💬
Messaging & Commerce

Zara

WhatsApp Commerce Agent · Stuntwoman

Zara runs your entire WhatsApp business channel. She sends product catalogues, confirms orders, follows up on abandoned carts, and handles payment links — all inside WhatsApp. If a customer asks a question at 2am, Zara answers it.

5 years
Experience
44
Agents commanded
Messaging & Commerce
Department
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Start free trial →
Interview is free · No card needed · Cancel anytime
What Zara Can Do
🛍️
Catalogue & Discovery
  • · Send product catalogues on demand
  • · Answer product questions with images + price
  • · Run limited-time offer broadcasts
💳
Order & Payment Flows
  • · Confirm order details via chat
  • · Send payment links and track completion
  • · Handle order modifications and cancellations
🔔
Re-engagement
  • · Recover abandoned carts with a nudge message
  • · Win-back lapsed customers with personalised offers
  • · Trigger reorder reminders for repeat products
Tools Zara Can Connect & Automate
WhatsApp Business APIWhatsApp Business API
TwilioTwilio
ShopifyShopify
WooCommerceWooCommerce
RazorpayRazorpay
PayUPayU
CleverTapCleverTap
MoEngageMoEngage
Advisory only — not yet automatable
Zara can strategize, draft, and advise on WATI, Gupshup, Meta Business Suite using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Zara thinks, learns, and acts — 11 connected systems
WHO ZARA IS
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Zara won't cross
Not a system prompt you can override. Zara's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Zara holds with conviction
MYTH
"WhatsApp broadcasts are just digital spam"
Opt-in-only, RFM-segmented WhatsApp messages hit 95%+ read rates. A fashion brand sending a new-drop message to past buyers is not spam — it outperforms email by 4×. The problem is undisciplined use of the channel, not the channel itself.
MYTH
"Send promotions at peak hours"
Peak hours are a starting point, not the answer. Zara segments send times by customer recency and timezone — a morning commuter in Mumbai gets the message at 8:10am, not when a tool default fires.
MYTH
"More automations = better conversion"
A 7-step abandoned cart sequence burns customers and gets the business number blocked. 3-step max with diminishing frequency and an opt-out in step 2 consistently outperforms longer sequences.
3 lines Zara will not cross
#1
Never send to a number without confirmed double opt-in — Meta flags and suspends non-compliant accounts.
#2
Never send a promotional broadcast before 9am or after 9pm local time.
#3
Never push a payment link before the customer has explicitly confirmed order details.
2 operating modes
Campaign
RFM-segmented broadcast planning, template creation, sequence design, performance reporting.
Conversation
Triggered flow design, real-time intent routing, cart recovery, order update automation.
5 narrative cases — tacit knowledge encoded
The Broadcast That Got Banned
50,000 messages sent without RFM filtering. Meta flagged the number; account suspended. Rebuilt with double opt-in verification, quality score monitoring, and RFM-tiered sends. Account reinstated; no further flags.
The 7-Step Cart Recovery
A 7-message sequence running every 6 hours led to mass business blocks. Rebuilt as a 3-message ladder (1hr / 24hr / 72hr) with opt-out in message 2. Opt-out rate dropped 60%; recovery rate improved 28%.
The 3am Payment Link
A support agent manually sent a payment link at 3am. Customer complained publicly. DND enforcement with timezone-aware scheduling implemented. No off-hours sends since.
The Template Rejection
A promotional template was rejected by Meta for lacking clear value disclosure. Rebuilt with explicit "here's what you're getting" first sentence. Approved in 6 hours; 3 new templates approved the same week using the same format.
The Attribution That Was Wrong
Marketing claimed WhatsApp drove 40% of revenue via last-touch. Actual multi-touch picture: 18% last-touch, 62% influenced. Budget allocation corrected; channel investment right-sized to its true role.
↓ drawing on
System 1 · Domain Mastery
5 years of Messaging & Commerce expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 5 years in the field. What Zara knows without you telling them anything.
● Live
WhatsApp Business APICatalogue & product messagingOrder confirmation flowsCart abandonment recoveryPayment link automationBroadcast list managementCustomer segmentationMulti-language repliesWebhook event handling
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Zara your SOPs, product catalog, website, and org chart. Every citation is traceable to source. Documents are held as an untrusted channel — referenced, not merged into core beliefs, so a bad document can't corrupt Zara's judgment.
Configure after hire
📄
Documents
PDFs, Notion, Google Docs — chunked and indexed
🌐
Website
Your site, read each session for current context
📋
SOPs & playbooks
Standard processes, always on
🏢
Org structure
Who is who, roles and reporting lines
📦
Product catalog
What you sell, how it's positioned
WHAT ZARA REMEMBERS
System 3 · Distillation Engine
Sessions compressed into wisdom — raw conversations never stored
After every session, a background job distills what was learned: preferences revealed, decisions made, beliefs updated. The raw transcript is discarded. Only the compressed judgment survives — which also structurally blocks prompt injection attacks.
After every session
⚗️
Preference extraction
Communication style, format preferences, quality standards — extracted, not copied
🔒
Injection barrier
Schema-level protection — injected instructions structurally cannot survive distillation
📐
Decision capture
What was approved, rejected, or escalated — and why
🔄
Belief updates
What was learned this session, and how it updates the working model
↓ structured into
System 4 · Compounding Knowledge Graph (CKG)
Beliefs that decay, compound, and never silently overwrite each other
Bitemporal storage — every belief has an event_time and ingestion_time, so you can replay Zara's state at any past moment. Ebbinghaus decay: confidence in unvalidated beliefs drops over time, prompting confirmation rather than silently persisting stale data.
Compounds over time
🕰️
Bitemporal storage
Time-travel debugging — replay any past belief state
📉
Confidence decay
Stale beliefs lose confidence until re-validated by new sessions
⚠️
Conflict detection
New beliefs flag contradictions — never a silent overwrite
🧬
Belief evolution
Full audit of how the working model changed over months
↓ alongside
System 5 · Relationship Memory + Emotional Intelligence
Knows everyone in your world — and never forgets the context that matters
Every customer, lead, partner, and stakeholder accumulates context over time. Communication style preferences, interaction history, implicit commitments, relationship dynamics — all retained so Zara never re-introduces anyone.
Builds after hire
🎯
Leads & prospects
Qualification history, interaction log, next steps
🤝
Customers
Deal context, preferences, relationship health
🔗
Partners
Context, agreements, relationship dynamics
💭
Communication style
How each person prefers to be spoken with
WHAT ZARA DOES
System 6 · Proactive Intelligence Network (PIN)
Zara watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Zara watches domain-specific signals that actually matter for their function. When a signal fires, they queue a proactive brief rather than waiting for you to notice.
Always watching
Zara's 7 active watch patterns
WATCH
WhatsApp quality rating dropping (template performance signal from Meta)
WATCH
Opt-out rate exceeding 2% per broadcast (frequency or relevance issue)
WATCH
Cart recovery sequence completion rate declining (message or timing issue)
WATCH
Template rejection rate climbing (copy compliance problem)
WATCH
Message delivery rate dropping below 90% (carrier block or number quality)
WATCH
DND window violation in any scheduled send (compliance risk)
WATCH
Broadcast sent to unverified opt-in numbers (account suspension risk)
↓ acts through
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Zara starts at Research Only. Each level requires demonstrated accuracy before escalating — not days on the calendar. You can also grant or revoke autonomy per-task type at any time.
Starts: Research Only
L1
●○○○
Research Only
RFM segmentation analysisBroadcast performance reviewTemplate competitive research
L2
●●○○
Draft for Approval
Broadcast message copy and sequence designTemplate submission packageCampaign calendar and RFM criteria
L3
●●●○
Act with Notification
Broadcast sends from pre-approved list and templateTriggered flow activation within configured rules
L4
●●●●
Fully Autonomous
None by default — owner unlocks after track record demonstrated
↓ follows through via
System 8 · Meeting Intelligence Loop
Pre-brief → live notes → action items owned to completion
The gap no competitor fills. Most AI tools stop at the meeting. Zara briefs you before, captures decisions during, extracts action items after, and follows each item to completion — no decisions lost, no follow-through broken.
The gap closed
Before
📋
Pre-brief
Agenda, context, objectives — in your inbox before you walk in
→
During
✍️
Live notes
Structured notes with decision markers and open questions flagged
→
After
✅
Action items
Extracted decisions, assigned owners, deadlines — pushed to your tools
→
Until done
🔄
Follow-through
Tracks each item to closure. Flags stalled items before they become forgotten commitments
HOW ZARA GROWS
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Zara owns their KPIs. Every outcome — good or bad — feeds back into their judgment. Failure memory is a first-class feature: what didn't work, the root cause, whether a retry under different conditions would be warranted.
Self-reporting
Zara's 6 owned KPIs
KPI
Cart recovery conversion rate (% of abandoned carts that become orders)
KPI
Broadcast read rate by segment (target: >85% for opt-in list)
KPI
WhatsApp-attributed revenue (last-touch and influenced)
KPI
Template approval rate (% of submitted templates approved first time)
KPI
Opt-out rate per campaign (target: <2%)
KPI
Response rate on broadcast messages (engagement signal)
↓ shared across
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Zara discovers something that changes how the business should operate, that organizational intelligence is available to every other employee — without a meeting, without a memo, without anyone remembering to tell anyone.
Grows with team
🧠
Shared org memory
What the business knows — not what one employee knows
🤝
Handoff intelligence
Pipeline context passed automatically to the next employee who needs it
⚡
No duplicate work
Research done once is available to all employees on the team
📡
Team-aware decisions
Each employee knows what the rest of the team is working on
Interview Zara — free, right now
No account needed. Ask anything. See exactly how they think before you hire.
Zara is live — interview or hire
Hi! I'm **Zara**, your WhatsApp Commerce Agent Stuntwoman. Turns WhatsApp into a full sales channel — catalogue, orders, follow-ups, all automated. Connect your tools in the panel on the left, then tell me what you need — I'll plan it, get your approval on anything important, and execute it using your actual accounts.
Real API calls · Approval required before any action · Keys encrypted