Skip to Content

Setup

Open Configurations (/configurations). Tabs: Configurations List, Analysis & LLM, Agents. Import (JSON) sits on the right.

Create a configuration

  1. Create New (Quick Access) or click a card to edit.
  2. Name and optional description.
  3. Set configuration type: Analytic, Interactions, Personality, or Financial (help modal shows sample rows).
  4. Bind a data source:
    • MongoDB — database + collection (optional aggregation pipeline). Default collection in samples is often logging.data_ecosystemruntime_flatten for runtime logs.
    • Trino — catalog / schema / table or SQL. Trino is extract-only; report writes stay on Mongo.
  5. Map fields the type requires (especially Financial — aliases alone are not enough).
  6. Enable analysis families (or leave defaults). Disable unused families to keep jobs fast.
  7. Save. You cannot edit a config while a job for it is running or queued.

Import loads a previously exported JSON (metadata stripped). Use this to clone environments.

Analytic

Best for a single wide table (events, customers, transactions).

Enable on Analysis & LLM (or the form):

ModuleWhat it produces
Main analysisProfiling, correlations, histograms — Main analysis
CategoricalTests and charts for categories — Categorical
ActuarialRisk, extremes, survival-style metrics — Actuarial
Feature engineeringML-ready features — Feature engineering
Time seriesOff by default. Needs a datetime column — Time series

Optional: LLM interpretation on the analysis agent. Time Series also has its own page for datetime, grain, journeys, and event association.

Interactions

Full walkthrough: Interactions Analytic.

Pair calls (ecosystemruntime) with responses (ecosystemruntime_response) by UUID. Mongo connection and database come from Source. Then:

  1. Set calls and responses collections.
  2. Discover Predictors — pick specific predictors or Analyze all. Required before Run on Mongo.
  3. Optional date range and attribution window (hours, default 168).
  4. Optional declared experiment groups (control + treatments).
  5. Enable families on Analysis & LLM. Marketing mix is off by default.
FamilyFocus
General performanceCampaign & predictor — also channels, convergence, economics, fairness
Offers and catalogOffers & catalog — also experimentation
Customer engagementCustomer uptake
Market intelligenceMarket intelligence
Marketing mixAdstock / saturationoff by default
Entity clusteringOffers by category — on by default when enough catalog rows

Acceptance is uptake, not purchase or causal lift. LLM interpretation cannot change metrics. After a simulation, point this config at the same logging collections.

Personality

Requires transactions with customer, amount, merchant/category, timestamp. Optional score / campaign collections (often suggested from the source name).

FamilyFocus
General / spend / moneyOverview, spend, money
DriftTransitions
Category patternsTxn-scan co-occurrence
CalendarWeekend, DOW, daypart
RecommendationsLifecycle cards
Intelligent campaigningPlaybook / export
Customers / data qualityChange reasons

Needs enough history for drift. Not a substitute for Spend Personality scoring in Runtime.

Financial

Map identity, time, and recognized revenue. Map cost if you need ROI/CAC. Industry profile: generic, banking, telco, or gambling.

FamilyKPIs (when mapped)
Unit economicsARPU / ARPA / ARPPU
ReturnsROI, ROAS, CAC
ValueObserved LTV
ProfitabilityMargin, cost-to-serve
GrowthNRR, GRR, churn
Time / breakdowns / distributions / comparisonsTime, breakdowns, distributions, comparisons
CampaignsAttribution
LedgersAR/AP/GL
Industry packProfile-specific
Data qualityMapping coverage

ROI is skipped, never invented, if cost/investment is not mapped.

Dimensions (product, region, customer, division, category, account, type) slice measures. Hierarchies such as region → category → product run when two or more levels are mapped.

Analysis & LLM tab

After Save, use Analysis & LLM for the selected config:

  • Agent LLM interpretation
  • Module LLM interpretation (Personality / Interactions / Financial)
  • Per-type family checkboxes (same families as above)

Save Settings applies to new jobs, not in-flight ones.

Agents tab

Embedded test console: bind the saved config, pick a specialist, ask questions over jobs and reports (MCP tools). Same catalog as the Agents sidebar page.

After a job completes, each family has its own report page under Reports.

Last updated on