TELECOM / OPTICAL NETWORKING

Engineering design documents generated from technical manuals

Engineers spend days writing network-element design documents from large sets of equipment manuals. Wexa built agents that retrieve the right facts per section and write the document directly.

Download this case as PDF Book a demo

of sections accepted at the interim review
writing into the team's document workspace

CLIENT: Optical-networking software and services firm
REGION: US
WHEN: 2025
ENGAGEMENT: Proof of concept
WEXA COMPONENTS: Knowledge base · retrieval agents · document writer

01Case 30

The challenge

Large, overlapping technical documentation
Manual assembly of design documents
Consistency across documents and engineers

What Wexa built

Ingestion and tagging of equipment documentation
Per-section retrieval through question-and-answer prompts
Writer agents composing a structured design document in real time
Next steps identified: diagrams, detailed specifications, per-pattern agent tuning

02Case 30

How it runs on Wexa

FigureHow this use case runs on Wexa: client systems connected, ontology discovered, context graph in the Wexa memory layer, agents and process flows, and governance. Highlighted components are central to this use case.

03Case 30

Solution architecture

FigureDocument-generation architecture (redrawn from the project design).

04Case 30

Results

Measure	Before / without Wexa	With Wexa
Engineer days per design document (100 documents a year)	5 days	2 days
Annual cost of the process	$500K	$200K
Time to implement the AI solution	4 months	6 weeks
AI build cost (one-time)	$192K	$22K
AI operating cost per year (models, infrastructure, upkeep, platform)	$141K	$69K
Total AI cost in year 1	$333K	$91K