Skip to main content

Telco · ML Inference & Explainability

Augur

Metadata-driven model execution and explainability — turning Conduit's features into audited predictions, no ML team required.

O conteúdo detalhado desta página está disponível apenas em inglês.

Visão Geral

Augur is the inference execution layer of the Sapium platform. It takes features materialised by Conduit, runs registered model artefacts against them on a schedule or trigger, and writes predictions — plus per-prediction SHAP explainability — back into the operator's feature store, completing the data-to-decision pipeline.

Resultado

Completes the feature-to-prediction pipeline for the same Tier 2 operator already running Conduit in production. Churn and revenue-assurance predictions are now scored automatically on every pipeline run, with per-prediction explainability generated for regulatory audit — without the operator adding a dedicated ML team.

What it does

An operator registers a model artefact by its storage location (S3 or GCS), maps its declared inputs to feature views already produced by Conduit, and configures where its predictions should be written back to. Augur validates that mapping before anything runs — a model input with no matching feature is rejected at save time, not discovered mid-execution.

Once a Prediction Workflow is enabled, Augur runs it on a Conduit webhook, a cron schedule, or on demand: it fetches the right feature vectors per entity, executes the model, and writes each prediction back through Conduit’s API alongside a SHAP-based explainability record. Every run is tracked as an immutable record — status, entity count, duration, and the feature importances that drove the result.

Where it fits

Conduit turns raw CDRs into features. Augur turns those features into predictions. The boundary is strict: a registered model has no dependency on Conduit or the underlying feature store, and Augur never touches raw network data directly — all feature I/O is mediated by Conduit’s API. That separation is what lets one registered model serve multiple prediction workflows, and what keeps every prediction traceable back to the exact feature set and model version that produced it.

Explainability as a first-class output

Every prediction Augur produces ships with a feature importance vector and a confidence score, not just a number. That is not a reporting add-on — it is the audit trail GDPR Article 22, the EU AI Act, and Brazil’s LGPD Article 20 require whenever a scoring model informs a commercial decision like a churn-triggered offer or a service restriction. Run records, model versions, and per-entity explainability are retained so an operator can answer “why did the model decide this” without digging through logs.

Pronto para transformar dados em decisões?

Trabalhamos com operadoras de telecomunicações de médio porte prontas para levar a IA da prova de conceito à produção.

Iniciar uma conversa