How do you translate a technical product into something workable inside someone else’s operation?
Context
At Conduit, formerly FleetGlue, I worked as a field-deployed engineering intern. I visited factories and spoke with floor staff, purchasing, and others along the workflow. Those conversations exposed details that a product description alone could not supply.
What I did
- 01
Gathered operational context directly from people working in industrial environments.
- 02
Used AI-recorded conversations to build customer-specific knowledge bases, with a flow from calls into that material.
- 03
Prepared customer presentations with NotebookLM and AI video tools, and worked on customer-oriented letters of intent.
Architecture / workflow
Keep the context attached to the conversation.
What disappears when a conversation becomes a summary?
- 01HUMAN JUDGMENT
Listen in the field
Factory staff and purchasing explain the operation
- 02INFORMATION / ARTIFACT
Capture context
Recorded conversations and field observations
- 03MODEL ASSISTANCE
Organize knowledge
AI-assisted customer knowledge and presentations
- 04HUMAN JUDGMENT
Interpret constraints
The internal team considers deployment questions
INSPECT THE FAILURE BOUNDARYA summary erases who said something or treats an observation as a requirement.
The account supports a knowledge workflow, not a complete or independently verified model of a customer’s operation.
Author-reported workflow; exact implementation is not publicly evidenced. No customer identities or factory details are reproduced.
Where it gets difficult
Different people describe the same operation from different positions. A useful knowledge base must preserve that context instead of flattening it into an apparently complete summary.
The engineering team needs operational constraints, not just enthusiasm for a product. Preparation has to help the team ask better deployment questions.
Limits & evidence
- This case study is based on my first-hand account, recorded during the earlier portfolio review. The call workflow and letters are not independently verified by public artifacts.
- No quantified reduction in meetings or deployment performance is claimed.
- Customer identities, factory details, and private conversations are omitted.
Industrial field work and customer context
Fitz’s account, recorded in the November 2026 portfolio review, describes factory visits, customer knowledge bases, presentation tools, and work as a field-deployed engineering intern.
What this does not establish
Customer conversations and artifacts are not public. The workflow is author-reported, not independently verified by a public artifact; no quantified business outcome is claimed.
What this changed
Operational context is technical input. AI-assisted preparation is useful when it helps the team retain what people actually said and understand what the customer environment requires.