Elevated Connections — Easy-to-Understand System Review

A clear review of your contacts, follow-ups, messages, and AI tools

Location jKDGcgAPUDBfll8zpO3V · Penticton, British Columbia · 17 August 2026

82
Contacts
incl. test & duplicate records
14
Potential sales
none have been moved forward or given a dollar value
26
Automatic follow-ups
23 active · 3 unfinished · 1 has an error
106
Information fields
about 25 repeat information stored elsewhere
0
Reusable business details
links and details must currently be changed one by one
18
Funnels
6 for Kangen alone · 6 templates
3
Active AI tools
2 sorting tools · 1 automatic chat assistant
CA$0
Revenue tracked
all time
Is the account ready for AI?overall score: 2.8 / 10

Each area is scored from 1 to 10. A score of at least 7 out of 10 is recommended before allowing AI to speak or make decisions without your approval. Place your mouse over a bar to see why it received that score.

0246810
Readiness score · vertical rule = AI-deployment threshold (7)
2.8 / 10 Not ready for unsupervised AI yet. The good news is that this can be cleaned up in 3–4 weeks. You do not need to start over.

What this score means: this is not a criticism of you or the people who helped build the account. The system was created for the larger business you are building, but there have not been enough leads yet to make every problem obvious. The repair list is clear and manageable. We simply need to fix the foundation before adding more AI.

● URGENT Please fix these within a few days8 items
1 · The chat assistant can answer people automatically without your approved information CONFIRMED

EC Assistant is set to Auto Pilot and deployed to SMS, Instagram (all pages), Facebook (all pages), TikTok, WhatsApp and Live chat. Bot Training reads verbatim: "No triggers configured. Add a trigger to route conversations to specific knowledge bases." Its instructions are template defaults — "Your goal is to assist the customers with their queries" — with no product information, no pricing, no scope boundary and no compliance language. Both "Send bot to sleep when I send a: Manual Message" and "Workflow Message" are OFF, so it may continue replying while you are personally speaking with someone or while your scheduled messages are being sent.

This is a wellness business making nervous-system and hydration claims, selling water systems and recruiting income partners. Usage is currently near zero (1 unique contact, 0 actions, 0 bookings MTD) — which is exactly why this is cheap to fix now and expensive after traffic scales.

AI Agents → Conversation AI → Agents List → EC Assistant → Bot Settings / Bot Training / Agent Deployment
2 · The AI is sorting some leads into labels that do not exist CONFIRMED

EC Lead Sorter (Published) runs as step 1 of the master router on every intake submission.

AI Sorter branchTag the agent writesTag that exists in CRMMatch
NSR Leadint-ecresetint-nsrNo
Kangen leadint-kangenint-kangenYes
Partner Leadint-businessint-partnershipNo
Unsure— no tag, straight to End NodeSilent drop

The agent's prompt compounds it, instructing the model that "Workflow values must be exactly: NSR Main Workflow / Kangen Intake / Audit Path / Elevated Partnership Workflow"none of those three workflows exist in this account. As volume rises this forks the taxonomy into populations no filter reconciles.

AI Agents → Agent Studio → Flow Agents → EC Lead Sorter → click each "Update Tag" node · compare with Settings → Tags
3 · Some Facebook and Instagram replies are not reaching your leads CONFIRMED

Comment Trigger - NSR - RESET appears under Needs review (1). Execution logs, 13 Aug 2026:

TimeContactActionStatus
9:03:01 amReese Gracefb_interactive_messengerError
9:03:00 amReese GraceInstagram DMSkipped
9:02:59 amits_allgrayfb_interactive_messengerSkipped
"Can't send Facebook message as the last inbound message was earlier than 24 hours ago and there is no valid Facebook inbound comment message."

This is a design fault, not just a connection fault: a Wait step sits between the first and second DM, so by the time the follow-up fires Meta's 24-hour messaging window has closed. Compounding it, the Instagram integration shows a red alert badge. Comment-triggered DM is the primary top-of-funnel motion for all three pillars.

Automation → Workflows → Needs review (1) → Comment Trigger - NSR - RESET → Execution logs → View details
4 · Alerts are turned off when an automatic follow-up fails CONFIRMED

Global Workflow Settings → Notifications: OFF. This is why P0-3 sat unresolved for four days. Every future automation failure will also fail silently — the single most dangerous default in an account about to run AI agents.

Automation → Global Workflow Settings
5 · A person can receive the same partner emails more than once CONFIRMED

Partner — Non-booker Follow-Up Sequence (14 enrolments) has two triggers — tag added int-partnership and a funnel page view on the partnership video page — with Allow re-entry ON, Allow multiple opportunities ON and Stop on response OFF. Every revisit to the video page re-runs the entire 3-email sequence and can create another opportunity.

Worse: the act-bookedcall check happens once, at the top. Someone who books after Day 1 still receives Days 2 and 3 asking them to book.

Automation → Workflows → Partner — Non-booker Follow-Up Sequence → Builder + Settings
6–7 · Some leads can disappear without anyone being notified CONFIRMED

The AI Sorter's "Unsure" branch routes straight to an End Node — no tag, no note, no notification. The master router's "None" branch does the same for anyone who submits the intake form without selecting an interest. In both cases a real lead disappears and nobody is told.

Agent Studio → EC Lead Sorter (Unsure → End Node) · Automation → WF-EntryIntake-Router (None branch)
8 · Anyone can enter the Legacy Partner follow-up, even if they are not a good fit CONFIRMED vs stated requirement

The brief states partnership "should NOT automatically be offered to everyone". In practice, anyone who submits Partners Optin, or ticks the partner option on the intake form, is immediately tagged, given an opportunity, and entered into partner nurture — with no qualification step anywhere. The tags int-partnership-qualified and int-partnership-clarity-call exist but appear unused, and the Pre-Call Qualification – Version B form receives submissions that nothing reads.

Sites → Forms → Pre-Call Qualification – Version B · Automation → Partnership | Opt-in Entry · Settings → Tags
◆ IMPORTANT Fix these before adding more AI14 items
IDFindingLabel
P1-1Kangen leads split across two tags — the quiz path applies kangen-quiz-completed, the router applies int-kangen. Two disjoint populations that never reconcile.CONFIRMED
P1-2{{contact.radio_15uga}} and {{contact.radio_17wad}} are hard-coded in the live AI Summary Agent prompt. Rename those fields and the prompt renders blank — with no error.CONFIRMED
P1-3The hydration quiz is captured twice: Quiz | 5 Minute Hydration Quiz (15 radio fields) and Survey | Survey 0 (13 checkbox fields) ask the same 12 questions. Two fields are both labelled "Q7."; two ask "How much water do you drink daily?"CONFIRMED
P1-4No lifecycle, stage or temperature fields — only additive stat-* tags that nothing removes. A contact can be stat-cold and stat-hot simultaneously.CONFIRMED
P1-5Zero Custom Values. Every booking link, offer name and brand fact is hard-coded inside individual emails and workflows — and the AI has no canonical source to reference.CONFIRMED
P1-6Not one workflow has "Stop on response" enabled. Nothing in this account stops talking when a human being replies.CONFIRMED
P1-712 knowledge bases, each containing a single FAQ question, 0 documents grouped, 12 of 15 slots burned — and none attached to the live chatbot.CONFIRMED
P1-8The AI Summary Agent's output has no destination; its router transition is still the unconfigured placeholder text "Describe the transition condition" → End Node.CONFIRMED
P1-9Interest Selection is multi-select feeding a first-match If/Else. A lead interested in both NSR and Kangen is silently classified as NSR only — your most cross-sell-ready leads are the most mis-segmented.CONFIRMED
P1-10Hands On Therapy is a whole business line — own domain, website, 6 workflows, 5 calendars, 3 forms — with no tag, no pipeline, and no place in either AI agent's prompt.CONFIRMED
P1-11Allow multiple opportunities is ON on the master router, which creates opportunities in all three branches.CONFIRMED
P1-12Pipelines encode entry branch, not progress. 11 of 11 opportunities sit in "Routed:" stages; 3 of 3 in "Routed - New Lead". Engaged, Booked, Attended, Buyer and Converted have never held an opportunity. All values CA$0.00.CONFIRMED
P1-13You currently have two administrator accounts — "Jen ElevatedConnections" and "Jen HandsOnTherapy". This can split your notifications, calendar information, and record ownership between two places.CONFIRMED
P1-14You do not have saved contact lists for NSR, Kangen, Partners, Hands On Therapy clients, or leads who still need review. This makes it difficult for you to quickly see each group.CONFIRMED
▲ NEXT  ○ LATER Organization and cleanup27 items

Fix next

  • Six Kangen funnels with no canonical entry point (Bonus Version B, Product Education, Kangen Water, Simple LEAD Gen, SLO funnel, Business Opportunity)
  • Three overlapping intro calendars (Discovery Call / No-Cost Initial Consultation / Free Q&A Call) and five near-duplicate HOT calendars; only 2 of 5+ are in the HandsOnTherapy group
  • No phone number — Phone System is blocked at an incomplete 2FA step. No SMS anywhere; the SMS-reply notification workflow can never fire; the chatbot is deployed to a channel that doesn't exist
  • No cancellation or reschedule handling on appointment reminders
  • 16 orphaned custom fields from deleted assets (Survey 0 13, HOT Liability Waiver 2, Optin 1)
  • Duplicate contacts — four records for the same person (Christine Mendoza / Chrstnxm9 / Christine Marco / Christine M), who is also an admin user
  • Test data in production: Test 1, Asd, and a contact literally named testing (the most recent router enrolment)
  • ~10 contacts with no email and no phone — social DM captures that cannot be nurtured and skew every denominator
  • No UTM strategy; 12 src-* tags as a manual substitute; "NA" values in the attribution report
  • Zero custom reports, zero dashboards; the main Dashboard is still the default FG onboarding screen
  • GeminiBackEndAiProtocol private-integration API key — active since 21 Apr, Last Used: never
  • 5 published workflows have never enrolled anyone; 1 draft workflow (Kangen Water – Video Follow-Up) has 2 stranded contacts
  • No Preference Management — subscribers can only opt out of everything
  • GA4 / GTM / Meta Pixel not confirmed; external tracking script installation unverified
  • 4 of 5 users hold ACCOUNT-ADMIN; elevatedconnections.ca is connected with no products attached

Clean up later

  • Six untouched "CLONE THIS FUNNEL BEFORE" templates, one template website, three template forms
  • "Form 11" — unnamed form, purpose unknown; "7-DAY EMAIL NURTURE SEQUENCE" — a funnel with 0 steps
  • Tag convention breaks: kangen-quiz-completed, qa-zoom-registered
  • Naming inconsistencies: -PARTNERSHIP spacing; "Day-of Appointment Reminder" also sends a day-before email; "HOT New Client Confirmation" vs "Returning Client Confirmation Email"
  • Two unused snapshot pipelines (Application, Services); garbled "Updated by" values on several forms
  • Business Profile lists Europe as a region of operation for a Canadian business
  • Account timezone America/Los_Angeles vs the business in Penticton BC (America/Vancouver) — functionally identical, cosmetically wrong
  • Hydra chatbot exists, switched off, purpose undocumented; Auto Save ON globally with four admin editors
  • No naming convention or data dictionary documented anywhere
✓ WORKING WELL What is already set up correctly8 items

These parts should be kept while the account is cleaned up. You already have a stronger starting point than many businesses.

  • The tag taxonomy is well designed. 37 tags with a consistent, machine-readable prefix convention — int-, act-, src-, stat-, type-. Better than 90% of GHL accounts and a strong foundation for AI classification, once the AI is made to actually use it.
  • The intent to route rather than blast is present. WF-EntryIntake-Router — the busiest workflow at 69 enrolments — is a genuine router: one intake form, one branch per pillar, tag + opportunity + follow-up per branch. The pattern is correct.
  • Email deliverability hygiene is set up properly. Dedicated sending domain verified, SSL issued, proper warm-up. All three FG hygiene workflows are published and each correctly removes the contact from all workflows, tags them, and sets DND.
  • The 7-Day Journey is properly bookended. Adds int-nsr on entry, then at the end adds int-nsr-completed and removes int-nsr. Deliberate lifecycle state management — rare, and the right instinct.
  • Opportunity source is populating. Real values ("FORM-Entry Intake", "5 Minute Hydration Quiz", "Partners Optin"). The attribution plumbing exists even though the pipeline isn't worked.
  • Social distribution is broadly connected. Facebook, Instagram, LinkedIn, TikTok Messaging, TikTok Lead Gen, Google, Google Business Profile, Google Contacts and Google Forms. Reach is not the bottleneck.
  • A partner qualification form already exists and receives submissions. The gate the business needs has already been designed — it just isn't wired.
  • Audit Logs are enabled and populated. You have a change history, which materially de-risks the cleanup ahead.
What currently happens after someone becomes a lead4 paths

This section shows what the account is doing today, step by step, even when that is different from what was originally planned.

1 · Nervous System Reset

TRAFFIC
 ├─ IG/FB comment "RESET" ──► Comment Trigger - NSR - RESET
 │                             → Respond on comment
 │                             → Instagram DM         ⚠ SKIPPED
 │                             → FB Interactive Msgr  ✖ ERROR (24hr window)
 │                             ► MANY LEADS DEAD-END HERE
 │
 ├─ NSR Optin form ──► EC : 7-Day Journey - Lead Nurture & Access
 │                      → Tag int-nsr → Opportunity (Routed: EC Reset, CA$0)
 │                      → Course Grant → Email Day 1…Day 7 (no exit conditions)
 │                      → Tag int-nsr-completed → REMOVE int-nsr → END
 │
 └─ FORM-Entry Intake ──► WF-EntryIntake-Router
                           → EC Lead Sorter AI   → tag "int-ecreset"  ✖ doesn't exist
                           → EC Lead Summary AI  → output goes nowhere ✖
                           → Branch A → Tag → Opportunity → Course Grant → Add to Workflow → END

CONVERSION: ► NONE DEFINED. No NSR calendar. No paid offer wired.
            "Buyer: EC Paid" stage = 0 opportunities, all time.

2 · Kangen

TRAFFIC
 ├─ IG/FB comment "HYDRATE" ──► Comment Trigger - KANGEN - HYDRATE (same 24hr design risk)
 │
 ├─ 5 Minute Hydration Quiz ──► Kangen Nurture Sequence
 │                               → Tag kangen-quiz-completed   ⚠ NOT int-kangen
 │                               → Opportunity → ~7 emails with waits → END
 │
 ├─ FORM-Entry Intake ──► Router Branch B
 │                         → Tag int-kangen   ⚠ DIFFERENT TAG from the quiz path
 │                         → Opportunity → Email → Wait → Condition → Email …
 │
 └─ 6 separate Kangen funnels, no canonical entry point  ⚠

CONVERSION: ► NONE DEFINED. No Kangen calendar. No product catalogue.
            "Buyer: Kangen Product" stage = 0 opportunities, all time.

3 · Legacy Partner

TRAFFIC
 ├─ IG/FB comment "ALIGNED" ──► Comment Trigger -PARTNERSHIP - ALIGNED
 ├─ Partners Optin form ──► Partnership | Opt-in Entry → Tag → Opportunity → Email → END
 │                          ✖ NO QUALIFICATION STEP
 ├─ FORM-Entry Intake ──► Router Branch C → Tag → Opportunity → Email → END
 │                          ✖ NO QUALIFICATION STEP
 └─ Tag int-partnership  ─┐
    OR partnership video  ├──► Partner — Non-booker Follow-Up Sequence
    page VIEW ────────────┘     → Wait → Opportunity
                                 → Condition (NOT act-bookedcall) ← checked ONCE
                                 → Email Day 1 → Day 2 → Day 3 → END
                                 ⚠ Re-enters on every page revisit

QUALIFICATION: "Pre-Call Qualification – Version B" EXISTS and receives submissions.
               Data lands in a generic "Additional Info" folder.
               ✖ No workflow reads it. int-partnership-qualified appears unused.

BOOKING: "Elevated Connection Partnership Fit…" round-robin calendar exists — ungated.
CONVERSION: "Converted" stage = 0, all time. All 3 opportunities in "Routed - New Lead".

4 · Hands On Therapy — the un-mapped fourth journey

TRAFFIC ──► handsontherapy.ca (2-page website)
         ──► HOT New Client Calendar (90 / 120 min) · HOT Returning Client Calendar (90 / 120 min)
              → HOT New Client Confirmation (7)
              → HOT New Client - 48hr Preparation (5)
              → HOT New Client Intake - Safe Exhale form (18 fields)
              → HOT Liability Waiver (form deleted; 2 orphan fields remain)
              → HOT New Client - 24hr Aftercare        (0 — never used)
              → HOT Returning Client - 48hr Check-in   (0 — never used)
              → HOT 60-Day No Booking Nurture          (0 — never used)
              → Returning Client Confirmation Email (5)

✖ No tag.  ✖ No pipeline.  ✖ Not in either AI agent's prompt.

Where the journeys overlap

  • FORM-Entry Intake is a shared front door for all three stated pillars — and multi-select interest means a lead can only ever be routed to one
  • Every pillar has two entry paths that tag and create opportunities independently
  • All three stated pillars share one 13-stage pipeline, so a lead who is an NSR customer and a Kangen buyer cannot be represented
  • Kangen and Partner overlap by design, and nothing distinguishes "Kangen customer" from "Kangen partner prospect"
  • Your Hands On Therapy clients may also be interested in NSR or Kangen, but your account does not currently connect those services together
  • The Auto-Pilot chatbot sits across all journeys at once and does not pause for workflow messages
Can you easily find the answers to these 8 questions?only 2 can be partly answered
QuestionAnswerable?Why
Where did this lead come from?CoarselyReferral / Social / Direct only. No UTM campaign data. "NA" values present. 12 src-* tags require manual application.
Which pillar are they interested in?NoThree competing mechanisms: workflow int-* tags, AI-applied int-ecreset/int-business, and kangen-quiz-completed. No single field.
What content did they consume?NoPage views tracked in aggregate only. act-emailclicked is a binary flag with no reference to which email.
Did they book?Partiallyact-bookedcall exists, but the "Booked: Call / Q&A" stage has 0 opportunities — so it isn't being used.
Did they buy?NoBoth Buyer stages hold 0. Attribution shows CA$0.00 revenue closed, all time.
What did they buy?NoNo product object, no Kangen model field, Payments module unused.
What stage are they in?No14 of 14 opportunities sit in a "Routed:" stage. Stage reflects entry classification, not progress.
What is their next expected action?NoNo next-action field, no task automation, no follow-up date.

Right now, six of these eight questions cannot be answered clearly. This is the main reason I do not recommend giving AI more control yet. If AI only has part of the information, it may give you an incomplete or incorrect answer with too much confidence.

Where AI can help, and where it should not be usedsimple recommendations

SAFE TO USE WITH REVIEW

  • Short lead summaries for you — AI can turn a person’s 18 written answers into a short three-sentence summary, making it easier for you to understand what they need.
  • Help sorting new inquiries — AI can read longer written answers and suggest where the person belongs. If it is unsure, it should ask you to review the lead instead of guessing.
  • Suggested answers to common questions — AI can prepare a draft using your approved information, but you review and send every message. It should never make health or income claims.
  • Internal weekly summary — read-only synthesis from the new structured fields.

WAIT UNTIL LATER

  • Autonomous conversation handling — needs 60+ days of Suggestive-mode transcripts and a resolved compliance position.
  • Lead scoring — needs won/lost outcomes to learn from. Currently zero opportunities won, ever.
  • Content generation at scale — needs a documented brand voice and compliance checklist.
  • BI / reporting agent — needs the six unanswerable questions to become answerable first.
  • Deciding whether a potential partner is a good fit — this should wait until your form is properly connected and you tell us exactly what makes someone a good partner.
  • Voice AI receptionist — needs a phone number and 90 days of proven text performance.

KEEP THESE HUMAN-CONTROLLED

  • Pillar routing from the intake form — the user already ticked a box. Using AI to re-derive a stated fact is exactly how P0-2 happened. Fix the multi-select handling instead.
  • Tag application — must be deterministic.
  • Appointment reminders — solved by native triggers.
  • Lead-source attribution — a UTM parameter beats a model guess.
  • Partner qualification decisions — MLM-adjacent financial-opportunity decisions must not be made by a model.
  • Any health, medical or income claim — human-written and compliance-reviewed only. Hard-block in every prompt.
Simple 30-day repair plan4 weeks

Week 1 — Stop the urgent problems

Goal: receive alerts when something breaks, and do not let AI answer people without your approval.
  • Set EC Assistant to Off
  • Turn Global Workflow Notifications ON
  • Fix the 3 AI Sorter tag nodes
  • Rewrite the Sorter prompt (real tags, real workflows, all four pillars)
  • Add a notification to the "Unsure" branch
  • Redesign Comment Triggers for the 24-hour window; re-auth Instagram
  • Partner sequence: re-entry OFF, remove page-view trigger
  • Router: multiple opportunities OFF
  • Stop-on-response ON across all nurtures
  • Revoke or document the unused API key

Week 2 — Organize your contact information

Goal: quickly understand who each person is, what they want, and what should happen next.
  • Build 6 structured fields (Lifecycle, Primary Pillar, Temperature, Partner Qualification, Lead Source, Next Action)
  • Add HOT as a first-class pillar
  • Merge kangen-quiz-completed into int-kangen
  • Rename junk fields and update the AI prompt in the same window
  • Delete 16 orphaned fields; resolve the quiz duplication and the duplicate "Q7."
  • Rebuild pipelines around progress; archive the 2 unused ones; add lead values
  • Combine your two administrator accounts if possible, and review who has permission to make changes
  • Clean test/duplicate contacts; build 6 Smart Lists

Week 3 — Simplify follow-ups and tracking

Goal: give each service one clear path and record where every lead came from.
  • Populate Custom Values
  • 6 Kangen funnels → 1; delete 6 template funnels, template site, 3 template forms
  • 3 intro calendars → 1; 5 HOT calendars → 2; fix grouping
  • Wire the Partner qualification gate
  • Audit the 5 never-enrolled workflows; resolve the stranded draft
  • Complete Phone 2FA; add SMS reminders; add cancel/reschedule handling
  • UTM convention; verify GA4 + Pixel + tracking script
  • Build one real dashboard; replace the FG onboarding screen
  • Set up Preference Management

Week 4 — Carefully turn on the first AI tools

Goal: use only two helpful AI features, monitor both, and require your approval before messages are sent.
  • 12 knowledge bases → 1 with 12 articles
  • Rebuild the Summary Agent with a real destination + confidence + manual-review flag
  • Rebuild the Sorter to write Primary Pillar, not tags
  • Redeploy EC Assistant in Suggestive mode, grounded, scoped, sleep-on-reply ON, one channel only
  • Delete or document Hydra
  • Stand up the weekly AI accuracy review
  • Deliver the AI governance one-pager

Explicitly out of scope for 30 days: autonomous conversation handling, lead scoring, a reporting/BI agent, Voice AI, and content generation at scale — each is listed under "AI LATER" with its unblocking condition.

Questions I need to ask you, Jen30 questions · start with the 8 marked ★

Jen, the questions marked ★ affect how I should organize your account, so please answer those first.

Business model & strategy

  • Hands On Therapy is a whole business inside this account — own domain, website, 6 workflows, 5 calendars — but no tag, no pipeline, and no place in the three-pillar model. Is HOT a fourth pillar, a legacy business, or the actual primary revenue source?
  • ★ Is there a paid offer for Nervous System Reset? The 7-day journey ends with no booking or purchase step.
  • ★ What exactly does someone buy in the Kangen pillar, and where is that transaction recorded? It is not in GHL — CA$0.00 all time.
  • What is the difference between a "Kangen customer" and a "Legacy Partner"? How should the CRM tell them apart?
  • What does a qualified Legacy Partner actually look like? I need your criteria to wire the gate.
  • Printify is connected — is there a merchandise line not in the pillar model?

Journey & offers

  • ★ What is the intended next step after the 7-Day Journey completes? Right now it just ends.
  • What is the difference between "Discovery Call", "No-Cost Initial Consultation" and "Free Q&A Call"? Which is current?
  • What is the difference between the 90- and 120-minute HOT sessions?
  • qa-zoom-registered and a draft "Q&A Campaign" exist — is there a live Q&A motion?
  • What was WF-DMAbandon-AllPillars meant to do? Created and deleted the same day (12 Aug).
  • Six Kangen funnels exist — which is the canonical entry point?

Data & definitions

  • ★ What does stat-hot / warm / cold mean operationally — who sets it, and when?
  • What should happen to a lead who selects more than one pillar? The system currently picks the first match only.
  • Should pillar interest be permanent history or current state? The 7-Day Journey deletes int-nsr on completion.
  • Are the ~10 contacts with no email and no phone worth keeping?
  • Is there revenue happening outside GHL — Enagic, in-person HOT payments, Stripe elsewhere?

Team & operations

  • ★ You appear twice as an administrator. Which account do you normally use, and may we combine them if the system allows it?
  • Who are Grace Obunyushe and Christine Joy? Both are actively building; Christine Joy is also an admin and four duplicate contact records.
  • Four of five users are ACCOUNT-ADMIN. Intentional?
  • Who is expected to work the pipeline day to day? Nothing has ever moved past a routing stage.
  • What is the intended response time on Instagram/Facebook DMs?

Rules for using AI

  • Do you know that EC Assistant is currently replying to people autonomously on Instagram, Facebook and web chat, with no knowledge base attached? I need to confirm this was intentional before changing it.
  • ★ What are you comfortable with AI saying — and never saying — about health outcomes and income potential?
  • What is GeminiBackEndAiProtocol? There is an active API key for it that has never been used.
  • What is the Hydra chatbot?
  • Would you rather AI draft and you approve, or AI act and you review afterwards? My recommendation is draft-and-approve for 90 days.

Compliance & regional

  • Business Profile lists Europe as a region of operation for a Canadian business — do you market into the EU?
  • Are there Enagic-imposed compliance rules on product or income claims? Those become hard constraints in every AI prompt.
  • elevatedconnections.ca is connected with no products attached — redirect, host, or release?