INDUSTRY ARCHITECTURE / Manufacturing & energy

Manufacturing & energy architecture

A connected reference design spanning domain information, data engineering, AI services, agent execution, and governance.

DOMAIN DESIGN DECISION

The business context
shapes the architecture.

A sensor anomaly alone does not describe asset condition; maintenance history, operating state, and inspection context also matter.

Align equipment identifiers and time zones, record sensor units and calibration context, and separate observed symptoms from inferred causes.

Start with asset maintenance rather than attempting to automate the whole industry at once. Define a bounded request, the evidence required to answer it, and the person accountable for accepting the result.

DATA → AI → AGENTIC AIDOMAIN CONTEXT: Asset / Sensor observation / Work order / Inspection finding

Data architecture

01
Domain sources
Sensor events, maintenance logs, inspection images, manuals. Identify the system of record, owner, refresh rate, and approved purpose for each source.
02
Ingestion & contracts
Batch, change-data capture, events, and document intake as appropriate. Validate schema, identity keys, event time, and rejected records.
03
Storage & transformation
Separate raw evidence, validated records, and curated domain products. Preserve version history and reconciliation results.
04
Semantic serving
Asset · Sensor observation · Work order · Inspection finding. Publish agreed definitions, access rules, and reusable interfaces for analytics and AI.

AI architecture

01
Approved information
Use curated domain products and approved documents. Preserve metadata, effective dates, and access scope.
02
Retrieval & features
Build permission-aware retrieval indexes or model features for the specific task. Test relevance and freshness independently.
03
Model & evaluation
Evaluate candidate methods on representative domain examples. Check groundedness, completeness, uncertainty, cost, and failure behavior.
04
Experience & feedback
Serve sourced drafts or scored signals through a review experience. Capture feedback without silently retraining or widening data access.

Agentic AI architecture

01
Task & identity
Record the initiating user, allowed purpose, task boundary, and completion criteria.
02
Reasoning & state
Maintenance planning agent and Quality investigation agent. Keep task state, retrieved evidence, and unresolved questions traceable.
03
Scoped enterprise tools
Expose typed, permission-checked search, lookup, and draft tools. Validate arguments and handle retry or timeout safely.
04
Approval & audit
Equipment operation, work orders, and safety decisions require qualified approval. Record tool calls, reviewer decisions, and the accepted result under an agreed retention policy.

Shared governance & operationsOwnership · classification · lineage · access · quality · retention · evaluation · observability · incident response · cost management

Implementation decisions
to resolve before build.

Data lifecycle

Identify authoritative records, history requirements, update frequency, retention, and the consequences of stale information. Preserve source event time and ingestion time where ordering matters.

Serving & integration

Choose batch, event, API, or document access based on workload needs. Separate read-only retrieval from tools that alter enterprise records. Define timeouts, retries, and recovery ownership.

Operational evidence

Measure asset-event alignment, useful evidence retrieval, false-positive review burden, and draft work-order completeness. Keep versioned evaluation cases, end-to-end traces, and reviewer feedback so changes can be assessed against an agreed baseline.

CASE

A contextual maintenance planning and quality review workflow

See the proposed architecture applied to a focused workflow.

Asset & quality intelligence

Connect asset knowledge, inspection findings, and maintenance planning.