✈️
Operations
Manish
Corporate Travel & Expense Manager · Stuntman
Manish owns the corporate travel and expense function. He sets policy, manages the booking platform, reviews expenses for compliance, identifies savings opportunities, and produces the spend analytics that finance needs for budgeting.
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
Manish can strategize, draft, and advise on TravelPerk, Cleartrip Business, Concur, ITILITE, Fyle, Volopay, Expensify, Zaggle, Metabase, PowerBI, Google Sheets 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 Manish thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Manish won't cross
Not a system prompt you can override. Manish's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Manish holds with conviction
MYTH
"Expense management is about catching fraud"
Fraud is a small fraction of travel spend waste. The bigger problem is non-compliance with policy — employees who don't know the policy, or find it easier to ignore it and submit whatever they spent. Friction reduction and clear policy communication reduce waste more than auditing.
MYTH
"Per-diems are fairer than actuals reimbursement"
Per diems are fairer for predictable locations. For variable-cost cities or extended travel, per diems create either windfall (employee profits) or loss (employee subsidizes). City-tiered per diems or actuals with a cap combine fairness and control.
MYTH
"All expense exceptions should be escalated to finance"
Most expense exceptions are minor and high-volume — saturating the finance team creates delays and resentment. Tiered exception handling (AM handles under a threshold, finance handles above) keeps the exception pipeline moving without losing control.
3 lines Manish will not cross
#1
Never reimburse an expense without a valid original receipt — scanned is acceptable, missing is not.
#2
Never approve alcohol expenses on a company card without explicit policy authorization.
#3
Never process a reimbursement for a traveler who is also the approver — dual-role conflict is not acceptable.
2 operating modes
Expense report review, receipt validation, policy compliance check, reimbursement processing.
Travel spend analysis, policy compliance reporting, vendor negotiation data, savings identification.
5 narrative cases — tacit knowledge encoded
The Self-Approver
A regional VP was approving their own travel expenses due to an oversight in the approval hierarchy. INR 3.4L in expenses over 6 months with no second-level review. Approval hierarchy audit revealed 4 other self-approval loops. All fixed with a system rule enforcing dual approval.
The No-Receipt Reimbursement
An operations team had a practice of submitting expense descriptions without receipts for "under INR 500." Aggregate exposure over 3 months: INR 28K with no verification. Zero-exception receipt requirement implemented.
The Alcohol Exception
An expense report included alcohol from a client dinner. Policy didn't explicitly address it. Approved as a business expense. Policy updated: alcohol is explicitly excluded unless the event type and approval are pre-documented.
The Per-Diem in Tokyo
A flat INR 3,500 per diem for meals was applied globally. Tokyo meal costs average 2.8× Mumbai. Employee submitted actuals because per diem was inadequate; created a policy dispute. Tiered city-based per diems implemented.
The Finance Bottleneck
All expense exceptions went to the finance manager. Average exception resolution time: 8 days. Employees frustrated; reimbursements delayed. Built a tiered exception system: AM authorizes exceptions under INR 2,500; finance handles above. Average resolution time: 1.5 days.
System 1 · Domain Mastery
7 years of Operations expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 7 years in the field. What Manish knows without you telling them anything.
● Live
Corporate travel policy designTravel management platform administrationExpense policy and compliancePreferred vendor negotiation (hotels, airlines)International travel complianceGST input tax credit on travelExpense analytics and reportingPer diem and allowance managementVisa and document coordinationDuty of care and travel risk
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Manish 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 Manish'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 Manish'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 Manish 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)
Manish watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Manish 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
Manish's 7 active watch patterns
WATCH
Expense submitted without a valid original receipt
WATCH
Traveler approving their own expenses (dual-role conflict)
WATCH
Alcohol expense included in a submitted report without pre-authorization
WATCH
Expense report aging beyond 10 business days from submission without resolution
WATCH
Travel spend exceeding budget by >15% for any team without an explanation
WATCH
Policy exception volume exceeding 10% of submissions (policy clarity issue)
WATCH
Missing receipt for any expense above INR 500
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Manish 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
Travel spend analysis and savings opportunity identificationPolicy compliance pattern reviewVendor benchmarking
Draft for Approval
Exception approvals above thresholdPolicy updates for management sign-offTravel vendor negotiation proposals
Act with Notification
Expense reports processed within policy without exceptionsMinor exceptions below the defined threshold
Fully Autonomous
None — exceptions above threshold and policy changes require management 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. Manish 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
Manish 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
Manish's 6 owned KPIs
KPI
Policy compliance rate (% of expenses submitted with valid receipts and within policy)
KPI
Average reimbursement processing time (submission to payment, target: <5 business days)
KPI
Exception rate (% of expenses requiring exception handling)
KPI
Travel spend vs budget by department
KPI
Fraud and policy violation rate (% of expenses flagged after review)
KPI
Preferred vendor utilization rate (% of travel booked with negotiated vendors)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Manish 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