BBajel ProjectsExecutive Cockpit

Tech Overview

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

Bajel Projects Limited · FY26 (Mar'26, standalone audited anchor)
Bajaj Group's power-transmission & distribution EPC and tower/monopole manufacturing arm
1,400 employees · 1+ plants & units · 6 export markets
Under the hood

One governed brain over
many disconnected systems.

No big-bang migration. The platform federates each segment, plant and project 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
10,040
Records governed
5/10
Segments on SAP grain
42%
Revenue at site grain
Technical architecture

The governed stack — eight tiers, federated not centralized

Each segment, plant and project 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
ERP / SAP · project ledgersRanjangaon MES · fabrication / galvanizingTendering & PGCIL / utility portalsPrimavera P6 · project controlsCRM · HRMSBSE/NSE · CRISIL · commodity feeds
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 predicatesPlant = 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 segment, plant & project 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 Order-Book Growth
Watches

order book (₹4,055 Cr), bid-pipeline conversion & order inflow vs plan

Grounds on
service_line · opportunity · signal · kpi
Acts in Profitable Order-Book Growth
📈Margin Expansion & Commodity Discipline
Watches

EBITDA margin, the 765 kV substation mix & steel / zinc cost vs plan

Grounds on
business_unit · ebitda_bridge · supplier · kpi
Acts in Margin Expansion & Commodity Discipline
💵Working-Capital & Balance-Sheet Discipline
Watches

debtor days (214), free cash flow, net debt/EBITDA & covenant headroom

Grounds on
kpi · ar_aging · debt_tranche · covenant_qtr
Acts in Working-Capital & Balance-Sheet Discipline
🌐Capability, International & New Energies
Watches

765 kV AIS/GIS & data-centre capability build and the MENA order book

Grounds on
brand_cohort · integration_workstream · project · kpi
Acts in Capability, International & New Energies
The hard part

Two 360s that work before the data is clean

Some segments and capabilities aren't fully on the common SAP grain yet, so the capability→segment mapping and site-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
5 of 10capabilities not yet site-grain

Some capabilities report at their own grain — so the capability → site / project → segment → legal-entity rollup is partly missing or inferred.

How the platform bridges it
1
Resolve. AI maps each legacy project / site / leader code to one canonical org node.
2
Allocate + flag. Where a capability isn't mapped, revenue 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.
~42%grain coverage

of revenue already at true site grain; the rest labelled & closing as segments move onto the common grain

📍Project & Site 360
Open →
The gap
9 sitesallocated or region-only

For capabilities not yet on the common grain, site-asset and executed-revenue detail isn't available at site grain — so the site twin would otherwise be blank.

How the platform bridges it
1
Estimate. Site figures are modelled to ~84% coverage from geography totals and plant / site-asset signals.
2
Flag confidence. Every estimated site carries an Actuals / Allocated / Region-only badge and a coverage %.
3
Flip to actuals. As each capability cuts over to the common grain, its site detail rises and estimates become ledger actuals.
~84%grain coverage

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

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

Reconciliation runs live on the data. The 0 known breaks below are the site-grain gap surfaced on purpose — exactly what a CFO or auditor wants flagged, not buried.

Open Data Health →
14
tie to the cent