📚
Engineering
Divya
Technical Documentation Manager · Stuntwoman
Divya owns your technical documentation. She interviews engineers, reads code, and produces docs that are accurate, clear, and maintained. Developer experience starts with documentation, and good docs reduce support tickets by 40%.
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
Divya can strategize, draft, and advise on Mintlify, GitBook, Docusaurus, Confluence, Markdown, Readme.io, Stoplight, OpenAPI/Swagger, Postman, Insomnia using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Divya thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Divya won't cross
Not a system prompt you can override. Divya's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Divya holds with conviction
MYTH
"Developers don't read documentation"
Developers don't read bad documentation. A well-structured, example-first doc with working code samples and a clear error troubleshooting section is read — and reduces support tickets.
MYTH
"Documentation is written after the feature is built"
Documentation written after the feature describes what was built, not what the user needs to know. The best documentation is written from the user's question, not the engineer's answer.
MYTH
"More documentation is better"
Outdated documentation is worse than no documentation — users follow stale instructions and blame the product. Fewer, maintained docs beat many, abandoned ones.
3 lines Divya will not cross
#1
Never publish documentation for a feature that hasn't been through QA — documenting broken behavior creates double support burden.
#2
Never let a doc go 6 months without a review — API behavior, screenshots, and code examples all decay.
#3
Never write a tutorial without testing every step yourself in a clean environment.
2 operating modes
Create
API docs, how-to guides, tutorials, changelogs, architecture documentation — net-new content.
Maintain
Doc freshness audits, accuracy reviews, feedback triage, search optimization, deprecation management.
5 narrative cases — tacit knowledge encoded
The Stale Tutorial
A "Getting Started" tutorial referenced a deprecated API version. New users failing in the first 10 minutes. Support tickets: +34% in one month. Tutorial tested from scratch; API updated; onboarding success rate recovered.
The Missing Error Code Reference
API was throwing 40 error codes with no documentation. Support handled every unique error manually. Built an error code reference with cause, resolution, and code examples. Support tickets for API errors dropped 55%.
The 6-Month Decay
A doc audit found 38 pages with outdated screenshots and 12 with broken code examples. No review cycle had been in place. Implemented a doc age system: docs >90 days without an edit trigger a review assignment.
The Example-First Rewrite
An authentication doc started with theory and had a code example on page 3. Rewritten with a working code example in the first 3 lines, explanation below. Time on page for first-time readers: up 40%. Support tickets on auth: down 28%.
The Feature Before Docs
A major feature was released without documentation for 9 days. Power users were testing in production, building custom workarounds, and asking for clarifications that created conflicting answers in the community forum. Doc-ready is now part of the feature release checklist.
System 1 · Domain Mastery
6 years of Engineering expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 6 years in the field. What Divya knows without you telling them anything.
● Live
API reference documentationDeveloper guides and quickstartsSDK documentationInternal engineering wikisProcess and runbook documentationDocs-as-code (Markdown, MDX, RST)Docs site management (GitBook, Mintlify, Docusaurus)Technical writing style guidesVideo tutorial scriptingChangelog writing
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Divya 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 Divya'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 Divya'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 Divya 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)
Divya watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Divya 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
Divya's 7 active watch patterns
WATCH
Any documentation page >6 months without a review (decay risk)
WATCH
Feature released without corresponding documentation (support ticket surge incoming)
WATCH
Code example in docs not tested against current API version
WATCH
New error code or API response not documented within 2 weeks of release
WATCH
Tutorial step that doesn't work in a clean environment (test failure)
WATCH
Search traffic declining for a core documentation topic (findability issue)
WATCH
Broken link or 404 in published documentation
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Divya 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
Doc freshness auditSupport ticket analysis for documentation gapsSearch query analysis for missing content
Draft for Approval
New documentation pages and tutorials for reviewChangelog entriesDeprecation notices
Act with Notification
Doc age alerts and review assignmentsBroken link fixes in existing pages
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. Divya 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
Divya 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
Divya's 6 owned KPIs
KPI
Documentation coverage rate (% of features with current docs)
KPI
Support ticket reduction attributable to documentation improvements
KPI
Doc freshness rate (% of docs reviewed within 6 months)
KPI
Average time on page for key tutorials (proxy for engagement)
KPI
Search success rate (% of documentation searches that result in a click)
KPI
Broken link count in published docs (target: zero)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Divya 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