Elevare - Debby Action Plan - v2

Where language
meets life.

Your 60-day plan is locked for review. Full merged plan + pre-ship audit + your action steps below. Read time: 8 minutes. Action time: ~90 minutes across today and tomorrow.

From Donal 2026-04-15 Goal: lock Week 1, ship Monday

Hit play - hear Debby's 50-sec intro

Two handsome Irish boys and the Elevare origin story.

Tap to hear (opens in Drive)
Audio URL pending - Donal pasting in
Where we're at

What's changed since you last saw the plan

Three additions, all customer-facing, all meant to stress-test the plan before any ad dollar lands.

Added

Stage 4 Deep-Dive

The $29/mo AI Tutor Practice Buddy is now fully specced: pedagogy (Benny Lewis + Krashen), 4 session modes, architecture + latency budget, Amara persona + system prompt, pronunciation scoring, SRS loop, 10-prospect demo flow, tier gating, safety + moderation, KPIs + failure modes, 60-day build order.

Added

Security, Stability, Speed audit

35 risks identified before launch. 11 must-fix-before-ship, 15 must-fix-in-first-month, 9 optimise-later. Zero redesigns needed, all mitigations.

Timeline

60 days, not 90

Because you're in Chiang Mai with your coworking AI-expert crew on tap, velocity is 2-3x solo-remote. We capture that window. The $5k Day-90 stretch stays; the main push compresses to 60.

What's coming

A build template we're testing overnight

If it works, your Stage 4 build runs as 3 cycles x 4 waves of parallel AI agents. You get the output, not the template. Expect cleaner, faster shipping.

Tonight, while you sleep

What Donal is shipping

So you know the picture. 16 parallel streams ran on Donal's M5 overnight. You wake up to working infrastructure, not empty promises.

The picture

16 agents worked in parallel while you slept. Review queue tomorrow is substantial, that's the point.

StreamWhat it builtFilesScope
Wave 1
8 subagents (C/D/E/G/H/I/K/M)
Product code, legal, ads, social, email, SEO, QA, sales41 filesCustomer-facing assets + delivery infrastructure
Wave 2
5 subagents (L/N/O/P/Q)
Keywords, QA, marketing cron, paid onboarding, coach-prep29 filesFunnel + retention + ops automation
CC windows
3 chats (A/B/F)
DNS, voice-clone infra, incident + monitoring15 filesFoundation infra + safety net
Totals: 16 parallel streams · ~90 files on main · 4 commits db07bad / f602873 / d9cec36 / +current
Translation

You wake up to working DNS, a voice-clone pipeline ready for your sample, a ready-to-merge Stage 4 v0 PR, a one-click site-fix patch, drafted legal docs, and a full ops runbook. You review, not build.

What we need from you

5 steps, ~90 minutes total

In this order. Reply in one Telegram message when done, or three if long.

Overall progress
0%
1

Blocker sheet (10 min, mostly AI-driven)

10 min

I've pre-filled Time-to-do / Time-freed / ROI across the blocker table below. Estimates marked with *. Your job is faster than from-scratch:

  • Feed the docs into your OpenCode. Tell it: "Audit the blocker table. For any row where my situation differs, flag it and suggest a better estimate. Return as a markdown diff."
  • Override my * estimates where yours differ. Replace * with (D) on changed rows.
  • Fill Status + Notes yourself, one line each.
  • Strike out anything that doesn't apply. Add anything missing.
Why this way: humans bring the context AI doesn't have. AI bulks the repetitive stuff. You + OpenCode beats either alone.
0%
2

Your open questions (20 min, ALL AT ONCE)

20 min, bulk in one message

Things you've been wondering about that we haven't covered. Drop as bullets in one Telegram message, not dripped over the day. Full list lets me answer in one pass and plan around it.

"How do I handle a student who wants to pay in Thai baht?" · "Can I record the voice sample in two takes?" · "Should I keep the Skrill button while Whop is setting up?"

No filter. Bulk them. Send once.

0%
Live placeholder

Your questions land here once you Telegram them to Donal

[Empty slot, waiting for your list]

3

Plan feedback, paragraph-by-paragraph (30-40 min)

30-40 min

Open the master plan. For any section you have thoughts on: copy the text, put it in quote marks, add a dash, write your feedback, tell me which section.

Example 1, copy critique

Section: "First-session wow moment"
"Amara is warming up, pour yourself a coffee." - I like the warmth but worried it implies the tech is slow. Could we test "Amara is getting her notes ready" (purposeful) vs the coffee line?

Example 2, missing-thing flag

Section: "Session types (4 modes)"
"Lesson-guided, Freeform practice, Pronunciation drill, Scenario rehearsal" - nothing here for a student prepping IELTS/TOEFL. Add an "Exam prep" mode, or is that under Scenario? If covered, say so explicitly.

Example 3, factual correction

Section: "Pricing Math" (Day 30 = $750)
"5x Lingua Live ($745) + 10x AI Tutor ($290) = $1,035" - my Lingua Live is $179/mo not $149, so 5 x $179 = $895. Either drop price Month 1 or re-math the target.

Focus on Stage 4 Deep-Dive and Week 1 Checklist, highest-leverage.

0%
4

Feed both docs into your OpenCode (10 min)

10 min

Feed the docs into your OpenCode. Paste both URLs. Tell it:

"Read these two docs. Ask me 5 clarifying questions based on gaps, choices that need my input, or things that don't match my actual situation."

Reply to those 5. Copy the whole exchange. Send to me on Telegram. Your OpenCode will spot stuff we missed.

0%
5

Done

-

Once I have: blocker edits + open questions + plan feedback + OpenCode exchange, I adjust the plan, send you locked Week 1, we ship Monday.

0%
How to send feedback

This page is a live preview, not an editor

  1. Feed docs into your OpenCode, then paste the exchange to Donal on Telegram.
  2. Telegram Donal directly, bullet edits by section name.
  3. You have Read access to agency-operator on GitHub. Open the MD version there if you want raw source.

Edits land via Telegram, not this page.

The blocker sheet

Edit this

* = Donal/Claude estimate. Override with yours, replace * with (D) on changed rows.
You fill: Status + Notes. Override any * value you know better.
Priority is locked, don't change.

P0 - Gating Week 1

must move today or tomorrow
#BlockerOwnerPriTime-to-doTime-freedROIStatusNotes
B01Answer the 5 start-here questions (voice, tutor team, beta students, Whop, daily window)DebbyP015m~30 hrs Donal parallel workWhole Week 1 plan
B02Record + send the 5-min voice sampleDebbyP020m2-3 day voice-clone waitAmara has your voice, ad demos possible
B03Sign up for Whop (free) at whop.comDebbyP010mPayment rail liveAll paid conversions, $750 Day-30
B04Fix site honesty issues (WhatsApp placeholder, fake 14 open positions, Rise mental-health framing)DebbyP020m (after Donal's patch)Ads legal to runAd spend becomes possible
B11elevare.work DNS + Zoho Mail verify (debby@, hello@, tutors@)DonalP01-2 hrsEmail + brandAll comms professional

P0 - Gating Stage 4 build

this week
#BlockerOwnerPriTime-to-doTime-freedROIStatusNotes
B05OpenAI API key wired into tutor-dashboardDebby + crewP015mAI Tutor v0 runs3 beta students test
B06Cloudflare account set up (R2, Workers, Vectorize)Debby + crewP030mArchitecture liveVoice + state + KB possible
S3API-key audit on darnygirl/elevare/.gitignore before next pushDebby + DonalP015mSafe commitsPrevents breach

P0 - Gating ads

this week
#BlockerOwnerPriTime-to-doTime-freedROIStatusNotes
B08Meta ad account under Debby's name (Donal's is banned)DebbyP030m$100 ad spend unlocksDay-30 $750 realistic
B09Meta Pixel + Conversions API installed on siteDebby + DonalP01hAd tracking worksCan measure conversions
B10Business verification on MetaDebbyP01-2 hrs + waitSpending caps liftedScale past $100/day
Show P0 legal/safety + P1 first-month tables (S1, S2, B07, ST1, ST2, ST7, SP1, W4-W6)

P0 - Gating legal / safety

before any ad runs
#BlockerOwnerPriTime-to-doTime-freedROI
S1Voice-clone consent doc signedDonal (legal)P030mVoice clone liveProtects you + brand
S2Privacy policy + DPA with OpenAI / Cloudflare / Airtable before adsDebby + DonalP02 hrsAds can startGDPR + Thai PDPA safe

P1 - First month

must fix by Day 30
#BlockerOwnerPriTime-to-doTime-freedROI
B075 open questions answered (voice branding, coach handoff, off-topic rules, retention, Orpheus fallback)Donal + DebbyP130m callCycle 3 build lockedClean Stage 4 spec
ST1M5 Orpheus to XTTS automatic failoverDonal (code)P12 hrsNo single point of failureStudents don't churn on outage
ST2Multi-provider API fallback (Sonnet, Haiku, text-only)Donal (code)P13 hrsOutage-resilientRefund-proof sessions
ST7Kill switch dry-run (pause AI tutor, all traffic to humans)Donal (ops)P130mCrisis plan testedReact in 30 sec
SP1Latency validation (p50 < 2.5s, p95 < 4s)Donal (code)P14 hrsUX meets targetNo "laggy" churn
W4Incident runbook (API outage, voice down, payment fail, student distress)DonalP12 hrsDebby can actFewer Donal pings
W5Staging environment (Cloudflare preview + feature flags)DonalP13 hrsSafe deploysNo prod regressions
W6Monitoring (uptime + p95 latency + error rate alerts)DonalP12 hrsEarly warningCatch failures early

P2 (optimisation / later): rolled into Cycle 2 + 3 exit criteria of the build plan. See Stage 4 Deep-Dive in the master plan.

The 60-day arc + stretch

Month 1, Month 2, Month 3

Where we're heading. M1 is now. M2 locks the model. M3 is the stretch goal that proves the system can scale without you.

Month 1, current focus

Honest foundation, first cash

Day 0 to Day 30
Goal: $750 MRR
  • Site honesty + Whop live + 3 beta students on AI Tutor v0
  • Voice clone trained, ads legal to run
  • Week 1 ships Monday, blocker sheet cleared
0%
Month 2

State model + first testimonials

Day 30 to Day 60
Goal: $1.5k MRR
  • Stage 4 v0.2 with state model, 10 paying students
  • Monday marketing brief live, weekly cron operating
  • First testimonials captured, voice-clone content engine live
0%
Month 3, stretch

RAG + scoring + tier bump

Day 60 to Day 90
Goal: $5k MRR (stretch)
  • RAG layer (Cloudflare Vectorize) live for freeform mode
  • Voice-clone ad demos shipping, Whop tier bump $49 to $79
  • Pronunciation scoring MVP, autonomous pipeline kickoff
0%

If stuck

Ping Donal

Telegram him. One line: "Stuck on [thing]." He replies with the next step. Don't sit on anything over 2 hours.

Important

Do not read the master plan cover to cover. It's 2,000+ lines, designed for skim-to-section. Hit Stage 4 Deep-Dive, Week 1 Checklist, Commercial Reality. Skip the rest unless you're curious.

Elevare · 2026-04-15 · v2 · Where language meets life.