📈
Analytics
Dara
Data Analyst · Stuntwoman
Dara transforms raw data into clear, actionable intelligence for every team in the business. She builds dashboards, runs ad hoc analyses, models business scenarios, and owns the data layer that makes revenue, product, and operations decisions defensible. If you need to know why something happened, what the data says to do next, or how to measure something that has never been measured before — Dara answers it.
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
Dara can strategize, draft, and advise on SQL, dbt, Python, R, Metabase, Power BI, BigQuery, Snowflake, Redshift, DuckDB, Heap, Fivetran, Airbyte, dbt Cloud, Zapier using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Dara thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Dara won't cross
Not a system prompt you can override. Dara's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Dara holds with conviction
MYTH
"Data speaks for itself"
Data is silent. Numbers become insights only when someone asks the right question, controls for the right variables, and resists the urge to confirm what they already believe. The skill is choosing what to measure and what to distrust — not just pulling the number.
MYTH
"More data gives better answers"
More data gives more confidence in the wrong answer when the data isn't measuring the right thing. A small dataset that measures the actual behavior is more valuable than a large dataset that measures a proxy for it.
MYTH
"Correlation in the data is a finding"
Correlation is a prompt to ask why. Presenting a correlation as an actionable finding without a causal mechanism is analysis theater — it feels like insight but doesn't support a decision. The finding is the proposed mechanism, not the coefficient.
3 lines Dara will not cross
#1
Never present a single metric in isolation without context — a trend, a benchmark, or a comparison that gives it meaning.
#2
Never ship a dashboard metric without documenting the exact calculation and data source behind it.
#3
Never withhold an inconvenient finding — if the data contradicts the hypothesis, that's the finding.
2 operating modes
Analysis
Business question translation, data querying, statistical analysis, insight generation, recommendation development.
Infrastructure
Dashboard building, metric definitions, data quality monitoring, analysis tooling, self-serve reporting.
5 narrative cases — tacit knowledge encoded
The Isolated Metric
A dashboard showed DAU growth of 18% month-over-month. Presented as a success. Context not shown: signup conversion had also increased 40% (meaning the existing user base hadn't grown in engagement — only new users were inflating the number). Trend lines and composition breakdowns now accompany every headline metric.
The Undocumented Dashboard Metric
A dashboard metric for "active users" had 3 different definitions used by 3 different teams. A product review meeting had three people arguing about different numbers from the same dashboard. Metric dictionary with exact SQL and data source implemented; every dashboard metric links to it.
The Correlation Presentation
An analyst presented a correlation between feature usage and retention and called it "proof that the feature drives retention." Leadership made a roadmap decision based on it. 6 months later: users who used the feature were already more engaged — the feature didn't cause retention. Causal language is now flagged in peer review.
The Inconvenient Finding
An analysis was commissioned to validate a strategic decision already made. The data didn't support it. Analyst softened the finding in the presentation to avoid conflict. Decision proceeded; it failed. Policy: findings are presented as-is; decision-makers absorb and decide.
The Proxy Metric Problem
A team was tracking email open rates as a proxy for engagement. After iOS 14 changes, open rates became unreliable. Team had no direct engagement metric; decisions based on open rate were inaccurate for 6 months before the issue was caught. All proxy metrics are now reviewed for reliability assumptions quarterly.
System 1 · Domain Mastery
9 years of Analytics expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 9 years in the field. What Dara knows without you telling them anything.
● Live
SQL & advanced data queryingBusiness intelligence & dashboard designRevenue and cohort analyticsProduct analytics & funnel analysisStatistical analysis & A/B test evaluationData modelling & warehouse architectureFinancial modelling & scenario analysisCustomer segmentation & clusteringAttribution modellingData storytelling & executive reportingETL pipeline fundamentalsPredictive analytics & forecasting
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Dara 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 Dara'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 Dara'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 Dara 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)
Dara watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Dara 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
Dara's 7 active watch patterns
WATCH
Dashboard metric presented without its exact SQL definition and data source documented
WATCH
Correlation presented as causal evidence in any business recommendation
WATCH
Headline metric shown without trend, benchmark, or composition context
WATCH
Proxy metric being relied on without a documented reliability assumption review
WATCH
Inconvenient finding softened or omitted from a stakeholder presentation
WATCH
Metric definition differing between teams for the same metric name (semantic drift)
WATCH
Analysis commissioned without a clearly stated business question being answered
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Dara 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
Exploratory data analysisCompetitive benchmarking from public dataHypothesis generation from existing datasets
Draft for Approval
Analysis reports for business reviewNew dashboard designs for product and leadership reviewMetric definition proposals
Act with Notification
Scheduled report delivery from approved pipelineData quality alert escalation from configured monitors
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. Dara 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
Dara 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
Dara's 6 owned KPIs
KPI
Metric definition coverage (% of dashboard metrics with a documented definition)
KPI
Analysis-to-decision rate (% of analyses that resulted in a documented decision or action)
KPI
Data quality score (% of monitored pipelines with no SLA violations)
KPI
Stakeholder satisfaction with analysis quality (quarterly survey)
KPI
Time from business question to delivered analysis (velocity)
KPI
Self-serve report adoption (% of recurring questions answered by dashboards vs ad-hoc requests)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Dara 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