Skip to content

Optional analytics

Allow optional analytics to help improve projects, writing and navigation. It uses a pseudonymous first-party identifier after consent. No names, email addresses, messages or search text are collected.

Read the privacy policy
Case studyRevenue intelligence system

Automated Intelligence Revenue System (AIRS)

Turns product usage signals into prioritised, explainable revenue action.

A revenue intelligence system design connecting behavioural product data, governed analytical models, explainable scoring, orchestration, and operational sales interfaces.

Workflow map
product and account data
governed features
explainable score
revenue action
My role

Data architecture, analytical modelling, ML workflow, and product design

Project stage

Current system design

What it replaces

Replaces stale product exports with prioritised accounts, clear reasoning, and sales-ready next steps.

Current evidence

Current system design

01
Overview

What the system is meant to change.

For

Product-led teams that need to connect usage, account health, and revenue signals into prioritised actions.

Replaces

Product usage, account health, CRM, and billing signals often live in separate systems. Revenue teams work from stale exports or intuition because no governed layer converts that behaviour into prioritised action.

Produces

A governed daily view of prioritised accounts, score explanations, and recommended next actions, designed around sales capacity rather than an arbitrary probability threshold.

02
Architecture

Treat scoring as one governed step inside a revenue workflow.

Product events, CRM accounts, and billing state land in BigQuery and are modelled with dbt. A feature pipeline supports baseline comparison and XGBoost scoring, SHAP provides local explanations, and Airflow coordinates delivery into sales briefings and Power BI.

01
BigQuery
02
dbt
03
Features
04
XGBoost
05
SHAP
06
Airflow
07
Power BI
01

Product and account data

02

Explainable scoring

03

Revenue action

Design constraints
  1. 01Model product, CRM, and billing data at a stable account and scoring-date grain.
  2. 02Compare a simple rules or logistic baseline before accepting a more complex model.
  3. 03Keep explanations tied to governed features rather than generated sales language.
  4. 04Design delivery around team capacity and duplicate-safe orchestration.
Engineering decisions
  1. 01Stable analytical grain: Account and scoring date form the contract across features, scores, explanations, and delivery.
  2. 02Baseline before complexity: Rules and logistic regression provide a reference before evaluating whether XGBoost adds decision value.
  3. 03Capacity-aware thresholds: Precision and lift at the team’s workable daily volume matter more than an arbitrary probability cut-off.
  4. 04Explain before outreach: SHAP-backed reasons support account review; generated outreach remains outside current evidence.
System behaviour and reliability
  1. 01Product, CRM, and billing data are modelled at account and scoring-date grain.
  2. 02Contract checks protect keys, freshness, accepted values, and feature ranges.
  3. 03Baseline and candidate models produce comparable account scores.
  4. 04Local explanations translate model signals into controlled operational language.
  5. 05Airflow coordinates scoring and delivery into a decision interface.
  6. 06The design uses stable account and scoring-date keys.
  7. 07Batch writes are designed around merge semantics instead of blind append.
  8. 08Notifications require deterministic delivery keys to prevent duplicate outreach.
Evaluation approach
  1. 01Use temporal train, validation, and untouched test windows.
  2. 02Compare PR-AUC, precision@k, recall@k, lift@k, Brier score, and calibration.
  3. 03Keep generated factual statements traceable to allowed evidence fields.
03
Visual proof

Interface views for the workflow and its decisions.

Design representation — replace these views with production screenshots as the product matures.

Revenue action queue
Workflow map
product and account data
governed features
explainable score
revenue action
Revenue action queue

A proposed decision surface showing priority, evidence, explanation, and the next review step.

Account explanation
Account review
Northstar Labs
priority score
0.84
Weekly active seats
+ signal
Feature adoption
+ signal
Admin inactivity
risk
Review expansion readiness. Lead with seat growth and feature adoption; verify the inactive admin before outreach.
Account explanation

A feature-level view designed to make the ranking inspectable before anyone acts on it.

04
Evidence and boundaries

What exists now, what remains limited, and what comes next.

This separation is intentional: planned evaluation and reliability work is not presented as completed evidence.

Current evidence

Current system design

Limitations

  1. 01No measured model or business-performance claim is published yet.
  2. 02Outreach generation remains outside current evidence until its evaluation benchmark exists.

Next validation

  1. 01Compare a rules baseline, logistic regression, and XGBoost on a temporal split.
  2. 02Select thresholds using precision, recall, and lift at the team’s daily capacity.
  3. 03Publish an idempotency test before presenting the orchestration as production-ready.
  4. 04Evaluate generated outreach for evidence coverage and unsupported claims.
05 · Discuss a similar system

Send the current workflow, source material, report, or product idea.

A polished specification is not required. The rough version is enough to establish the problem boundary and useful next step.

Discuss a similar system