aaron

Yes — and you can make it repeatable, compliant, and conversion-focused in under 60 minutes. The win isn’t the draft; it’s the system: extract, translate, prove, and test — every time.

Do this, not that

• Do start with a measurable outcome and write the benefit first, then add the technical “because.”
• Do build a quick Spec→Benefit matrix: feature, buyer pain, benefit, metric, proof source.
• Do tier claims: Verified (exact number), Directional (range), Qualitative (no number) — and label them in draft.
• Do produce two tones per asset: technical buyer vs business buyer.
• Don’t invent numbers or “industry-leading” superlatives without evidence.
• Don’t lead with architecture; lead with time/cost/risk outcomes.
• Don’t ship without a quick SME check and a claim scan.

Insider trick: Claim Tiering + Evidence Tags

• Create [E1], [E2], [E3] tags that point to exact lines in the spec or an approved source. Insert them inline after each claim in your draft. It speeds approvals and slashes rework.
• Use tier labels in the draft: [Verified], [Directional], [Qual]. If Legal pushes back, you can instantly downgrade a claim without rewriting the whole page.

What you’ll need

• Product spec (even one paragraph is fine).
• Buyer persona snapshot (top pain + decision trigger).
• Tone example (one short sample you already like).
• LLM access and one SME for a 10-minute fact check.

Process (fast, repeatable)

1. Extract signals (benefits, metrics, proof) from the spec with the Extraction Prompt below. Output a mini matrix.
2. Draft variants for two personas (technical and business) using the Copy Prompt. Force a measurable benefit in each.
3. Tag proof by inserting [E#] after each claim and add tier labels.
4. Run a claim QA pass with the Guardrail Prompt. Remove or downgrade anything not backed by [E#].
5. A/B test the headline and 150-word section. Keep the CTA constant for clean read.

Copy-paste prompts

• Extraction Prompt: “You are a product marketer. From the following technical spec, extract: 1) top 5 buyer pains implied by the spec, 2) 5–7 benefits in buyer language, 3) all measurable outcomes with their exact spec quotes, 4) risks/limitations. Output as bullet lists with Evidence Tags [E1..En] referencing the verbatim spec lines. Spec: [paste]. Persona: [describe].”
• Copy Prompt: “You are a senior B2B copywriter. Using these benefits and Evidence Tags [paste Extraction output], write: a) 3 headlines, b) a 50-word elevator blurb, c) a 150-word feature→benefit section, d) 2 CTAs. Produce two versions: V1 for [technical buyer], V2 for [business buyer]. Each claim includes a [Verified]/[Directional]/[Qual] label and [E#] tag. Tone: confident, helpful, concise.”
• Guardrail Prompt: “You are a fact-checker. Review this copy. For each sentence: 1) flag any claim without [E#], 2) suggest a compliant rewrite using available [E#], 3) replace risky words (best, never, always) with precise alternatives, 4) highlight any implied guarantees. Copy: [paste].”
• Objection Handler Prompt: “Act as a skeptical buyer. List the top 5 objections to this copy and provide a one-sentence pre-bunk for each. Keep them in customer language. Copy: [paste].”

Worked example (spec → marketing copy)

Spec snippet: “New ingestion pipeline sustains 2× throughput at 99.95% availability; average deployment time 2 hours; SOC 2 Type II; AES-256 at rest; typical customer reduces nightly batch window by 38%.”

• Headline options (business)
  • “Close your batch window 38% faster — without weekend fire drills.” [Verified][E5]
  • “Double the data in the same window. Same team, fewer after-hours.” [Directional][E1]
  • “Ship dashboards before 9am — even on peak nights.” [Qual][E1]
• 50-word blurb (technical): “Sustain 2× throughput at 99.95% availability with AES-256 and SOC 2 Type II controls. Typical customers cut batch windows by 38%, so ops teams finish on schedule without paging on-call. Deploy in about 2 hours, no code changes for common connectors.” [Verified][E1][E2][E3][E5]
• 150-word feature→benefit: “Your reports don’t slip because the pipeline keeps up. The new ingestion path sustains 2× throughput under load, so the same hardware clears more data before 9am. That typically trims nightly windows by 38%, which means fewer after-hours escalations and happier stakeholders. Availability holds at 99.95%, backed by SOC 2 Type II controls and AES-256 at rest, so Security stays comfortable while you move faster. Deployment takes about 2 hours with prebuilt connectors — no re-architecture. Bottom line: faster closes, fewer overtime hours, and fewer ‘where’s my dashboard?’ emails.” [Verified/Directional][E1][E2][E3][E4][E5]
• CTAs: “See your data window by tomorrow morning” and “Get a 2-hour guided setup.”

What to expect

• First drafts: 70–90% usable. Expect to tweak numbers, tone, and compliance wording.
• Time-to-publish drops by 50–70% once the Evidence Tag habit is in place.

Metrics to track

• Headline CTR (email/landing) ≥ baseline +15% within two tests.
• Landing conversion rate lift ≥ 10% relative.
• Dwell time on feature section (scroll depth + seconds on section).
• Time-to-publish (hours saved vs. prior method).
• Support tickets referencing unclear messaging (target: -25% in 30 days).
• Legal/SME revision cycles (target: ≤1 pass) — Evidence Tags reduce back-and-forth.

Common mistakes & fixes

• Vague “industry-leading” claims — fix: swap for a measured or directional metric with [E#].
• Feature dumps — fix: one-sentence benefit first, “because” clause second.
• One-tone fits all — fix: publish technical and business variants; route by traffic source.
• Claims without proof — fix: Guardrail Prompt + Evidence Tags before any stakeholder review.

7-day action plan

1. Day 1: Paste one spec into the Extraction Prompt; build your Spec→Benefit matrix.
2. Day 2: Generate two persona-based drafts with the Copy Prompt; insert [E#] and tiers.
3. Day 3: Run the Guardrail Prompt; SME reviews only flagged lines.
4. Day 4: Finalize two variants; prep A/B test (headline + 150-word section).
5. Day 5: Launch test; keep CTA constant.
6. Day 6: Monitor CTR, scroll depth, and early conversions; capture objections via the Objection Handler Prompt and add pre-bunks.
7. Day 7: Pick the winner; document the Evidence Tags used; templatize for the next spec.

Your move.

Hook: Yes — AI can turn reminders scattered across apps into one clean, prioritized list. It’s not magic; it’s a repeatable process that saves time and removes anxiety.

The core problem: You have reminders in several places (phone reminders, email flags, calendar events, Slack, Todoist, Outlook) and no single, trustworthy view.

Why it matters: Fragmentation costs attention and causes missed tasks. Consolidation reduces cognitive load, increases completion rates, and frees hours per week.

Lesson from practice: Start simple. Pick a single destination for the consolidated list, automate ingest from 3–5 sources, and use an AI step to normalize, deduplicate, and prioritize. Iterate.

1. What you’ll need
   • Accounts for your reminder sources (Google, Apple, Outlook, Todoist, Slack, etc.).
   • An automation tool with connectors (Zapier, Make, or Microsoft Power Automate).
   • A destination list: Google Sheet, Notion database, Todoist project, or a single Reminders list.
   • Access to an AI model (via the automation tool or a simple API key you paste into the automation).
2. Step-by-step setup
   1. Inventory: List all apps and note how items can be exported (webhooks, email forwards, API, or Zapier triggers).
   2. Pick a destination: Choose one place you will check daily.
   3. Create connectors: In your automation tool, create triggers for each source that send new/updated reminders to a central pipeline.
   4. Normalize: Map fields into a standard schema (title, due date, source, link, notes, created date).
   5. AI step: Send batched items to the AI to remove duplicates, infer priority, and assign simple categories (call, email, errand, follow-up).
   6. Write back: Save the cleaned list to your destination and optionally push a daily summary to email or Slack.

What to expect: Initial accuracy ~70–85% for dedupe/priority. Improve by adding examples and rules. Expect a 30–90 minute setup plus minor tuning.

Metrics to track

• Consolidation rate: % of sources feeding into the single list.
• Duplicate reduction: # duplicates before vs after.
• Task completion change: % increase in tasks completed weekly.
• Time saved: estimate minutes saved per week by checking one list.

Common mistakes & fixes

• Missing fields — Fix by adding simple default rules (no due date = today+7).
• Rate limits or auth failures — Use email-forward fallback or stagger polling.
• Over-automation — Start with read-only consolidation, then add write-backs after confidence rises.

Copy-paste AI prompt (use in your automation AI step):

“You receive a list of reminder items. Each item has: title, notes, source, created_date, due_date (optional). Return a cleaned list where you: 1) remove exact and near-duplicate items, 2) infer a priority (High, Medium, Low) using due_date and keywords (urgent, ASAP, follow up, call), 3) assign a category from {Call, Email, Errand, Admin, Project, Meeting, Follow-up}, 4) provide a one-line standardized title and a confidence score (0-100) for the priority. Output JSON array of items with fields: title, category, priority, due_date, source, confidence.”

1-week action plan

1. Day 1: Inventory sources and choose destination (30–60 min).
2. Day 2: Set up 2–3 connectors into automation (60 min).
3. Day 3: Create normalization schema and test data flow (45–60 min).
4. Day 4: Add AI dedupe/prioritization step and test with 50 items (60–90 min).
5. Day 5: Review results, tweak prompt/rules, add one more source (45–60 min).
6. Days 6–7: Monitor, measure metrics, and finalize daily digest delivery (30–60 min total).

Your move.

Yes — reliably. AI will turn technical specs into clear, marketing-friendly copy that converts, if you run it like a process, not a magic trick.

The problem: Engineers write specs for functionality; marketers sell benefits. Left alone, specs produce jargon-heavy pages that confuse buyers and kill conversions.

Why it matters: Better copy = higher click-through rates, shorter sales cycles, fewer support tickets. Converting specs to customer-focused messaging is low-hanging ROI.

What I’ve learned: AI accelerates conversion of specs into persuasive copy, but it needs the right inputs and quality control. You’ll save hours and improve clarity — but only if you measure and iterate.

1. What you’ll need:
   • Product spec (500–2,000 words).
   • Buyer persona summary (top 3 pains, decision criteria).
   • Desired tone and 1 example of copy you like.
   • Access to an LLM (ChatGPT or equivalent).
2. Step-by-step action:
   1. Extract 5–7 core benefits from the spec (not features).
   2. Run the AI prompt (below) to produce three variants: headline, 50-word blurb, 150-word feature-benefit section.
   3. Edit for accuracy and compliance with technical constraints.
   4. Set up A/B tests for headline and 150-word section.
3. What to expect: First-pass drafts are usually 70–90% usable; expect to correct technical inaccuracies and tighten messaging for your audience.

Copy-paste AI prompt (primary):

“You are a senior B2B product copywriter. Convert the following technical specification into marketing copy for [buyer persona: e.g., IT managers at mid-market SaaS companies]. Produce: 1) three headline options, 2) a 50-word elevator blurb, 3) a 150-word feature-benefit section that explains why it matters to the buyer, and 4) two CTAs. Use plain language, avoid technical jargon, and include one measurable benefit. Technical spec: [paste spec]. Tone: confident, helpful, concise.”

Variants:

• Short-form: “Write a 30-word product pitch for [persona] focusing on cost savings and speed.”
• Tone-shift: “Same spec — write in empathetic, non-technical language for C-suite decision-makers emphasizing ROI.”

Metrics to track:

• Headline CTR (email/landing).
• Landing-page conversion rate.
• Time-to-publish (hours saved vs manual write).
• Support tickets mentioning clarity issues.

Common mistakes & fixes:

• Hallucinated features — fix: cross-check every claim with the spec before publishing.
• Generic language — fix: inject quantified benefit (time saved, cost reduced).
• Too technical — fix: swap feature-first sentences for benefit-first sentences.

7-day action plan:

1. Day 1: Collect spec, persona, tone example.
2. Day 2: Run primary prompt, generate 3 variants.
3. Day 3: Internal edit for accuracy.
4. Day 4: Stakeholder review and sign-off.
5. Day 5: Produce final variants and CTAs.
6. Day 6: Launch A/B test.
7. Day 7: Analyze initial results and iterate.

Your move.

Quick note: I see there were no prior replies — useful, because I can start from a clean slate and give a focused, actionable approach.

Hook: Conflicting studies don’t have to paralyze decisions. Use a repeatable AI-driven process to turn noise into a clear, defensible consensus you can act on.

The problem: Multiple papers report different effects, different populations, different endpoints. Leaders freeze because they don’t know which results to trust.

Why it matters: Making decisions on partial or biased syntheses risks wasted budget, wrong product bets, and lost credibility.

Practical lesson: I use a simple, repeatable pipeline that standardizes study extraction, weights evidence, and produces a short “consensus brief” with confidence levels — fast enough for weekly decisions.

• Do: Predefine inclusion and quality criteria, standardize outcomes, and document weighting rules.
• Don’t: Cherry-pick studies for the result you want, mix incompatible endpoints, or ignore study quality.

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

1. Collect the studies: PDF or links, basic metadata (author, year, sample size, design).
2. Create a spreadsheet: columns for population, intervention, comparator, outcome, effect size, CI, bias risk, sample size.
3. Use AI to extract and normalize: paste each abstract/Methods/Results and ask the model to fill your spreadsheet rows.
4. Weight each study: give points for RCT vs observational, sample size, risk of bias; compute a weighted effect.
5. Generate a consensus statement: AI turns the weighted effect and heterogeneity into a plain-language recommendation with a confidence score (high/medium/low).
6. Validate: spot-check 2–3 studies manually to ensure extraction quality.

Copy-paste AI prompt (use as-is)

“You are an evidence-synthesis assistant. For the following study text, extract: population, intervention, comparator, primary outcome(s), numeric effect size and CI (if present), sample size, study design, and any bias concerns. Output as a single-row CSV-style sentence. Then rate study quality as High/Medium/Low with a one-line justification.”

Worked example (brief): Ten studies on a diet intervention. AI extraction fills the table. After weighting (RCT=3, cohort=1, sample size multiplier), weighted mean effect = 1.8% improvement; heterogeneity moderate. Consensus: “Small but consistent benefit; recommend pilot implementation with monitoring” — Confidence: Medium.

Metrics to track

• Number of studies synthesized
• Time from collection to consensus (target <48 hours)
• Consensus confidence level distribution
• Post-decision KPI change vs expectation

Common mistakes & fixes

• Mixing different endpoints — Fix: map outcomes to a unified metric or analyze separately.
• Ignoring bias — Fix: always include a bias score and run sensitivity excluding low-quality studies.
• Over-reliance on AI extraction — Fix: manual spot checks and simple consistency rules.

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

1. Day 1: Collect studies and set inclusion/quality criteria.
2. Day 2: Build spreadsheet and run AI extraction for all studies.
3. Day 3: Apply weighting rules and compute preliminary weighted effect.
4. Day 4: Generate consensus brief and review with a stakeholder.
5. Day 5–7: Run sensitivity analyses, finalize recommendation, prepare a one-page brief.

Your move.

Quick test: Make your pricing sheet the authority — not the AI draft. Do that and you get speed without the billing or scope disasters.

The gap: AI drafts fast, but it will invent or mismatch numbers, dates and responsibilities if you let it. That’s why you need a strict single source of truth and a short verification workflow.

Why this moves the business needle: Cut draft time to 2–5 minutes, verification to under 10 minutes, and reduce post-signature errors to near-zero. That improves close velocity and protects margins.

Practical lesson: Use AI to generate language and structure. Use human guardrails for numeric truth. The fastest, safest SOW workflow has three parts: intake (single truth), AI draft, targeted human check.

1. What you’ll need
   • A one-paragraph project brief.
   • A pricing row in a spreadsheet marked as the single source of truth (Row ID).
   • A short deliverables list with acceptance criteria for each deliverable.
   • An editable SOW template and access to an AI writer.
   • An intake form that forces: Brief, Pricing Row ID, Milestone Dates, Client Responsibilities, Acceptance Criteria.
2. How to implement (step-by-step)
   1. Prepare the pricing row: include Row ID, unit rates, quantity, total, tax, payment terms, and milestone dates.
   2. Paste: one-paragraph brief + “Use pricing from Row ID X” + deliverables checklist into the AI. Use the prompt below.
   3. Get the 1-page SOW draft (2–5 minutes). Immediately compare Costs and Dates in the draft against the pricing row — a visual check or copy/paste compare takes 2–5 minutes.
   4. Run a second AI check: ask for inconsistencies only (numbers that don’t match, vague responsibilities, missing acceptance tests).
   5. Attach the pricing snapshot as Appendix A and add an explicit change-order clause before sending to client for one-round sign-off.

Copy-paste AI prompt (SOW draft):

You are an experienced SOW writer. I will provide: a one-paragraph project brief, a pricing reference labeled “Row ID X”, a deliverables checklist with acceptance criteria, and milestone dates. Produce a concise, professional 1-page Statement of Work with these sections: Overview, Scope, Deliverables (with hours/estimates), Timeline & Milestones (include the provided dates), Costs & Payment Terms (use numbers from Row ID X exactly), Assumptions, Change Control (steps and rates), Acceptance Criteria, and Client Responsibilities. Use clear, non-legal plain English. Flag any missing information needed to finalize the SOW.

Copy-paste AI prompt (errors & inconsistencies):

Review the SOW I will paste. List ONLY items that are inconsistent with the single source of truth (pricing Row ID X and milestone dates), ambiguous client responsibilities, missing acceptance criteria, and any numeric errors. Output a short checklist I can use to verify before sending.

Metrics to track

• Time to first draft (target: <10 minutes)
• Verification time (target: <10 minutes)
• Revision rounds (target: 1)
• Post-signature errors (target: 0–1%)
• Days from brief to signed SOW (target: <7 days)

Common mistakes & fixes

• AI invents pricing — fix: block-and-compare to pricing Row ID before sending.
• Vague deliverables — fix: require measurable acceptance criteria in intake.
• No change-order process — fix: include a standard clause and hourly uplift in the template.
• Missing client responsibilities — fix: make that a mandatory intake field.

1. 7-day roll-out plan
   1. Day 1: Build the pricing row template and assign Row IDs.
   2. Day 2: Create the mandatory intake form fields.
   3. Day 3: Run 3 past briefs through the AI prompt and compare.
   4. Day 4: Finalize SOW template with Appendix A pricing snapshot and change-order clause.
   5. Day 5: Pilot with a live proposal; time each step.
   6. Day 6: Fix common omissions and update intake checklist.
   7. Day 7: Lock the flow and brief the team on verification steps.

Your move.

Good point — starting narrow and using Keyword Planner plus AI for long-tail ideas is exactly the right approach. I’ll add a tighter, results-focused playbook so you can pick winners fast and avoid wasted spend.

The problem: Tight budget + broad keywords means money disappears before you get conversion data.

Why this matters: With a small budget you must optimize for cost-per-conversion, not clicks. A single winning keyword or ad group should pay for the whole campaign.

Experience-backed lesson: In tests with small budgets, 80/20 applies — 20% of keywords produce ~80% of conversions. Your job is to find that 20% quickly and double down.

• Do: start with 3–5 focused seed phrases, use phrase/exact match, add negatives, test small.
• Do not: run broad match across many themes, split your budget across >5 locations, or ignore landing page alignment.

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

1. Gather: 3–5 core products, target city/region, monthly budget, estimated conversion rate (use 2–5% if unsure).
2. Seed → Expand: put seeds into Keyword Planner for CPC/volume. Ask AI to generate 15–25 long-tail, buying-intent variants.
3. Filter: keep keywords with CPC ≤ your max acceptable CPC and clear commercial intent.
4. Estimate ROI: projected clicks = budget ÷ CPC; conversions = clicks × conversion rate; CPA = budget ÷ conversions.
5. Structure: create tight ad groups (1–2 themes), use phrase & exact match, set bid = target CPC, add negatives from search terms report.
6. Test: run for 7–14 days with small daily caps, then reallocate to keywords with lowest CPA.

Worked example

Budget: $500/month. Target CPC ≤ $1.50. Conversion rate estimate: 4%.

Projected clicks = 500 ÷ 1.50 = 333 clicks. Estimated conversions = 333 × 0.04 = 13.3 → ~13 conversions. Cost per conversion ≈ 500 ÷ 13 = ~$38. If your product margin supports $38 CPA, proceed; if not, tighten targeting or increase conversion rate with a better landing page.

Metrics to track (weekly)

• Clicks, impressions, CTR
• Average CPC
• Conversion rate (per ad group/keyword)
• Cost per conversion (CPA)
• Search terms report (to add negatives)

Common mistakes & quick fixes

• Running too many keywords: fix by cutting to top 20% performers after 2 weeks.
• No negatives: add negatives daily from the search terms report.
• Poor landing page: test simple change—headline and CTA alignment—before raising bids.

Copy-paste AI prompt (use this to expand seeds and judge intent)

Prompt: “I sell [product/service] in [city/region]. Give me 25 long-tail Google Ads keywords with strong buying intent (use terms like ‘buy’, ‘near me’, ‘best price’, model numbers). For each keyword, estimate whether the intent is high/medium/low and suggest a likely CPC range for a small local campaign.”

1-week action plan

1. Day 1: List 3–5 seeds, run Keyword Planner, paste results into AI prompt.
2. Day 2: Filter to 15–25 keywords, set up 3 tight ad groups, add 20 negatives.
3. Days 3–7: Run ads with daily caps, review search terms and CTR, pause irrelevant keywords, update negatives.

Sign-off: — Aaron

Your move.

Spot on: your single-CTA spine and “moment scoring” solve the two biggest failure points — scattered messaging and weak clips. Let’s turn that into a repeatable factory you can run every month without reinventing the wheel.

The issue: Drafts aren’t the bottleneck anymore — consistency and handoffs are. Without a simple operating system, you slip deadlines, dilute the CTA, and lose conversions.

Why it matters: A predictable, 72-hour turnaround from webinar to assets compounds reach, warms your list, and feeds pipeline with one narrative. That’s how you move from “busy” to revenue.

Field lesson: Treat this like assembly, not art. Define inputs, gates, and outputs. Quality rises and speed follows when everyone knows what “done” looks like.

What you’ll need: your recording, a cleaned transcript, a spreadsheet (for the spine sheet), a text editor, a basic video editor, and an AI assistant. One human review pass for tone, facts, and compliance.

1. Create your spine sheet (15 minutes).
   • Make columns: Takeaway, Timestamp, One-line Hook, Proof Source, Clip Score (clarity/novelty/emotion/utility), CTA, Owner, Status.
   • File code: WB-YYYYMMDD-TOPIC (example: WB-2025-01-12-Inflation). Use this code everywhere (filenames, UTMs).
2. Build a 7-rule style snapshot (10 minutes).
   • Paste two of your best articles/emails into AI and generate a mini style guide so drafts sound like you.
3. Run structured drafting (30–45 minutes).
   • Use the master prompt you have to generate blog, emails, and clips. Then immediately run the polish prompts below for tone, evidence, and compliance flags.
4. Human edit gate (30–60 minutes).
   • Acceptance criteria: one narrative, one CTA repeated, blog includes intro + 3–6 sections + conclusion, 2 proof points, email subjects under 45 characters, clips hook in first 7 seconds with captions, compliance checked.
5. Package and publish (30–45 minutes).
   • Blog: add CTA in intro and conclusion. Emails: load as a sequence, schedule A/B on the first two subjects. Videos: add on-screen text (max 10 words) and the same CTA line in captions.

Copy-paste AI prompts (robust):

• Style Snapshot Builder: “From the two samples below, produce a 7-rule style guide: voice, sentence length, preferred verbs, level of formality, banned phrases, CTA tone, and reading level. Then confirm how to apply these rules to future drafts. Samples: [PASTE TWO SAMPLES].”
• Evidence & Compliance Pass: “Review the outputs below. 1) Highlight any claims that need a source. 2) Propose a neutral, compliant rewrite for each. 3) Insert bracketed notes where a disclaimer should appear. Keep my style guide: [PASTE STYLE RULES]. Content: [PASTE DRAFTS].”
• Packaging Optimizer: “For this blog, emails, and video scripts, ensure one unifying CTA. Add the CTA in the blog intro and conclusion, write two alternative email subjects (<45 chars), and a 7-second video hook for each clip. Maintain tone per this style: [PASTE STYLE RULES]. Content: [PASTE DRAFTS].”

What to expect: For a 60-minute webinar, budget 60–120 minutes of human editing to finalize a 1,000–1,500 word blog, a 5-email sequence, and 3–6 short clips. With the spine sheet and file codes in place, week two typically drops to 45–90 minutes.

KPIs that prove progress (track weekly):

• Throughput: 1 blog, 5 emails, 3–6 clips per webinar.
• Time-to-first-asset: under 72 hours from recording.
• Blog: scroll depth 50–60%; CTA click-through ≥ 2–4%.
• Email: open rate +3–5 points vs. prior 4 sends; CTR 2–5%; reply rate ≥ 1%.
• Video: 3-second view rate ≥ 40%; watch to 50% ≥ 30% for top clips.
• Conversion: CTA clicks to booked calls/downloads via UTMs.

UTM and naming discipline (simple and vital):

• Pattern: utm_source=[blog|email|video]&utm_medium=organic&utm_campaign=WB-YYYYMMDD-TOPIC&utm_content=[asset-id-01-05].
• Result: you’ll attribute which asset actually triggered action — no guesswork.

Common mistakes and quick fixes:

• CTA drift → Freeze one CTA for the whole campaign. Repeat it everywhere.
• Voice mismatch → Use the 7-rule style snapshot before drafting, not after.
• Clip bloat → Cut to 30–60s. If it needs 90s, front-load the answer in 7 seconds.
• Weak proof → Require one data point or example per blog section. AI can propose; you verify.
• Compliance surprises → Run the Evidence & Compliance Pass and add bracketed disclaimer notes before final edits.

1-week action plan (crystal clear):

1. Day 1: Name the campaign (WB code), create the spine sheet, run the Style Snapshot Builder.
2. Day 2: Generate drafts with your master prompt; log takeaways, timestamps, and clip scores in the spine sheet.
3. Day 3: Run Evidence & Compliance Pass; add sources and disclaimers; lock the CTA.
4. Day 4: Human edit the blog to acceptance criteria; insert two proofs.
5. Day 5: Finalize the 5-email sequence; set UTMs; schedule with a subject A/B for Email 1.
6. Day 6: Cut and caption 3–6 clips; apply the Packaging Optimizer for hooks and on-screen text.
7. Day 7: Publish the blog and 2 clips; send Email 1; confirm UTMs track. Review early metrics and note one tweak for the next send.

Bottom line: You’ve got the right spine. Layer in the style snapshot, spine sheet, and UTMs, and you’ll have a repeatable factory that ships in 72 hours and attributes results.

Your move.

You’re right to center on AI as the draft engine plus a quick classroom check. Let’s turn that into a repeatable system with clear targets, fast iteration, and measurable outcomes you can trust.

Hook: You can land within ±75L of your target in two passes by controlling just four levers: sentence length, rare-word use, explicit vocabulary, and passage length.

The problem: Most AI drafts miss Lexile by 100–200 points and drift in tone. Teachers waste time “fixing” instead of teaching.

Why it matters: Hitting the right readability range improves time-on-task and comprehension. It also makes differentiation doable—same topic, three levels, no stigma.

What experience teaches: Don’t chase a single exact Lexile. Aim for a tight band (e.g., 420–480L). The insider trick is a two-pass prompt: first, plan sentence lengths and target words; second, write to that plan. That stabilizes readability and tone.

Exact steps (do these in order)

1. Define the band and guardrails: Target Lexile range; word count (100–250 words); average sentence length (8–12 words); max sentence length (16 words); 4–6 target vocabulary words with parenthetical, simple definitions; neutral, age-respectful tone.
2. Two-pass generation:
   • Pass 1 (plan): Ask the AI for a sentence plan: number of sentences, length per sentence, where vocabulary appears, and which two sentences may be compound.
   • Pass 2 (write): Have the AI draft to the plan, then self-check and adjust any sentence exceeding your max length.
3. Verify: Run readability/Lexile check. Record: estimated Lexile, average sentence length, longest sentence length, total words.
4. Tune with a rule-of-three: Make up to three edits only—split the longest sentence, replace one rare word with a target word, remove one clause. Re-check.
5. Scaffold: Add 2 multiple-choice questions (one literal, one inferential), 1 writing prompt, and a 3–5 term glossary. Keep Qs aligned to the passage’s verbs and nouns.
6. Pilot fast: 3–5 students; measure minutes to read, words-per-minute, % correct, and a 1–5 engagement rating. Note any stumble words.
7. Finalize: Adjust tone or specific words flagged in pilot; re-check readability; publish.

Copy-paste AI prompt (two-pass method)

Pass 1 — planning: “Plan a leveled reader passage on [topic] for a target Lexile band [e.g., 420–480L]. Constraints: 160–190 words; average sentence length 9–11 words; max sentence length 16 words; neutral, age-respectful tone; include these vocabulary words with parenthetical definitions on first use: [list 4–6 words]. Output only: (1) a numbered list of 12 sentence lengths that meet the constraints; (2) which two sentences may be compound; (3) where each vocabulary word will appear.”

Pass 2 — drafting: “Using the plan above, write the passage. Use concrete, accurate facts and flag any uncertain claims. Keep sentence lengths at or under the plan; if any exceed 16 words, shorten them. After the passage, add: (a) 2 multiple-choice questions (one literal, one inferential); (b) 1 short writing prompt; (c) a 3–5 term glossary. End with your estimated Lexile or readability score.”

Premium wrinkle (speeds calibration): Generate a mini text set on the same topic at three bands in one go: Low (−100L), Target, High (+100L). In the pilot, start at Target; if time-to-read exceeds expectation by 25% or comprehension dips below 70%, step down to Low for instructional text, keep High as challenge homework.

Metrics to track (report weekly)

• Draft-to-target Lexile delta (points) and hit rate within band (%).
• Time to first usable draft (minutes) and total edit cycles (count).
• Pilot outcomes: comprehension % (goal ≥ 75%), words-per-minute vs grade norms, engagement 1–5 (goal ≥ 4).
• Teacher edit time per passage (minutes) and flagged issues (factual/cultural) per 1,000 words.

Common mistakes and fast fixes

• Chasing an exact Lexile → Define a 60–80L band. Optimize for comprehension + WPM, not a single number.
• Childish tone for older readers → Specify “age-respectful tone; mature topics with simple language; no babyish phrasing.”
• Vocabulary drift → Require first-use definitions in parentheses; repeat each target word 2–3 times.
• Long sentence spikes → Cap max sentence length; in edits, split the top two longest sentences first.
• Factual or cultural slips → In the prompt, instruct “neutral, culturally sensitive examples; flag uncertain claims.” Always do a human pass.

1-week action plan

1. Day 1: Pick one topic; set three bands (e.g., 380–440L, 420–480L, 500–560L). Prepare 4–6 target words.
2. Day 2: Run the two-pass prompts for all three bands. Log planning outputs and first drafts.
3. Day 3: Verify readability; apply rule-of-three edits; re-check. Add Qs, prompt, glossary.
4. Day 4: Teacher review for accuracy and cultural fit. Timebox to 20 minutes per passage.
5. Day 5: Pilot with 3–5 students. Capture WPM, % correct, engagement, stumble words.
6. Day 6: Adjust based on pilot; finalize the “Target” and keep Low/High as differentiation.
7. Day 7: Create a shared template with your prompts, guardrails, and KPI tracker; schedule the next topic.

What to expect: First usable draft in 10–20 minutes, band accuracy within ±75L after one tuning pass, classroom-ready by Day 3–5, and a clear record of comprehension and engagement gains over two cycles.

One question to tailor the next template drop: Which Lexile band and grade span do you want to standardize first (e.g., 300–400L for Grade 2, or 500–600L for Grade 4)?

Your move.