SSBI LifeExecutive Cockpit

Tech Overview

The architecture under the cockpit — how data flows from many disconnected product, channel and policy systems into one governed truth, how that truth becomes a decision, and how two 360s still deliver over real data gaps.

SBI Life Insurance Company Limited · FY26 (Mar'26, audited anchor)
India's #1 private life insurer by Individual NBP (25.5% private share) & IRP (22.9%)
29,344 employees · 1230+ own offices · 9 bancassurance partners
Under the hood

One governed brain over
many disconnected systems.

No big-bang migration. The platform federates each product, channel and policy system, resolves it to one ontology, and serves a single trusted number — then turns that number into a decision, and the decision into an owner's action.

10/12
Sources fresh
9,879,528
Records governed
4/10
Products on PAS grain
55%
Premium at office grain
Technical architecture

The governed stack — eight tiers, federated not centralized

Each product, channel and policy system stays where it is. The platform layers ingestion, master-data resolution, a shared ontology and a semantic layer on top, then serves one governed truth to the apps and AI. Data flows top → bottom.

Sources
12 systems of record
Policy Admin System (PAS)Underwriting engine · rulesBancassurance CRM · SBI branch feedAgency & digital portalInvestment / AUM systemIRDAI / exchange filings · news
Ingestion
adapters · lineage · SLA
Source adaptersCDC & batch loadsFreshness / SLA monitorLineage capture
Store
raw → curated
Raw landing zoneCurated storeVersioned snapshots
MDM · Resolution
many codes → one node
Entity resolutionGolden recordsSurvivorship rulesDedup · term-conflict
Ontology
the knowledge graph
T-Box · 10 classesA-Box · instancesTyped predicatesOffice = keystone
Semantic
defined once, federated
Metric definitionsGrain tagsFederation engineAllocation + confidence
Serving
governed access
Governed metrics APIQuery layerReconciliation tests
Consumption
apps + intelligence
360 views · Next.jsExec briefs · deterministicAzure OpenAIAgentsweb-grounding
Data flow

How one record travels — source to served truth

A single transaction's journey through the stack. A confidence flag and a reconciliation tie-out ride along with it the whole way.

1
Extract

Adapters pull each product, channel & policy system's events on schedule / CDC.

2
Land

Raw records stored verbatim, with lineage + timestamp.

🧩
3
Resolve

Codes matched to one canonical entity.

🧬
4
Model

Mapped onto the ontology — classes & relationships.

📐
5
Define

Native fields → governed metrics; estimates flagged.

🔌
6
Serve

One metrics API; reconciliation gates the numbers.

🔭
7
Consume

360 views, exec briefs & AI read one truth.

🏷 A confidence flag (Actuals / Allocated / Region-only) and a reconciliation tie-out travel with every value — so a number is never shown without knowing how bankable it is.
From data to action · the decision flow

How one number becomes a decision

The governed truth doesn't sit in a warehouse — it routes itself to the right view, the right action, and the right owner.

The agentic layer

An agent on every value pillar

The four value-creation pillars don't just have dashboards — each has a standing agent that reads its governed data products and recommends the next move. Same ground truth, automated.

📈Profitable Growth — APE & VNB
Watches

APE growth, VNB margin & protection / annuity new-business vs plan

Grounds on
business_unit · service_line · signal · kpi
Acts in Profitable Growth — APE & VNB
🛡Product-Mix Shift & Protection
Watches

the ULIP → non-par / par / protection mix shift & per-segment VNB margin

Grounds on
opportunity · pipeline_stage · brand_cohort · project
Acts in Product-Mix Shift & Protection
🏦Distribution Reach — Bancassurance & Agency
Watches

bancassurance, agency & digital reach and channel activation vs target

Grounds on
customer · vertical · site · kpi
Acts in Distribution Reach — Bancassurance & Agency
💎Persistency, Embedded Value & Capital Strength
Watches

13M / 61M persistency, solvency buffer & the embedded-value bridge

Grounds on
kpi · ops_metric · service_line · covenant_qtr
Acts in Persistency, Embedded Value & Capital Strength
The hard part

Two 360s that work before the data is clean

Some products and channels aren't fully on the common PAS grain yet, so the channel→segment mapping and office-grain detail are incomplete. These views still answer — by resolving, allocating-and-flagging, then reconciling. The estimate is labelled, never hidden.

🗂Org Roll-up 360
Open →
The gap
6 of 10products not yet office-grain

Some channels report at their own grain — so the channel → office → segment → legal-entity rollup is partly missing or inferred.

How the platform bridges it
1
Resolve. AI maps each legacy channel / office / leader code to one canonical org node.
2
Allocate + flag. Where a channel isn't mapped, premium is disaggregated from its geography on learned drivers — and marked an estimate.
3
Reconcile. Allocated parts must foot back to the segment total; breaks are surfaced, not hidden.
~55%grain coverage

of premium already at true office grain; the rest labelled & closing as channels move onto PAS

📍Distribution Network 360
Open →
The gap
10 channelsallocated or region-only

For channels not yet on the common grain, office, premium-at-grain and productivity detail isn't available at office grain — so the office twin would otherwise be blank.

How the platform bridges it
1
Estimate. Office figures are modelled to ~91% coverage from geography totals and office-network signals.
2
Flag confidence. Every estimated office carries an Actuals / Allocated / Region-only badge and a coverage %.
3
Flip to actuals. As each channel cuts over to PAS, its office grain rises and estimates become ledger actuals.
~91%grain coverage

avg office-grain coverage today — transparent where it's modelled

The harness catches the gaps
13 of 14 governed identities tie out to the cent

Reconciliation runs live on the data. The 1 known break below is the office-grain gap surfaced on purpose — exactly what a CFO or auditor wants flagged, not buried.

Open Data Health →
⚠ flagged
Renewal premium = Σ cluster renewals
13
tie to the cent