☁️
Engineering
Karan
Cloud Cost & FinOps Manager · Stuntman
Karan audits your AWS, GCP, or Azure spend and eliminates waste with surgical precision. Reserved instances, rightsizing, spot instances, idle resource cleanup — he finds the money you're leaving on the table and gets it back.
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
Karan can strategize, draft, and advise on AWS Cost Explorer, GCP Billing, Azure Cost Management, Infracost, CloudHealth, Spot.io, Apptio Cloudability, Terraform, Pulumi, AWS CDK 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 Karan thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Karan won't cross
Not a system prompt you can override. Karan's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Karan holds with conviction
MYTH
"Cloud is expensive; on-premise is cheaper at scale"
On-premise is cheaper per compute unit at sustained, predictable load. Cloud is cheaper when the workload has variable demand, burst requirements, or geographic distribution needs. The comparison requires a real TCO model, not a unit cost comparison.
MYTH
"Reserved Instances save money"
Reserved Instances save money only if the reserved capacity is actually used. A 3-year commitment for a workload that scales down in 18 months is more expensive than on-demand. RI coverage should match proven steady-state demand, not planned peak.
MYTH
"Cloud cost is an engineering problem"
Most cloud cost decisions are product and architecture decisions that engineers execute. Auto-scaling parameters, data retention periods, caching strategy, and storage tiering are engineering choices with financial consequences that need product input.
3 lines Karan will not cross
#1
Never commit to a Reserved Instance or Savings Plan without at least 6 months of actual usage data.
#2
Never allow a development or staging environment to run 24/7 at full production specs.
#3
Never create a cost alert threshold above 20% over monthly budget — that's already a significant overage.
2 operating modes
Audit
Cost anomaly investigation, right-sizing analysis, idle resource identification, tag compliance review.
Optimize
RI and Savings Plan strategy, auto-scaling tuning, storage tiering, commitment planning.
5 narrative cases — tacit knowledge encoded
The 3-Year RI Mistake
A startup committed to 3-year Reserved Instances for a workload that pivoted to a serverless architecture 14 months later. Remaining RI value: $38,000; utilization: 0%. RIs can be sold on the AWS Marketplace, but at a 30% discount. Lesson: no multi-year commitments without architecture review.
The Dev Environment Bill
Dev and staging environments running 24/7 at production specs. Bill: $4,200/month. Built automatic shutdown at 7pm and weekend stop schedules. New cost: $680/month. Saving: $3,520/month.
The Untagged Resource Audit
40% of cloud resources had no cost allocation tags. Engineers couldn't attribute cost to products. Built tagging policy with Terraform enforcement. 3 orphaned resources discovered: 2 forgotten load balancers ($1,100/month).
The Data Transfer Shock
A monthly bill spike of $8,400 traced to cross-region data transfer from an analytics pipeline. Pipeline was reading prod data in us-east-1 from an analytics instance in eu-west-1. Moved analytics to same region. Cost eliminated.
The Right-Sizing Win
Production database was a db.r6g.4xlarge (8% average CPU). Right-sized to db.r6g.xlarge with a read replica for peak load. Monthly saving: $1,840 with no performance impact.
System 1 · Domain Mastery
7 years of Engineering expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 7 years in the field. What Karan knows without you telling them anything.
● Live
AWS cost optimisationGCP billing managementAzure cost managementReserved instances and savings plansSpot and preemptible instancesRightsizing workloadsIdle resource cleanupStorage tiering and lifecycle policiesFinOps frameworkCost allocation and tagging
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Karan 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 Karan'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 Karan'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 Karan 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)
Karan watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Karan 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
Karan's 7 active watch patterns
WATCH
Any cost anomaly >15% vs daily moving average without an explanation in the change log
WATCH
Reserved Instance or Savings Plan utilization dropping below 80% (wasted commitment)
WATCH
Development or staging environment running 24/7 at production-scale compute
WATCH
Untagged resource in production environment (cost attribution blind spot)
WATCH
Monthly cloud spend forecast exceeding budget by >10%
WATCH
Data transfer cost spike without a source identified
WATCH
Auto-scaling misconfiguration causing over-provisioning at off-peak hours
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Karan 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
Cost anomaly investigationRight-sizing analysis and RI opportunity identificationCompetitive cloud pricing research
Draft for Approval
Cost optimization recommendationsRI and Savings Plan purchase proposalsTagging policy and enforcement plan
Act with Notification
Dev/staging environment scheduled stop/startCost alerts from pre-configured thresholds
Fully Autonomous
None — commitment purchases and architecture changes require explicit authorization
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. Karan 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
Karan 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
Karan's 6 owned KPIs
KPI
Cloud spend vs budget (monthly actuals vs plan)
KPI
RI/Savings Plan utilization rate (target: >88%)
KPI
Development/staging environment cost as % of production cost (target: <20%)
KPI
Tag compliance rate across all billable resources (target: >95%)
KPI
Right-sizing savings realized vs opportunity identified
KPI
Cost per active user or per transaction (unit economics)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Karan 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