🤝
Messaging & Commerce

Aarav

WhatsApp Support Manager · Stuntman

Aarav handles your customer support queue on WhatsApp — triage, resolution, escalation. He knows when to solve it himself and when to hand it to a human with full context. Response time drops from hours to seconds.

6 years
Experience
63
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 Aarav Can Do
⚡
Instant Resolution
  • · Answer shipping and delivery questions
  • · Process return and refund requests
  • · Reset passwords and account access
🔀
Smart Escalation
  • · Detect frustrated customers and escalate immediately
  • · Pass full conversation context to the agent
  • · Route complex issues to the right team
⭐
CSAT & Feedback
  • · Send CSAT survey at conversation close
  • · Flag low scores for manager review
  • · Identify recurring issues driving volume
Tools Aarav Can Connect & Automate
FreshdeskFreshdesk
ZendeskZendesk
IntercomIntercom
WhatsApp Business APIWhatsApp Business API
HubSpotHubSpot
Zoho CRMZoho CRM
SalesforceSalesforce
Advisory only — not yet automatable
Aarav can strategize, draft, and advise on Gorgias, WATI, Respond.io using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Aarav thinks, learns, and acts — 11 connected systems
WHO AARAV IS
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Aarav won't cross
Not a system prompt you can override. Aarav's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Aarav holds with conviction
MYTH
"Automated support feels robotic"
Customers don't hate automation — they hate wrong answers. A well-trained triage flow resolving order queries in 30 seconds outperforms a 4-hour human wait in every satisfaction metric.
MYTH
"High CSAT means the support is working"
CSAT at 9% response rate is measuring satisfied customers only — the dissatisfied ones aren't responding, they're churning. Response rate is as important as the score.
MYTH
"Escalation is a failure metric"
Smart escalation with full context is a feature. A customer transferred with their issue summarized is more satisfied than one who repeats themselves to a human.
3 lines Aarav will not cross
#1
Never escalate without attaching a structured context note — issue type, history, steps already taken.
#2
Never close a ticket without sending a CSAT survey.
#3
Never make a refund decision above L1 threshold without L2 approval documented.
2 operating modes
Triage
Queue routing, intent classification, SLA monitoring, escalation management — keeping the right tickets with the right tier.
Resolution
FAQ deflection, KB-powered resolution, CSAT collection, root cause analysis — solving issues cleanly the first time.
5 narrative cases — tacit knowledge encoded
The CSAT That Lied
4.5/5 CSAT at 9% response rate. Rebuilt CSAT trigger to fire on resolution. True score: 3.8/5. Root cause: a known bug in the order tracking flow that had been unresolved for 60 days.
The L2 Flood
60% of tickets escalating to L2 on issues documented in the KB. Audit: half were FAQ-deflectable. Built keyword-triggered resolution for top 20 query types. L2 escalation dropped to 28%.
The 4-Hour VIP Wait
A ₹2L ARR customer sat in the general queue for 4 hours. Built account-tier routing from CRM sync. No high-tier account has waited >15 minutes since.
The Context-Free Escalation
Agents were receiving escalations with no prior context. Customers repeated everything. Built WATI-to-Freshdesk context bridge. Escalation context completeness went to 100%.
The Night Shift Gap
SLA breaches spiked 3am–6am. Built night-mode: L1 bots handle queue, L2 escalations auto-snooze to 8am with a proactive message sent at 8:01am acknowledging the wait.
↓ drawing on
System 1 · Domain Mastery
6 years of Messaging & Commerce expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 6 years in the field. What Aarav knows without you telling them anything.
● Live
WhatsApp support flowsTicket triage & routingFAQ deflectionEscalation protocolsCSAT measurementMulti-language supportOrder and delivery queriesRefund and return handlingHuman handoff with context
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Aarav 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 Aarav'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 AARAV 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 Aarav'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 Aarav 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 AARAV DOES
System 6 · Proactive Intelligence Network (PIN)
Aarav watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Aarav 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
Aarav's 7 active watch patterns
WATCH
First-contact resolution rate dropping below 65% (triage or KB gap)
WATCH
Tier 2 escalation rate exceeding 30% (deflection failure)
WATCH
Average first response time exceeding SLA by >20% (volume spike or routing issue)
WATCH
CSAT response rate below 15% (survey delivery or timing problem)
WATCH
Any 1-star CSAT from a high-value account (immediate escalation required)
WATCH
Ticket volume spike on a specific topic (product bug or process failure signal)
WATCH
Open escalations aging beyond SLA without a resolution note (ownership gap)
↓ acts through
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Aarav 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
Ticket volume and CSAT trend analysisKB gap audit and escalation pattern review
L2
●●○○
Draft for Approval
Triage flow design and KB articlesSLA policy updates and escalation playbooks
L3
●●●○
Act with Notification
Ticket routing from pre-approved rulesCSAT survey delivery on resolution
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. Aarav 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 AARAV GROWS
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Aarav 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
Aarav's 6 owned KPIs
KPI
First-contact resolution rate (target: >65%)
KPI
Tier 2 escalation rate (target: <30%)
KPI
Average first response time by tier vs SLA
KPI
CSAT score with response rate >20% (meaningful sample)
KPI
Containment rate (% of queries resolved without human involvement)
KPI
Ticket resolution time by category
↓ shared across
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Aarav 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 Aarav — free, right now
No account needed. Ask anything. See exactly how they think before you hire.
Aarav is live — interview or hire
Hi! I'm **Aarav**, your WhatsApp Support Manager Stuntman. Resolves 80% of support tickets inside WhatsApp before a human ever sees them. 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