotional hook + single CTA) and Google RSA (headline + 90-char description).

1-week action plan (day-by-day)

1. Day 1: Create the brief (10–15 minutes) and run the prompt.
2. Day 2: Score outputs, pick top 8, human-edit for compliance (30–60 minutes).
3. Day 3: Format to platform specs and create ad sets (60–90 minutes).
4. Days 4–10: Run three small A/B tests (daily checks). After day 7, pause losers and scale the top performer.

Expect initial learnings within 7–10 days and a clear winner to scale by week 2. Track CPA and conversion lift as your north stars.

Your move.

Hook: Add one layer: a “shadow” AI score that runs alongside your rules and writes your dispute evidence for you. Expect faster decisions, fewer false positives, and tighter packets when disputes land.

Problem: Rules alone overblock or miss patterns. Manual reviews eat time. Evidence is scattered, so you lose winnable disputes.

Why it matters: A few avoided chargebacks and a higher dispute win rate lift margin and keep your processor happy. This is a light workflow upgrade, not a new platform.

Lesson: Keep rules for precision, add AI for context (messages, timing, device). Run AI in “shadow mode” for 1–2 weeks to learn, then let it guide verification tiers. Don’t auto-cancel; route to the right next action.

Do / Do not

• Do weight your rules (billing≠shipping, value bands, velocity) and let AI add context from customer messages and timing.
• Do tier verification by order value: SMS confirm for mid-tier; signature/photo-on-delivery for top-tier.
• Do maintain allowlist (repeat good buyers) and denylist (confirmed fraud devices/emails).
• Do timestamp all contact attempts; store proof in a single PDF per transaction ID.
• Do run a 24-hour hold rule: no verification → refund and cancel to prevent chargebacks.
• Don’t decline only on country mismatch; combine with value, velocity, device, and message signals.
• Don’t skip delivery proof on high-value orders; require signature/photo.
• Don’t let AI auto-reject; it recommends, you decide.

What you’ll need

• Order export with billing/shipping, order value, transaction ID, tracking.
• IP/device data, customer messages, phone/email, delivery proof (photo/signature).
• A spreadsheet or ticket for: rule flags, AI one-line summary, and a link to the PDF evidence pack.

How to do it (step-by-step)

1. Set weighted rules: start with +30 points if billing≠shipping, +25 if order>3x AOV, +20 if velocity (3+ orders/cards same IP in 24h), −25 if repeat buyer with clean history. Anything ≥40 = hold. Expect 10–25% false positives at the start.
2. Shadow AI scoring (no automation yet): for each flagged order, have AI produce a risk score, top reasons, and a single recommended action (ship, hold+verify, cancel+refund). Paste the summary into the ticket.
3. Evidence automation: standardize a 1-page packet: receipt, tracking screenshot, transaction ID, verification log, and delivery photo/signature. Export to a single PDF named with the transaction ID.
4. Tiered verification: Mid-tier (1–3x AOV) = SMS confirm; top-tier (>3x AOV) = SMS + signature-on-delivery; international or high-risk device = add phone call attempt.
5. Calibrate weekly: compare AI vs your final decision. Lower rule points that cause false positives; whitelist loyal buyers; add denylist for confirmed bad devices/emails.

Robust copy-paste AI prompt (use as-is)

Prompt: You are an e-commerce fraud analyst. Using the order data below, return both a concise human summary and a machine-readable JSON. Consider rules (billing vs shipping, value vs AOV, velocity, device/IP country), message tone/timing, delivery status, and my business costs. Data: {order_id, order_value, average_order_value, billing_country, shipping_country, ip_country, card_country, device_type, attempts_last_24h, customer_message, time_since_order_hours, customer_is_repeat, tracking_status, margin_rate, shipping_cost, potential_chargeback_fee}. Output 1 (human): risk score 0–100, top 3 reasons (short), and one recommended action: ship_now, hold_and_verify, cancel_and_refund — plus 3 one-line verification steps I can do in under 90 seconds. Output 2 (JSON): {“risk_score”:int, “reasons”:[…], “recommended_action”:”ship_now|hold_and_verify|cancel_and_refund”, “expected_loss_if_ship”:number, “expected_loss_if_hold”:number, “expected_loss_if_cancel”:number}. Optimize for the lowest expected loss while minimizing false positives with repeat customers.

Worked example

• Input snapshot: order_id=7842; order_value=$650; AOV=$95; billing=CA; shipping=US; ip_country=US; device=mobile; attempts_last_24h=3; message=“Need it by Friday, can you ship to my office?”; time_since_order=1.2h; repeat=false; tracking_status=not_shipped; margin=35%; shipping_cost=$18; chargeback_fee=$25.
• Expected AI output (human): Risk 72/100. Reasons: high value >3x AOV; billing≠shipping; 3 attempts from same IP. Action: hold_and_verify. 90-second checks: 1) SMS: “Reply YES to confirm delivery address.” 2) Call once and log outcome. 3) Request last 4 digits of card to match gateway partial (if supported).
• Decision: If verified within 60–90 minutes, ship with signature-on-delivery. If no reply in 24 hours, cancel+refund.

What to expect

• Dispute packet prep drops from 15–30 minutes to <5 minutes per case.
• False positives fall week-by-week as allow/denylists mature.
• Biggest ROI comes from stopping a few top-tier orders; track prevented loss by value.

Metrics and KPIs

• Chargeback rate; dispute win rate.
• % orders flagged; false-positive rate (verified within 1 hour).
• Verification conversion rate (replies within 90 minutes).
• Time to assemble evidence; average expected loss avoided per flagged order.
• Shadow AI vs human agreement rate; actions changed after AI review.

Common mistakes & fixes

• Mistake: Treating AI as the decision-maker. Fix: Keep human-in-the-loop; AI suggests, you decide.
• Mistake: Static thresholds that punish loyal buyers. Fix: Whitelist repeat customers and reduce score weight for their orders.
• Mistake: Weak delivery proof. Fix: Signature/photo-on-delivery for high-value orders; store in the PDF.
• Mistake: Poor logs. Fix: Timestamp all contact attempts; add to evidence packet automatically.

1-week action plan

1. Day 1: Turn on weighted flags; build the 1-page evidence template; name files by transaction ID.
2. Day 2: Start shadow AI scoring on all flagged orders; paste the one-line summary into tickets.
3. Day 3: Implement tiered verification bands; require signature/photo for top-tier.
4. Day 4: Create allow/deny lists from last 60 days; lower priority for allowlisted buyers.
5. Day 5: Review 10 shadow decisions vs your actions; adjust rule weights ±5–10 points.
6. Day 6: Measure KPIs; set targets: false positives <15%, verification reply rate >60%.
7. Day 7: Document the 24-hour hold policy and dispute packet SOP; train the team.

Your move.

Want product descriptions that actually sell — not read like every other listing? Do this in short sprints and test the results.

The problem: AI often produces safe, generic copy that sounds like every other product page. That kills differentiation and lowers conversion.

Why it matters: On product pages, clarity + credibility drive clicks and cart adds. A 10–20 minute edit that leads with customer outcome and one proof point will lift engagement — and gives you copy you can A/B test immediately.

What I’ve learned: Short, benefit-led headlines plus two supporting sentences outperform long feature dumps. Use AI to generate options; use a human edit to add a single sensory detail or specific proof point.

What you’ll need

• Product name
• One clear customer benefit (what they gain)
• One proof point (material, number, rating, guarantee)
• 15–20 minutes per product

Step-by-step (do this now)

1. Set a 15-minute timer for one product.
2. Write a benefit-led headline: lead with what the customer gets.
3. Add two short sentences: first = how it delivers the benefit; second = proof or risk-reducer.
4. Ask AI for three angles (practical, emotional, aspirational). Pick one and ask AI to shorten to 20–30 words.
5. Edit: swap one generic word for a concrete detail (time, material, number) and add a single objection line if space allows.

Do / Do-not checklist

• Do lead with benefit; be specific (hours, material, rating).
• Do keep sentences short and scannable.
• Do-not drown copy in every feature — highlight one supporting detail.
• Do-not use vague superlatives without proof.

Worked example — Orthopedic Pillow

Headline: Wake up pain-free — cervical support that restores your morning.

Description: Contoured memory foam aligns the neck to reduce pressure while you sleep. Clinically tested comfort foam and a 90-night trial mean you try it risk-free.

Copy-paste AI prompt (use as-is)

Act as an ecommerce copywriter. Write three short product descriptions for an orthopedic pillow. Each description should be: one benefit-led headline plus two short sentences (20–30 words). Deliver three angles: practical, emotional, aspirational. Include one proof point per description (material, hours, clinical test, or trial). Keep language simple and specific; avoid vague adjectives.

Metrics to track

• Headline CTR (or email subject CTR) — target a measurable lift vs baseline (aim for +10–30%).
• Add-to-cart rate on product page.
• Conversion rate (product view → purchase) and revenue per visitor.
• Time on page and bounce rate for qualitative signal.

Mistakes & fixes

• Too generic? Add a concrete number or material.
• Too technical? Translate the feature into a real-life outcome.
• Sounding robotic? Add one sensory word or a short risk-reducer (trial, guarantee).

1-week action plan

1. Day 1: Run three 15-minute sprints for your top 6 SKUs.
2. Day 2–3: A/B test headline A vs B on 3 SKUs (product page or email).
3. Day 4–6: Keep winners, roll to next set of 6; track CTR and add-to-cart.
4. Day 7: Review lifts, pick 3 repeatable templates to use for next month.

Your move.

You nailed the backbone: a firm opening instruction and a one-line recovery keeps the AI in tutor mode. Let’s turn that into a results system you can run on autopilot — tight constraints, adaptive difficulty, and clear KPIs.

Hook: If it asks better questions, you think better. If it wanders or answers, you don’t improve. We’ll lock in the first and eliminate the second.

Problem: Most “Socratic” sessions drift — questions get bloated, difficulty stays flat, and there’s no measurable outcome.

Why it matters: You want durable understanding you can use on a real task in under 15 minutes. That requires guardrails, adaptation, and a quick action to cement learning.

Field lesson: Best results come from three moves — constrain the format, adapt difficulty based on your confidence, and end with a 10-minute task. Think of it as a small workout with a clear rep count.

Do / Do not

• Do set “questions-only” with a recovery line and a word cap per question.
• Do specify topic, single outcome, and session length before starting.
• Do rate your confidence 1–5 after each answer to drive difficulty up/down.
• Do request one practical 10-minute task at the end.
• Do keep each question under 25 words and one idea.
• Don’t allow the AI to explain unless you ask for a “hint.”
• Don’t accept multi-part or vague questions — ask it to split or anchor to your goal.
• Don’t run beyond 20 minutes; frequency beats length.

Copy-paste prompt (premium version with adaptive difficulty)

“You are my Socratic tutor. Ask only questions — no explanations or answers unless I type ‘hint’. Session rules: 5 questions total, one at a time, each under 25 words. Labels: Q1 Recall, Q2 Understand, Q3 Apply, Q4 Scenario decision, Q5 Reflect. After each of my answers, ask me to rate confidence 1–5 in parentheses. If my confidence ≤2, step difficulty down one level; ≥4, step up one level. If I type ‘stuck’, ask two simpler diagnostic questions, then resume. Track unclear terms silently and at Q5 ask me to choose one for a 10-minute practice. Recovery line: If you output anything other than a question, I will paste ‘Tutor mode’ — resume questioning immediately.”

What you’ll need

• Any AI chat tool.
• One-line topic and one outcome (example: “Understand monthly compound interest well enough to estimate returns”).
• 10–20 minutes of quiet time.

Step-by-step (run it)

1. Paste the prompt above. Then state topic + outcome + time limit.
2. Answer each question in 2–4 sentences; rate confidence (1–5) as requested.
3. Type “stuck” when fuzzy; let the tool drill with two diagnostics.
4. At the reflective close, commit to the 10-minute task it proposes and do it immediately.

What to expect

• Immediate: sharper recall and clarity about your one weak link.
• 2–3 weeks: faster application under time pressure and fewer look-ups.

Worked example (topic: monthly compound interest)

• Q1 Recall: What does “compound monthly” mean in plain English? (Confidence 1–5?)
• Q2 Understand: Which three factors control the growth: principal, rate, time — how do they interact? (Confidence 1–5?)
• Q3 Apply: If you invest $1,000 at 6% APR, monthly compounding, what happens after one month? Estimate. (Confidence 1–5?)
• Q4 Scenario decision: For a 3-year horizon, which matters more: rate increase of 1% or adding $20/month? Why? (Confidence 1–5?)
• Q5 Reflect: What single rule-of-thumb will you use when evaluating offers? (Confidence 1–5?)

Metrics to track (KPIs)

• Sessions per week (target: 3).
• Average confidence trend (target: +1 point by week 2).
• 10-minute practice completion rate (target: 90%).
• First-try success on a real task tied to topic (yes/no, weekly).
• 72-hour retention check: answer one cold question without hints (score 0–2: miss/partial/hit).

Common mistakes & quick fixes

• AI starts explaining: paste “Tutor mode” and continue.
• Questions too long: add “keep to 15–20 words” to the prompt and restart.
• Too easy or too hard: be honest with confidence ratings; the prompt will adjust up/down.
• Drift from your goal: restate outcome and ask “tie the next question to my outcome.”
• No practical transfer: always end with, then do, the 10-minute task.

1-week action plan

1. Day 1: Run one 15-minute session on a single topic. Log baseline confidence and complete the 10-minute task.
2. Days 2–4: Two more sessions on micro-topics. Track confidence trend and retention (answer one cold question the next day).
3. Day 5: Scenario-focused session (decision trade-offs). Do the 10-minute task on a real decision.
4. Day 6: Synthesis session — ask the tutor to stress-test your understanding with an applied question.
5. Day 7: Review KPIs; adjust word cap, difficulty steps, or topic scope based on what stalled.

Insider tip: The confidence prompt is your lever. Treat it like weight on a bar. Push it higher only when answers feel clean and quick; if it wobbles, step down and build form.

Your move.

— Aaron

Smart call-out: the 80% capacity cap plus a 15-minute weekly reset is the engine. Let’s bolt on KPIs and a simple auto-tuning loop so AI not only plans your weeks but also adjusts based on results.

Do / Do not (the guardrails that make AI “automatic”)

• Do cap planned hours at ≤80% of your real capacity; don’t plan to 100% and hope.
• Do tie each week to one measurable KPI; don’t accept vague outcomes.
• Do set a WIP limit: max 3 A-tasks per week; don’t carry 8 “priorities.”
• Do force tasks to ≤90-minute blocks with a verb + output; don’t schedule amorphous work.
• Do front-load decisions and dependencies in Week 1; don’t defer approvals.
• Do calendar every A-task; don’t keep it in a list and hope time appears.
• Do drop at least one task weekly; don’t roll everything forward.
• Do backsolve task volume from KPI math; don’t assume effort equals impact.

What you’ll need

• One-sentence goal + deadline + definition of done.
• Weekly capacity in hours (we’ll plan 80% of it).
• Constraints: people, tools, approvals, dependencies.
• Baseline funnel math if relevant (e.g., outreach → replies → calls).
• Where tasks live: calendar or to-do app.

Planning prompt (copy-paste)

You are my KPI-first planning assistant. Goal: [insert]. Deadline: [date]. Weekly capacity: [hours]. Work windows: [e.g., Tue/Thu 9–11am]. Constraints: [tools, people, dependencies]. Definition of done: [one sentence]. Provide a 4-week plan capped at ≤80% of capacity. For each week: 3–5 tasks (each ≤90 minutes), hour estimates, A/B/C priority (max 3 A-tasks), and one KPI outcome with a numeric target. Backsolve weekly task volumes from assumed conversion rates (state the assumptions). Front-load decisions/dependencies in Week 1. End with: (1) milestone summary, (2) plain checklist to paste into my calendar, (3) risks + mitigations.

Auto-tune prompt (weekly)

You are my weekly planning editor. Planned vs. actual last week: [paste tasks with A/B/C, hours, KPI target vs. actual]. Blockers: [list]. Capacity next week (80% cap): [hours]. Revise the next week’s plan to hit my KPI by the deadline: re-estimate hours, keep 3–5 tasks, propose one task to drop, tighten assumptions, and adjust volumes (e.g., outreach count) so the math still lands on the goal. Output: revised weekly list (A/B/C, hours), updated KPI target, and a one-sentence rationale.

Worked example (KPI-led)

Goal: Book 10 qualified sales conversations in 4 weeks. Capacity: 6 hrs/week → plan at 4.8 hrs. Assumptions: 10% reply rate, 50% of replies convert to calls → need ~200 outreaches total (~50/week).

• Week 1 (4.8h) — Outcome KPI: 40 outreaches sent, 4 replies
  • A: Finalize ICP + message template v1 (0.9h)
  • A: Build 60-prospect list (0.9h)
  • A: Send first 40 personalized outreaches (3.0h)
  • B: Set up simple tracking sheet (0.3h)
• Week 2 (4.8h) — Outcome KPI: 50 outreaches, 5 replies, 2 calls booked
  • A: Send 50 outreaches (3.5h)
  • A: Follow-up to Week 1 non-responders (0.8h)
  • A: Book and confirm calls (0.5h)
  • B: Tweak template based on reply patterns (0.4h)
• Week 3 (4.8h) — Outcome KPI: 50 outreaches, 6 replies, 3 calls booked
  • A: Send 50 outreaches (3.5h)
  • A: Follow-up cadence #2 (0.8h)
  • A: Qualification + scheduling (0.5h)
  • B: Draft a simple one-pager to increase conversions (0.4h)
• Week 4 (4.8h) — Outcome KPI: 60 outreaches, 7 replies, 3 calls booked (cumulative ≈10)
  • A: Send 60 outreaches (4.0h)
  • A: Final follow-ups (0.6h)
  • B: Prep call agenda + notes template (0.2h)

Why this works

• KPI backsolving converts “do more” into precise volumes (e.g., 50 outreaches/week).
• ≤90-minute tasks increase completion rates for busy schedules.
• Weekly auto-tuning keeps the math honest when reality shifts.

Metrics to track (weekly scoreboard)

• % of A-tasks completed (target 80%+)
• Hours planned vs. used (variance ≤20%)
• Throughput: units completed vs. required (e.g., outreaches/week)
• Conversion by stage (reply rate, booking rate)
• Time-to-first-outcome (days to first reply/call)

Common mistakes and quick fixes

1. Planning tasks longer than 90 minutes → Fix: split by output (e.g., “Send 15 outreaches”).
2. No KPI target per week → Fix: force one numeric outcome every week.
3. Rolling everything forward → Fix: use a “drop-one” rule in the weekly edit.
4. Ignoring conversion data → Fix: adjust volumes weekly via the auto-tune prompt.
5. Underestimating approvals/dependencies → Fix: front-load decisions in Week 1 and set deadlines.

1-week action plan (make it real)

1. Day 1: Write your goal, deadline, definition of done, capacity (honest hours).
2. Day 2: Run the KPI-first planning prompt. Accept a plan at ≤80% capacity.
3. Day 3: Calendar your Week 1 A-tasks (max 3), each ≤90 minutes.
4. Days 4–6: Execute. If a block slips, move it within the week; keep total hours.
5. Day 7: Run the auto-tune prompt with your actuals. Adjust Week 2 to stay on target.

Your move.

Quick win: In your orders dashboard, filter for orders where billing country != shipping country or where IP country doesn’t match billing — flag any 5 highest-value mismatches and review them now (5 minutes).

Good call focusing on practical, small-business tactics. Here’s a direct playbook you can implement without being technical.

The problem: Chargebacks and buyer fraud drain cash, tie up staff time, and raise processing fees.

Why it matters: For small businesses a few disputed orders can wipe out net profit for a week and damage merchant relationships. The goal is to stop likely fraud before shipment and make disputes winnable when they happen.

Lesson: Automation alone doesn’t win disputes — targeted rules + a short human review workflow and solid evidence do.

1. Collect the right data (what you’ll need)
   • Order details, billing/shipping addresses, IP & device data, payment gateway transaction ID, customer messages, tracking info, and receipts.
2. Quick rules you can set today (how to do it)
   1. Flag orders where billing != shipping, high-ticket orders (> your average order x3), or new customers with multiple failed payment attempts.
   2. Add a manual review queue for flagged orders: staff verify phone/email and hold fulfillment until confirmed.
3. Add fraud scoring (what to expect)
   • Enable your payment gateway’s fraud scoring or plug in a low-cost service. Start with conservative thresholds, then lower false positives over 2–4 weeks.
4. Build an evidence pack for disputes (how to do it)
   • For each disputed sale keep order confirmation, proof of delivery/tracking, IP/device logs, support chat transcripts, and refund attempts in one PDF.
5. Use AI to triage messages (what you’ll need)
   • Feed customer messages and order metadata into a simple classifier to highlight likely friendly fraud vs legitimate complaints — frees staff for high-value cases.

Copy-paste AI prompt you can use now

Prompt: You are an e-commerce fraud analyst. Given this order data: order_id, order_value, billing_country, shipping_country, ip_country, card_country, device_type, customer_message, tracking_status. Output: a risk score 0–100, top 3 reasons for the score (short bullets), and three one-sentence verification steps to reduce risk for this order.

Metrics to track

• Chargeback rate (chargebacks / total transactions)
• Dispute win rate (won disputes / total disputes)
• Average time to respond to dispute
• % orders flagged and false positive rate
• Cost per prevented chargeback

Common mistakes & fixes

• Overblocking legitimate customers — fix: start with conservative thresholds and review false positives weekly.
• Relying only on blacklists — fix: combine behavior signals (IP, velocity, device) with human review.
• Poor evidence collection — fix: standardize a single PDF packet for every dispute before you submit.

1-week action plan

1. Day 1: Run the 5-minute filter and flag 5 suspicious orders; call/email to verify.
2. Day 2: Implement 3 quick rules in your checkout or payment gateway.
3. Day 3: Create an evidence packet template and fill it for any recent dispute.
4. Day 4: Set up basic fraud scoring or enable gateway scoring.
5. Day 5: Use the AI prompt above on 10 past disputed orders to learn signal patterns.
6. Day 6–7: Review metrics, tweak thresholds, and document the manual review workflow.

Your move.