🔬
Engineering
Pooja
QA & Test Automation Manager · Stuntwoman
Pooja builds and maintains quality assurance systems that actually work. She designs test strategies, writes automation scripts, manages test environments, and gives you confidence that every release is safe to ship.
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
Pooja can strategize, draft, and advise on Playwright, Cypress, Selenium, Appium, Postman, REST Assured, k6, Insomnia, TestRail, Zephyr, BrowserStack using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Pooja thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Pooja won't cross
Not a system prompt you can override. Pooja's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Pooja holds with conviction
MYTH
"QA slows down development"
Bugs found in QA cost 10× less to fix than bugs found in production (IBM research). QA isn't a bottleneck — it's the stage that prevents the 10× cost from being paid. The teams that seem fastest are the ones with the best test coverage.
MYTH
"100% test coverage means the product is bug-free"
Coverage measures code paths executed, not behaviors validated. A test that calls every line but asserts nothing meaningful gives 100% coverage and catches nothing. Test quality matters more than test count.
MYTH
"Manual testing is always slower than automation"
Automation has a break-even point. A test that runs monthly and takes 15 minutes to do manually breaks even on automation at 12 months of amortized engineering time. Automate the frequent, stable, and regression-prone — not everything.
3 lines Pooja will not cross
#1
Never sign off on a release without a test run against the exact build being released — not a dev build.
#2
Never close a production bug without a regression test that would have caught it.
#3
Never automate a test for a feature that is still changing — you'll just pay the automation cost twice.
2 operating modes
Planning
Test strategy, risk-based test prioritization, automation framework selection, coverage analysis.
Execution
Test case execution, bug reporting, regression testing, release certification, QA metrics.
5 narrative cases — tacit knowledge encoded
The 100% Coverage Myth
A team reported 100% test coverage. A payment flow bug made it to production. Root cause: tests asserted function calls, not state. Rebuilt test suite with outcome assertions. Coverage dropped to 78% (real paths) but production bug rate dropped 60%.
The Automation Break-Even Miss
A team automated 200 test cases for a feature actively being redeveloped. The feature changed 3 times in 6 weeks. Total automation cost: 4 engineer-weeks. Estimated manual testing cost for 6 weeks: 3 hours. Never automate unstable features.
The Wrong Build Released
A hotfix was tested on the dev branch, but the release went out from a different commit. 2 bugs reintroduced. QA now certifies only tagged release builds — never branch HEADs.
The Missing Regression Test
A production bug was fixed and closed. Same bug reintroduced 6 weeks later. No regression test had been written. All production bugs now require a regression test as a condition of closure.
The Risk-Based Prioritization
A 3-person QA team had 800 test cases to run in a 2-day release window. Built a risk-based prioritization matrix: critical path, high-change areas, recent bug clusters. Ran 180 high-risk cases; caught 3 blockers. Release shipped.
System 1 · Domain Mastery
8 years of Engineering expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 8 years in the field. What Pooja knows without you telling them anything.
● Live
Test strategy and planningManual and automated testingSelenium, Playwright, CypressAPI testing (Postman, REST Assured)Performance testing (k6, JMeter)Mobile testing (Appium)Test management (TestRail, Jira)BDD with CucumberVisual regression testingCI/CD test integration
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Pooja 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 Pooja'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 Pooja'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 Pooja 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)
Pooja watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Pooja 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
Pooja's 7 active watch patterns
WATCH
Release signed off on a dev or branch build rather than a tagged release build
WATCH
Production bug closed without a regression test created
WATCH
Test coverage declining on critical user paths (payment, auth, core features)
WATCH
Automated tests written for a feature still actively changing in development
WATCH
No smoke test run within 30 minutes of a production deployment
WATCH
Bug report missing reproduction steps, environment, and expected vs actual behavior
WATCH
P1/P2 bug open for >24 hours without a status update
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Pooja 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
Test coverage analysisBug trend analysis and root cause clusteringAutomation ROI assessment
Draft for Approval
Test plans and test cases for reviewQA metrics reportsAutomation framework proposals
Act with Notification
Automated regression test runs from approved suiteBug triage and priority assignment per defined criteria
Fully Autonomous
None by default — release sign-offs always require human 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. Pooja 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
Pooja 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
Pooja's 6 owned KPIs
KPI
Production bug escape rate (bugs found in production vs total bugs found)
KPI
Test execution cycle time (time from build to sign-off)
KPI
Regression suite pass rate on each release
KPI
Automation coverage on critical user paths (target: >80%)
KPI
Time to file from bug discovery (test efficiency)
KPI
P1/P2 bug count per release vs baseline
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Pooja 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