Jeff Bullas

This is the single most valuable piece of data for improving your content.

Short Answer: Analyse your graph for three key points—the initial drop-off, mid-episode dips, and moments of high retention—to understand what hooks your listeners and what causes them to leave.

This data provides an unfiltered look into your listeners’ behaviour, showing you exactly where your content is strongest and weakest.

Your analysis should focus on three content formats within your episode. The first is your introduction; a steep drop-off in the first few minutes is a clear sign that your opening format is too long, has a jarring musical sting, or fails to quickly state the episode’s value. The second format to identify is any segment that causes a mid-episode dip, where the graph scoops downwards. By checking the timestamp, you can pinpoint a specific interview question, a tangent, or an ad break that caused listeners to lose interest or skip ahead. The third and most important format to analyse is the plateau, the flatter parts of the graph where retention is highest; these are the moments your audience loves, and your strategic goal should be to identify what was happening there and create more content just like it. A common mistake is obsessing over a perfectly flat line; no content has 100% retention, so the goal is to understand the story the data is telling you and make incremental improvements.

Cheers,
Jeff

Short answer: Yes — AI can quickly model realistic profit margins after fees, taxes and ad spend, but it only works well if you give it accurate inputs and check the results.

Context: For non-technical founders and small-business owners, the hard part isn’t the math — it’s collecting the right numbers and running realistic scenarios. AI speeds up the scenario-building, sensitivity checks and “what-if” thinking so you can act faster.

What you’ll need

• Recent sales data (price per product, units sold)
• Cost inputs (COGS, shipping, packaging)
• Fees (marketplace % fees, payment processing fixed + %)
• Ad spend per sale (or cost-per-acquisition)
• Estimated tax rate (use your accountant’s number)
• A spreadsheet or an AI chat tool (ChatGPT or similar)

Step-by-step: how to do it

1. Collect one month of accurate numbers or rolling averages.
2. Create a simple spreadsheet with rows: Price, COGS, Shipping, Marketplace fee (% of price), Payment fee (%+fixed), Ads per sale, Other costs, Tax rate.
3. Calculate net before tax: Revenue – (COGS + Shipping + Fees + Ads + Other).
4. Apply tax to profit (or consult your accountant for taxable adjustments).
5. Compute net profit and profit margin = Net profit / Revenue.
6. Run three scenarios: Best, Likely, Worst (vary ad cost, returns, and fees).

Quick worked example

• Price: $50
• COGS: $15, Shipping: $5
• Marketplace fee 10% = $5; Payment fee 2.9% + $0.30 = $1.75
• Ad cost per sale = $10; Tax rate = 25%

Net before tax = 50 – 15 – 5 – 5 – 1.75 – 10 = $13.25. Tax = 25% of 13.25 = $3.31. Net profit ≈ $9.94. Profit margin ≈ 19.9%.

Common mistakes & fixes

• Do not forget variable fees (percentage-based) — include them per unit. Fix: calculate fees as % of price in the spreadsheet.
• Do not mix per-order fixed fees with percentage fees incorrectly. Fix: separate fixed ($0.30) and % (2.9%) in formula.
• Do not neglect refunds, returns and chargebacks. Fix: add a returns line (e.g., 2–5% of revenue).
• Do run sensitivity scenarios — small ad-cost changes can flip profitability.

Practical AI prompt you can copy-paste

I sell a product online. Price: $50. COGS: $15. Shipping: $5. Marketplace fee: 10% of price. Payment processing: 2.9% + $0.30. Average ad cost per sale: $10. Expected tax rate on profit: 25%. Show a step-by-step profit calculation per unit, then provide three scenarios (best, likely, worst) varying ad cost by ±50% and returns by 0–5%. List assumptions and three simple recommendations to improve margin.

Action plan — ready in one hour

1. Pull last 30 days of orders and average costs.
2. Paste numbers into the prompt above and run the AI.
3. Copy AI outputs into a spreadsheet and verify one real order manually.
4. Set margin targets and run weekly checks; iterate ad spend if CAC too high.

Reminder: AI accelerates the math and scenario planning — but you still need to validate with real accounting data and run the sensitivity checks. Do the small experiments first: track one campaign, one SKU, one month.

Spot on — clear inputs are the lever. Let’s turn that into a simple, guardrails-based plan you can run today and keep on track without second-guessing.

Try this in under 5 minutes

• Write down one number: the largest temporary drop you can tolerate (e.g., “I can handle a 20% drawdown without selling”).
• Paste the Quick Prompt below and ask for three allocations that respect that drawdown. You’ll get instant, usable options.

What you’ll need

• Age, investable assets, monthly contribution
• Years until you need the money and a one-line goal
• Risk label (conservative/moderate/aggressive) and your max drawdown comfort number
• Basic tax note (tax bracket or account types) and any liquidity needs in the next 3 years

Why this works

• Turning “moderate” into a number (max drawdown) lets AI design allocations with guardrails instead of vibes.
• Adding a simple bucket for near-term cash reduces panic and keeps you invested.
• Light stress tests set expectations before the market tests you.

Step-by-step (do this now)

1. Define risk as a number (2 minutes): pick your max acceptable drawdown (e.g., 15%, 20%, or 30%).
2. Run the Quick Prompt (3 minutes): get three guardrail-aware allocations.
3. Add a bucket overlay (10 minutes): keep 1–2 years of known spending needs in cash/short bonds; invest the rest by your chosen allocation.
4. Stress test (10 minutes): ask AI for three scenarios (recession, inflation spike, rate cut cycle) and what your chosen portfolio might do.
5. Map to funds (15–30 minutes): for each asset class, pick one broad, low-cost ETF or mutual fund you already have access to.
6. Automate (10 minutes): set monthly contributions and a quarterly review with ±5% rebalance bands.
7. Measure (ongoing): track allocation drift, annualized return vs target, and cash runway months.

Copy-paste Quick Prompt (speed test)

Translate my risk tolerance into numbers. I can tolerate a temporary drawdown up to {max %}. I am {age} with ${assets}, contribute ${monthly}/month, years to goal {years}, goal: {one-line goal}, risk label {conservative/moderate/aggressive}. Give three portfolio options (conservative/moderate/aggressive) that respect my drawdown comfort. For each, provide: % by asset class (US equities, international equities, bonds, cash, alternatives), a simple rebalancing rule (±5% bands or quarterly), and a one-line expectation of typical volatility and worst-case drawdown. Educational, non-binding guidance only.

Copy-paste Robust Prompt (premium)

Act as an educational financial planning assistant (not advice). Inputs: age {age}, investable assets ${assets}, monthly contribution ${monthly}, years until goal {years}, goal: {one-sentence goal}, risk tolerance {conservative/moderate/aggressive}, max drawdown comfort {max %}, tax status {tax bracket/account types}, liquidity needs in next 1–3 years {amount/use}. Provide three portfolio options (conservative, moderate, aggressive) with: 1) % by asset class (US equities, international equities, bonds, cash, alternatives); 2) 5–10 year expected annualized return range and a rough severe drawdown estimate; 3) a bucket overlay (near-term cash/short bonds vs long-term growth); 4) a glidepath suggestion if my goal is within 3–15 years; 5) a simple rebalancing rule and cadence; 6) one-line tax-aware note (asset location / harvesting, educational only); 7) a 90-day implementation checklist. Then stress-test each option across three scenarios: recession, inflation spike, and falling-rate recovery, with plain-English expectations. Educational and non-binding; no guarantees.

Worked example (moderate with guardrails + buckets)

• Inputs: age 55, assets $300,000, $1,000/month, 10 years to retirement, income goal $40,000/yr, moderate risk, max drawdown comfort 25%, basic tax: mix of taxable + retirement accounts.
• Allocation: 55% equities (35% US / 20% international), 40% bonds (intermediate core + some short-term), 5% cash.
• Bucket overlay: hold 12–18 months of expected withdrawals in cash/short bonds; rest in the allocation above.
• Expectations: 4.5–6.5% annualized range; severe drawdown ~25–30% possible. Rebalance quarterly or at ±5% drift.

Insider tip (sets expectations fast)

• Ask AI to convert the allocation into a dollar drawdown at your balance today (e.g., “What does a 25% drawdown mean in dollars for $300,000?”). If that number makes your stomach drop, nudge toward more bonds/cash.
• Use a glidepath: start with your chosen mix and shift 1–2% from stocks to bonds per year in the last 5–10 years before your goal.

Common mistakes & fixes

• Vague risk label — fix: add a max drawdown number and ask AI to respect it.
• No near-term cash bucket — fix: keep 1–2 years of known spending in cash/short bonds.
• Over-tinkering — fix: use calendar reviews and ±5% bands; in-between, do nothing.
• Ignoring taxes — fix: ask for one-line asset location guidance (educational) before you buy.

30-minute action plan

1. List inputs + max drawdown number (5 minutes).
2. Run the Quick Prompt; pick the one you could live with in a bad year (5 minutes).
3. Add a 12–18 month cash/short-bond bucket if you’ll need money soon (10 minutes).
4. Map each asset class to one low-cost broad fund you already use; set monthly automation; add a quarterly rebalance reminder (10 minutes).

You don’t need perfect. You need a clear baseline, sensible guardrails, and a habit. Run the prompt, choose a framework, and automate the next contribution.

On your side,

Jeff

5‑minute start: paste one anonymized field note into your AI and run the “Trust‑check” prompt below. You’ll get themes anchored to direct quotes, plus one disconfirming question. That keeps you in control and makes weak themes obvious fast.

Why this works: ethnographic themes are only as strong as their evidence and context. If you force the AI to show its receipts (verbatim snippets) and propose what could disprove a theme, you turn it from a guesser into a disciplined assistant.

What you’ll need

• One short field note or 1–2 minute transcript excerpt (150–300 words), anonymized.
• An AI text tool.
• A simple checklist (below) to score trustworthiness.

Copy‑paste prompt: Trust‑check (use as‑is)

“Read the note below. Propose up to 3 candidate themes that are strictly grounded in the text. For each theme, provide: (1) a one‑sentence theme statement, (2) 2 short verbatim quotes copied exactly from the note to support it, (3) one sentence on important context that might be missing, (4) one disconfirming question that could prove the theme wrong, (5) a confidence level (High/Med/Low) based only on clarity and frequency in the note. Do not add facts not present. If evidence is weak, say ‘insufficient evidence.’ Finish with one follow‑up interview question and one observational check I can run next.”

The Trustworthy Theme Checklist (score each theme: Pass/Needs work)

1. Evidence anchored: At least two exact quotes support the theme. Pass if both quotes clearly point to the claim.
2. Specific, not generic: Avoids vague words like “users value convenience” unless the note shows it. Pass if the language is concrete (who/what/when).
3. Context present: Mentions roles, place, time, or sequence when relevant. Pass if readers could locate the moment in the note.
4. Language nuance: Hedges, pauses, laughter, or tone are noted if they matter. Pass if nuance is acknowledged or explicitly absent.
5. Counter‑pressure: Names what could make it false. Pass if there’s a clear disconfirming question.
6. Negative cases considered: Looks for exceptions or outliers. Pass if at least one possible counterexample is proposed.
7. In‑vivo phrasing: Uses participants’ own words where possible. Pass if at least one key phrase is in‑vivo.
8. Triangulation‑ready: States what other data could confirm it (another note, photo, behavior log). Pass if at least one test source is suggested.
9. Saturation signal: Marks whether the theme seems unique or recurring. Pass if it labels “unique” vs “recurring” and why.
10. Actionable next step: Leads to a new question or observation. Pass if there’s a concrete next move.
11. Reflexivity: Notes how your prior assumptions could color interpretation. Pass if you’ve written one line on your influence.

Fast workflow (7 minutes per note)

1. Anonymize the note; run the Trust‑check prompt.
2. Score each theme against the checklist. Keep only Pass items or rewrite “Needs work.”
3. Copy the AI’s disconfirming question into your interview plan; add one observational check (where/when to look).
4. Log one reflexivity line: “What did I expect to see? What surprised me?”

Insider tricks that raise quality

• Quote‑first forcing: Always demand exact quotes before summaries. It prevents fluffy themes.
• Vagueness audit: Ask the AI to replace generic words with observed behaviors. Example: swap “engagement” with “lingered 3–5 minutes at the stall.”
• Counter‑theme generation: For any strong theme, create a plausible opposite and what evidence would support it. This guards against early lock‑in.
• Compression test: Ask the AI to merge overlapping themes into one sharper claim; delete duplicates.

Copy‑paste prompt: Vagueness to Behavior

“Rewrite each theme to be behavior‑specific and time‑bound, using only what’s in the note. Replace generic words (e.g., ‘engagement,’ ‘convenience’) with observable actions or sequences. If you can’t ground a word in observed behavior, flag it as ‘unsupported.’ Return a before/after list.”

Copy‑paste prompt: Negative‑case hunter

“From this note, propose 2 plausible alternative explanations for the main behavior. For each, list one piece of evidence that would distinguish it in future observation, and one short follow‑up question to test it. Do not invent facts; keep it grounded.”

Mini example (what ‘good’ looks like)

• Note excerpt: “Customers cluster at the coffee stall after 10 a.m.; one woman refuses two free samples, returns later, buys quietly.”
• Strong theme: “Purchases follow private evaluation rather than public sampling for some buyers.”
• Evidence: “refuses two free samples”; “returns later, buys quietly.”
• Disconfirming question: “Was the refusal due to allergy or time pressure rather than evaluation?”
• Next step: Observe whether similar buyers circle back without sampling on three separate days.

Common mistakes and quick fixes

• Mistake: Long, mixed notes → Fix: Split into single moments; process one at a time.
• Mistake: Accepting generic themes → Fix: Run the Vagueness to Behavior prompt.
• Mistake: No counter‑evidence → Fix: Use the Negative‑case hunter on every “keeper” theme.
• Mistake: Losing reflexivity → Fix: One‑line log per session about how AI nudged your view.

1‑week action plan

1. Day 1: Pick 5 short notes; run Trust‑check; score with the checklist.
2. Day 2: Rewrite weak themes with Vagueness to Behavior; discard any with “unsupported” flags.
3. Day 3: Run Negative‑case hunter on top 5 themes; add disconfirming questions to your guide.
4. Day 4: Field one short observation session focused on testing counter‑questions.
5. Day 5–6: Repeat on 10 new notes; tally Pass rate and time per item.
6. Day 7: Produce a 1‑page brief: 3 strongest themes, the quotes that support them, and the next 3 observational checks.

What to expect

• Faster early patterning (under 3 minutes per item once you’re in rhythm).
• Fewer generic themes; more behavior‑anchored claims.
• Clearer next moves for interviews and observation, with built‑in disconfirmation.

Bottom line: AI is your acceleration partner, not your interpreter. Make it prove every theme with quotes, invite alternatives, and keep your reflexivity live. Do that, and your ethnographic insights stay human, grounded, and ready for action.

Quick win — and next steps you can use today

Nice work on the 5-minute de-identify routine. Here’s a tighter, practical playbook to turn that quick win into a repeatable, privacy-safe workflow your team can trust.

Why this matters

De-identifying lets AI help with wording, measurability and consistency — without exposing student data. The key is simple rules, a human reviewer and a short provenance note in the IEP.

What you’ll need

• One de-identified student profile (grade, primary area of need, objective performance numbers or ranges).
• A clear outcome statement (one sentence: e.g., improve reading fluency to X wpm).
• An educator (case manager/special ed teacher) to review and sign off.
• A place in the IEP to record how AI was used (one line of provenance).

Step-by-step (safe, repeatable)

1. De-identify: remove PII (name, DOB, ID, family details) and replace with placeholders like [STUDENT_A]. Keep only measurable info.
2. Write the desired outcome in one sentence.
3. Use the AI prompt (below) with the de-identified profile to draft 2–3 goals with benchmarks and data collection methods.
4. Immediate human review: confirm assessment numbers, adjust wording to district format, add any family context.
5. Record provenance: add a short note in the IEP (example language below).

Copy-paste AI prompt (use only with de-identified profile)

Act as a special education teacher. Using this de-identified student profile, draft three measurable, time-bound IEP goals with short-term objectives and suggested progress monitoring methods. Student profile: Grade: 4; Area of need: reading comprehension and fluency; Current level: comprehension at 2nd-grade level, fluency 70 wpm with 85% accuracy on grade-level passages; Supports: small-group instruction 30 minutes daily. Provide for each goal: goal statement, baseline, 3-6 month benchmarks, criteria for mastery, suggested instructional strategies, and practical data collection methods (what to measure and how often).

Worked example (de-identified result)

• Goal: Within 12 months, [STUDENT_A] will increase reading fluency to 95 wpm on grade-level passages with 95% accuracy, measured by weekly 1-minute oral reading probes. Benchmarks: 3 months—75 wpm; 6 months—85 wpm; 9 months—90 wpm. Strategies: repeated reading, guided oral reading, vocabulary preview. Data: weekly probes logged in class tracker.

Common mistakes & fixes

• Identifier slips: double-check for unique phrases or family names — remove them.
• Vague goals: add numbers, timeframe, and specific measures (wpm, % accuracy).
• Over-trust in AI: treat output as a draft—educator signs off and adapts to context.

7-day action plan

1. Day 1: Create one de-identified template (10 minutes).
2. Day 2: Run a profile through AI using the prompt and review with an educator (15–20 minutes).
3. Day 3: Add provenance language to IEP notes and save the de-identified template.
4. Days 4–7: Repeat with 2–3 files, refine prompts and district wording.

Provenance sample line for the IEP

“Initial goal language drafted using AI on a de-identified profile; reviewed and finalized by [educator role] on [date].”

Start with one profile this week. Small tests build confidence and protect privacy—then scale what works.

Right on: your focus on context-injection and link-awareness is the leap from “OK” to genuinely useful. Let’s add one more layer that saves even more review time — a simple triage system plus a context pack you can feed the AI in batches.

What to prepare (10 minutes)

• A lightweight spreadsheet with columns: page_url, image_url, file_name, image_role (product, hero, chart, screenshot, logo, decorative, functional), link_destination (if any), nearby_heading/caption, decorative_hint (yes/no).
• Your one-page style guide: character limits, tone, people rules, brand dictionary, banned buzzwords.
• One reviewer who knows the product/content.

How to run it — quick steps

1. Bundle context: For each image, grab the page title and nearest heading/caption. Note if it’s a link/button. If it’s visual flair (confetti, patterns), mark as decorative_hint = yes.
2. Use a structured prompt with triage (copy-paste below). Ask the AI to output ALT, a short LONGDESC for complex images, plus a confidence score and a yes/no REVIEW flag.
3. Auto-apply greens: If CONFIDENCE ≥ 85 and REVIEW = no for roles logo/decorative/hero, auto-insert. If functional and linked, check that ALT describes the action/destination, then auto-apply if high confidence.
4. Queue yellows/reds: Anything with CONFIDENCE < 85, any chart/screenshot, or any product image goes to your reviewer.
5. Feedback loop: Note recurring issues (e.g., missing text-in-image, over-length alts). Update the style guide and rerun that bucket.
6. Publish, then spot-check: Sample 10–20% of auto-applied items each batch to confirm drift hasn’t crept in.

Insider upgrades that pay off

• Functional over decorative: If an image sits inside a link or button, treat it as functional — ALT should describe the destination or action (e.g., “View pricing plans”). Do not describe the pixels.
• Duplicate-killer: If ALT matches the page title exactly or repeats a keyword, shorten it. Relevance beats repetition.
• People policy: Describe roles or actions only (e.g., “nurse drawing blood”), not names or attributes.
• Charts/screenshots: ALT gives the “what + timeframe”; LONGDESC adds the trend and a notable high/low.
• Brand dictionary: Provide correct product names and forbidden adjectives. Consistency is a quality multiplier.

Copy-paste prompt (context-aware with triage)

Act as a web accessibility specialist. You will receive: page_title, nearby_text, file_name, image_role (product, hero, chart, screenshot, logo, decorative, functional), link_destination (if any), decorative_hint (yes/no). Write alt text and, when relevant, a short extended description. Rules: 1) ALT ≤100 characters, factual, no marketing buzzwords, no “image of.” 2) Include visible text in the image verbatim in quotes. 3) Describe people by role/activity only, not names. 4) If the image is decorative and adds no information, ALT = empty string. 5) If the image is a link/button, ALT must describe the destination or action. 6) For charts/screenshots, include a 1–2 sentence LONGDESC with type, timeframe, and key trend or peak/low. 7) Emit a confidence score and a REVIEW flag: set REVIEW = yes if you’re unsure, if text-in-image seems incomplete, or if brand/product terms may be wrong. Output exactly:
ALT:
LONGDESC:
ROLE:
DECORATIVE:
LINK_FOCUS:
CONFIDENCE: <0–100>
ISSUES:
REVIEW:

Variant (charts/screenshots only)

Write a concise ALT (≤100 chars) and a 2–3 sentence LONGDESC for this chart/screenshot. Include chart type, timeframe, the main trend, and any labeled peaks/lows. Include visible text in quotes. Avoid marketing language. Output:
ALT: …
LONGDESC: …

What “good” looks like

• Product photo (not linked): ALT: “ThermoPro Go Mug, stainless 1‑liter travel mug with flip lid.” LONGDESC: none.
• Decorative confetti banner: ALT: “” (empty). LONGDESC: none. DECORATIVE: yes.
• Linked CTA image: ALT: “Start free trial.” LONGDESC: none. LINK_FOCUS: “free trial page.”
• Sales chart screenshot: ALT: “Bar chart of 2024 quarterly sales, Q4 highest; labels ‘Q1–Q4 2024’.” LONGDESC: “Quarterly sales climb through 2024 with the highest bar in Q4; overall growth about 12% YoY.”

Common mistakes and fast fixes

• SEO fluff or repeated keywords: Add a banned-words list (e.g., best, amazing, top #1). Sample 10–20% to catch drift.
• Missed text-in-image: Keep the rule “include visible text verbatim in quotes.” If OCR is uncertain, the model should set REVIEW = yes.
• Over-describing decorative art: Require a DECORATIVE decision. If it doesn’t inform the content, use empty ALT.
• Wrong focus on linked images: Ensure ALT names the action/destination, not the visual details.
• Over-length alts: Enforce the ≤100-character rule; trim non-essential words and adjectives.

What to expect

• First pass: 80–95% correct on simple images.
• Human review time: 15–60 seconds per image; longer for charts/screenshots.
• After one iteration with a tuned style guide: edit rate under 10% is realistic.

Today’s 90‑minute plan

1. Create the spreadsheet (include page title, nearby text, and link info). Tag 100 images across roles.
2. Run the context-aware, triage prompt. Auto-apply greens for logos/decorative/obvious heroes and high-confidence functional images.
3. Reviewer checks every product, chart, and screenshot, plus any item with REVIEW = yes or CONFIDENCE < 85. Log 3–5 recurring fixes and update the style guide.

Bottom line: Keep it simple, enforce crisp rules, and let the AI pre-triage the pile. You’ll reduce review time, improve consistency, and move your accessibility score fast — while making the experience better for real people.

Nice point: absolutely — the single biggest lever is the quality of the inputs and the rules you give the AI. That tiny step turns fuzzy advice into usable options you can act on.

Here’s a practical, do-first method to get three sensible portfolio frameworks in under 30 minutes, plus a ready-to-run AI prompt you can copy and paste.

What you’ll need

• Age, investable assets, monthly contribution
• Years until you need the money (time horizon)
• One-line goal (retirement income target, house purchase, etc.)
• Risk label: conservative / moderate / aggressive
• Any tax or liquidity constraints (tax bracket, required withdrawals)

Step-by-step (do this now)

1. Gather the inputs above (5 minutes).
2. Run the copy-paste AI prompt (below) to get 3 allocations with return ranges, drawdown estimates, ETF examples and rebalancing rules (5–10 minutes).
3. Sanity check: ensure conservative option keeps 3–6 months cash and that equities exposure aligns with your time horizon (10 minutes).
4. Map each asset class to one low-cost ETF or mutual fund you can buy, set up automatic monthly contributions, and schedule quarterly reviews (10–20 minutes).

Practical example (moderate, worked)

• Inputs: age 55, assets $300,000, $1,000/month, 10 years to retirement, target income $40,000/yr, moderate risk.
• Moderate allocation example: 60% equities (40% US / 20% international), 35% bonds (intermediate), 5% cash.
• Expect: ~5–7% annualized (range), potential peak-to-trough drawdown ~25–35% in a severe downturn. Rebalance when any class drifts ±5% or quarterly.

Common mistakes & fixes

• Chasing last year’s winners — fix: stick to diversified baseline and trim winners to rebalance.
• Overreacting to volatility — fix: follow a calendar review and a fixed rebalance band.
• Giving AI vague inputs — fix: always provide time horizon, cash needs, and tax status.

Copy-paste AI prompt (robust)

Act as a certified financial planner providing educational, non-binding guidance. I am an investor with these inputs: age {age}, investable assets ${assets}, monthly contribution ${monthly}, years until goal {years}, goal: {one-sentence goal}, risk tolerance: {conservative/moderate/aggressive}, tax status: {brief tax note}, liquidity constraints: {any}. Provide three portfolio options (conservative, moderate, aggressive) with percentage allocations by asset class (US equities, international equities, bonds, cash, alternatives). For each option give: a 5–10 year expected annualized return range, estimated max peak-to-trough drawdown in a severe recession, suggested low-cost ETF examples per asset class (general examples only), a simple rebalancing rule and cadence, one-sentence plain-English trade-off summary, and a 3-step implementation checklist. Use round percentages and include a one-line tax-aware note. No promises or guarantees.

Quick prompt (5-minute test)

I am {age}, have ${assets}, risk {conservative/moderate/aggressive}, years to goal {years}. Give 3 simple allocations (conservative/moderate/aggressive) with % by broad asset class and a one-line expected risk note.

1-week action plan

1. Day 1: Collect inputs and run the quick prompt.
2. Day 2: Run the robust prompt and save the three proposals.
3. Day 3–4: Sanity check vs liquidity needs and tax notes.
4. Day 5: Pick baseline, choose funds/ETFs, set automation.
5. Day 6–7: Implement and add a quarterly calendar reminder for review.

Small actions beat perfect plans. Run the quick prompt now, review one proposal, and set an automated contribution. You can tighten the inputs and I’ll help craft or review the AI output for fit.