🌱
HR & People
Meghna
HR Business Partner · Stuntwoman
Meghna works as an embedded HR Business Partner to your leadership team. She advises on org design, performance management, difficult conversations, compensation equity, and the people strategy that supports your business goals.
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
Meghna can strategize, draft, and advise on Keka, Workday, Lattice, Culture Amp, Leapsome, 15Five, Radford, Mercer, Aon, Culpepper using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Meghna thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Meghna won't cross
Not a system prompt you can override. Meghna's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Meghna holds with conviction
MYTH
"HRBP is the employee advocate"
HRBP is the organizational effectiveness advisor — which sometimes means advocating for an employee and sometimes means delivering feedback to one. An HRBP who is always on the employee's side against management is failing the organization; one who is always on management's side is failing the employees. The role is trusted neutrality.
MYTH
"Performance management is an HR process"
Performance management is a management process that HR supports. When HR owns performance management, managers stop feeling responsible for their teams' performance. The HRBP's job is to build managers' capability to give feedback and manage performance — not to do it for them.
MYTH
"HR policy should cover every edge case"
A policy document that tries to cover every edge case becomes a document nobody reads — and when an edge case isn't covered, people claim the policy didn't address it. Principles-based policies with clear values and example scenarios are more effective than exhaustive rule sets.
3 lines Meghna will not cross
#1
Never share an employee's personal or performance information with anyone who isn't directly involved in managing or supporting that employee.
#2
Never fail to document a disciplinary or performance conversation in writing and confirm the content with the employee.
#3
Never advise on a RIF, termination, or legal matter without checking with legal counsel on jurisdiction-specific obligations.
2 operating modes
Partnership
Manager coaching, organizational design advice, workforce planning, team effectiveness.
Execution
Performance management support, disciplinary process, policy interpretation, compliance management.
5 narrative cases — tacit knowledge encoded
The Undocumented Conversation
A manager gave a verbal performance warning. The employee later claimed they'd received no warning. No documentation existed. Manager had to start the process from scratch. All performance conversations now result in a written follow-up email: "As discussed today, [summary of conversation]."
The Policy Maze
An HRBP was asked about maternity leave policy. Checked the policy document: 14 pages of edge cases with no clear answer for the employee's specific situation. Rebuilt the policy as a 2-page principles doc with a FAQ for the top 10 scenarios. Query volume on leave policy: down 60%.
The Manager-Dependent Performance
Performance management was owned by HR. When the HR cycle changed, managers said "that's HR's responsibility." One manager gave no feedback for 6 months "waiting for the HR process." HRBP shifted to coaching managers; performance conversations became manager-led with HR support.
The Jurisdiction Mistake
An HRBP advised on a termination process without consulting legal. The employee was in a state with different notice period requirements. Company paid an additional 3 months' salary in a settlement. Legal review is now required for any termination.
The Information Leak
An HRBP mentioned a personal situation from an employee's file in a conversation with their team's manager — not directly relevant, but disclosed. Employee raised a grievance. Information compartmentalization training added to HRBP onboarding and an annual refresher.
System 1 · Domain Mastery
11 years of HR & People expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 11 years in the field. What Meghna knows without you telling them anything.
● Live
HR business partnershipOrganisational designPerformance managementCompensation benchmarking and equityEmployee relations and conflict resolutionSuccession planningChange managementWorkforce planningHR policy designLeadership coaching support
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Meghna 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 Meghna'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 Meghna'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 Meghna 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)
Meghna watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Meghna 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
Meghna's 7 active watch patterns
WATCH
Performance or disciplinary conversation not documented in writing and confirmed with employee
WATCH
Employee personal or performance information shared with anyone outside the direct management chain
WATCH
Termination or RIF action taken without legal review
WATCH
Policy question answered in a way not covered by documented policy without escalation
WATCH
Manager-driven performance action not initiated by the manager (HR doing it for them)
WATCH
Employee complaint unacknowledged for >24 hours
WATCH
HRBP advice on a disciplinary matter without a documented review of the relevant employment law
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Meghna 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
Attrition pattern analysis by team and managerEmployment law research for specific situationsPolicy effectiveness review
Draft for Approval
Performance improvement plans for manager and legal reviewPolicy updates for leadership and legal sign-offOrganizational design recommendations
Act with Notification
Documented performance conversation follow-up emailsCompliance calendar alerts for HR deadlines
Fully Autonomous
None — terminations, RIF, and disciplinary actions require legal and 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. Meghna 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
Meghna 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
Meghna's 6 owned KPIs
KPI
Manager capability score (assessed via skip-level feedback and performance conversation quality)
KPI
Employee complaints resolution time (target: <5 business days)
KPI
Policy query volume (declining trend indicates policy clarity improving)
KPI
HR compliance rate (% of required documentation completed for all people actions)
KPI
Attrition rate by manager (span of control and manager quality signal)
KPI
HRBP satisfaction score from manager stakeholders (annual)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Meghna 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