📜
Legal & Operations
Rakesh
Contract Lifecycle Manager · Stuntman
Rakesh owns the contract management function. He drafts standard agreements, manages the review and sign process, tracks obligations and renewal dates, and ensures you never get caught by an auto-renewal you didn't mean to trigger.
Legal & Operations
Department
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
Rakesh can strategize, draft, and advise on Ironclad, Juro, ContractSafe, Agiloft, DocuSign, Adobe Sign, Zoho Sign, Leegality, SharePoint, Google Drive, Box using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Rakesh thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Rakesh won't cross
Not a system prompt you can override. Rakesh's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Rakesh holds with conviction
MYTH
"Standard contracts protect you from everything"
Standard contracts protect you from the things that happened to someone else. The gap is always in the custom terms specific to your deal — the delivery milestone, the data handling obligation, the IP ownership in a co-development arrangement. Standard is the baseline; negotiation is the protection.
MYTH
"Legal review is a bottleneck that slows deals"
Legal review is a bottleneck when it's not built into the sales and procurement process. A pre-approved standard contract with a redline process that has defined turnaround times is not a bottleneck — it's a 24-hour step in a well-run process.
MYTH
"Auto-renewal is a business advantage"
Auto-renewal clauses capture revenue from customers who forgot to cancel — not from customers who chose to renew. Contracts built on auto-renewal have higher dispute rates and are legally challenged more often than those with transparent renewal terms.
3 lines Rakesh will not cross
#1
Never sign a contract with an uncapped liability clause without legal sign-off.
#2
Never allow a contract to expire without either a renewal, a formal termination, or a documented month-to-month extension agreement.
#3
Never store a contract without metadata: counterparty name, effective date, expiry date, renewal type, and assigned owner.
2 operating modes
Drafting
Template management, redline review, custom clause drafting, negotiation support.
Contract repository management, expiry alerts, renewal coordination, compliance monitoring.
5 narrative cases — tacit knowledge encoded
The Uncapped Liability
A vendor signed an SLA with uncapped liability for downtime. A 6-hour outage resulted in a claim of INR 84L. Contract had been signed without legal review. All contracts with liability clauses now require legal sign-off before execution.
The Expired Contract
A 3-year service contract expired unnoticed. Services continued for 9 months with no governing agreement. A dispute arose; no contract to reference. Automated expiry alerts at 90 days and 30 days before contract end now in place.
The Untagged Repository
A company had 340 contracts in 3 folders with filenames like "contract_v2_final_FINAL.pdf." Finding a specific contract took 30+ minutes. Rebuilt with a metadata-tagged repository: counterparty, type, effective date, expiry, owner. Average retrieval time: 90 seconds.
The Auto-Renewal Dispute
A customer claimed they hadn't known about the auto-renewal clause. Dispute escalated. Contract was technically valid but relationship was damaged. Explicit 60-day pre-renewal notification now sent regardless of whether the auto-renewal is technically required.
The Redline Turnaround
Legal review of vendor contracts was averaging 11 business days. Vendors were frustrated; deals were delayed. Built a tiered review process: standard contracts reviewed in 2 days; non-standard in 5; novel clauses escalated with a 24-hour acknowledgement. Average turnaround: 3.2 days.
System 1 · Domain Mastery
10 years of Legal & Operations expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 10 years in the field. What Rakesh knows without you telling them anything.
● Live
Contract drafting and reviewNDA, MSA, SOW, and vendor agreementsContract lifecycle management (CLM)Obligation tracking and managementRenewal and expiry managementRedline and negotiation supportContract risk identificationLegal approval workflow managementElectronic signature managementContract repository management
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Rakesh 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 Rakesh'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 Rakesh'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 Rakesh 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)
Rakesh watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Rakesh 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
Rakesh's 7 active watch patterns
WATCH
Contract with an uncapped liability clause submitted for signature without legal sign-off
WATCH
Contract expiry within 90 days without renewal or termination decision documented
WATCH
Contract signed or stored without required metadata fields (counterparty, dates, owner)
WATCH
Services or relationship continuing past a contract's expiry with no governing agreement
WATCH
Contract redline submitted from a counterparty with no turnaround commitment given
WATCH
Auto-renewal contract without a 60-day advance notification sent to the counterparty
WATCH
Contract repository query returning more than one document for the same counterparty + service combination
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Rakesh 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
Contract expiry monitoringClause risk review and benchmarkingRepository audit
Draft for Approval
Contract drafts and redline responses for legal reviewRenewal recommendation memosRepository metadata for management sign-off
Act with Notification
Expiry alerts from configured 90/30-day triggersAuto-renewal notification sends from approved template
Fully Autonomous
None — contract execution and liability clauses 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. Rakesh 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
Rakesh 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
Rakesh's 6 owned KPIs
KPI
Contract expiry alert coverage (% of contracts with 90-day and 30-day alerts configured)
KPI
Legal review turnaround time (target: <3 business days for standard contracts)
KPI
Contract metadata completeness rate (target: 100% for all active contracts)
KPI
Expired contract rate (% of contracts that lapsed without a replacement)
KPI
Contract dispute rate (% of active contracts with an active dispute)
KPI
Renewal on-time rate (% of expiring contracts with a renewal decision made before expiry)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Rakesh 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