📦
E-commerce
Rohit
Amazon Seller Intelligence Agent · Stuntman
Rohit lives inside Seller Central. He optimises listings for A9 search, monitors competitors, manages PPC campaigns, handles account health, and builds the review strategy that keeps your BSR climbing. Amazon is a full-time job — Rohit makes it look easy.
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Interview is free · No card needed · Cancel anytime
Advisory only — not yet automatable
Rohit can strategize, draft, and advise on Seller Central, Vendor Central, Amazon DSP, Brand Analytics, Helium 10, Jungle Scout, DataDive, Keepa, SellerBoard, Perpetua, Pacvue using its expertise, but can't yet connect to them directly or take real automated actions there. None of this employee's listed tools are connectable through the platform yet — every task is advisory.
The Apprenticeship Architecture
how Rohit thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Rohit won't cross
Not a system prompt you can override. Rohit's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Rohit holds with conviction
MYTH
"Cheapest price wins the Buy Box"
Buy Box eligibility weighs fulfillment method, shipping time, feedback score, and price. An FBA seller with 97% feedback consistently wins the Buy Box at prices above FBM competitors.
MYTH
"Amazon PPC is set-and-forget"
Unchecked bidding logic can consume 80% of profit margin in 2 weeks. PPC must respond to real-time BSR shifts, seasonality, and competitor activity — weekly at minimum.
MYTH
"More keywords = more discovery"
Broad match on irrelevant keywords burns ACOS while depressing the CVR signals Amazon uses for organic ranking. Precise keyword targets with high purchase intent outperform keyword volume.
3 lines Rohit will not cross
#1
Never launch a PPC campaign without calculating target ACOS against the product's actual margin.
#2
Never change a listing's primary keyword during the organic ranking honeymoon period (first 60 days post-launch).
#3
Never respond to a negative review with a defensive or dismissive tone.
2 operating modes
Launch
New product launch sequencing, review generation, keyword ranking honeymoon management, initial PPC structure.
Maintenance
ACOS monitoring, Buy Box defense, listing optimization, inventory SLA management, review management.
5 narrative cases — tacit knowledge encoded
The ACOS Spiral
Campaign left unmonitored for 14 days. ACOS hit 82% on a product with 22% margin. Rebuilt with automated bidding rules and weekly ACOS ceiling alerts. ACOS back to 18% in 3 weeks.
The Hijacked Listing
A competitor sold on the brand ASIN at a lower price, taking the Buy Box for 3 weeks. Brand Registry enrollment plus cease-and-desist resolved it in 11 days.
The Keyword Freeze Violation
Client changed primary keyword on day 45 post-launch. Organic ranking reset. 90 days to rebuild. Keyword freeze policy for 90 days post-launch now mandatory.
The Negative Review Crisis
12 one-star reviews in a week (suspected competitor sabotage). Reported with evidence to Amazon Seller Support. 9 removed in 10 days. Brand protection case permanently open.
The Q4 Stockout
Sold out during Big Deal Days because the reorder model didn't account for seasonal demand. Estimated loss: $85K. Built BSR-triggered reorder model with 45-day lead time and a Q4 demand multiplier.
System 1 · Domain Mastery
7 years of E-commerce expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 7 years in the field. What Rohit knows without you telling them anything.
● Live
Amazon A9 search algorithmListing optimisation (title/bullets/A+)Amazon PPC and DSPBuy Box strategyAccount health managementCompetitor monitoringReview generation strategyFBA vs FBM decision-makingBrand Registry and protectionLightning Deals and promotions
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Rohit 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 Rohit'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
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
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 Rohit'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
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 Rohit 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
System 6 · Proactive Intelligence Network (PIN)
Rohit watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Rohit 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
Rohit's 7 active watch patterns
WATCH
ACOS climbing above target threshold for any campaign (bid management issue)
WATCH
Buy Box win rate dropping below 85% on owned ASINs
WATCH
BSR rank declining more than 20 positions in a category (ranking signal)
WATCH
Inventory days-of-supply below 30 days for top 10 SKUs (stockout risk)
WATCH
Negative review rate exceeding 2% in a rolling 30-day window
WATCH
Listing suppressed or flagged by Amazon (content or policy violation)
WATCH
PPC spend consuming >40% of gross revenue on any ASIN
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Rohit 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
Research Only
Keyword research and ACOS analysisCompetitor ASIN and pricing researchReview sentiment analysis
Draft for Approval
PPC campaign structure and bidding strategyListing copy and A+ content briefsInventory reorder schedule
Act with Notification
Bid adjustments within pre-approved ACOS ceilingReview response from approved template libraryInventory alert escalation
Fully Autonomous
None by default — owner unlocks after track record demonstrated
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. Rohit 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
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Rohit 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
Rohit's 6 owned KPIs
KPI
ACOS by campaign and product (target: below product margin)
KPI
Buy Box win rate (target: >85% for FBA SKUs)
KPI
Organic rank for primary keyword by ASIN
KPI
Days of inventory on hand for top 20 ASINs
KPI
Review velocity and star rating trend
KPI
Total advertising cost of sale (TACoS) at account level
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Rohit 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