AI Literacy & Prompting for Engineers

The durable AI fundamentals every engineer now needs: how large language models actually work, why they fail, how to prompt for engineering-grade output, and the verification habits that make AI safe to use on real work.

Private cohorts & on-site
Format: 2-day (8:30 a.m.–4:30 p.m.)
Level: Introductory
Location: Scheduled on demand · on-site at your facility or a regional venue
Date(s): Not yet scheduled for open enrollment. Get notified when it is, or book it privately for your team.
Includes: Certificate of Completion · printed slide binder · take-home reference text

Get notified when this course is scheduled

One email when dates are set. Or skip the wait: run it as a private cohort, on-site at your plant.

Talk to us about a private cohort
  • One email, no sequence
  • Never shared
  • Reply within one business day

Faculty

Faculty details for this seminar will be announced with the full schedule.

Fees

Early: $1,895 (payment 4+ weeks ahead)
Standard: $2,095 (check/ACH) · $2,165 (card)

Group discount: $200 off per attendee for 3+ from the same organization.

Also Available

  • Corporate on-site delivery at your facility
  • Private cohort sessions
  • Digital curriculum licensing

Seminar Overview

Every engineering role now touches AI tools, yet almost nobody has been taught how they work or where they break. This course fixes that: a plain-language model of how large language models generate answers, what context windows and training data imply, why hallucinations happen and where they concentrate, and how to structure prompts and workflows that produce engineering-grade output.

Day one builds the mental model and the prompting craft: task decomposition, providing constraints and context, few-shot examples, structured output requests, and iterating on poor answers. Day two builds judgment: verification habits (never ship an unchecked answer), source-grounding with your own documents, recognizing vendor overclaiming, and a practical policy for what AI may and may not do inside an engineering organization. No coding required.

Ideal Learner

  • Engineers of any discipline starting to use AI tools in daily work
  • Quality, manufacturing, and program staff who read AI-generated content
  • Managers setting expectations and policy for AI use
  • Teams preparing to adopt ChatETS, copilots, or other AI tooling

Learning Objectives

  • Explain how LLMs generate answers and why they hallucinate
  • Prompt for structured, constraint-bound engineering output
  • Verify AI output with a repeatable check routine
  • Recognize where AI adds value and where it manufactures confidence
  • Operate inside a sane team policy for AI use in engineering work

Consulting Sessions

Seminar attendees can sign up for individual consulting sessions with the instructor. Sessions are free for registered attendees, first-come first-served — sign up when registering by calling 248-539-0473 or during the seminar.

Seminar Outline

  • What a language model is (and is not)
  • Training data, context windows, and recency limits
  • Why hallucinations happen and where they concentrate
  • Determinism, temperature, and answer variability
  • Task decomposition and constraint specification
  • Reference material and few-shot examples
  • Structured output: tables, JSON, checklists
  • Iteration patterns for weak first answers
  • The check routine: source, calculation, sample
  • Cross-checking calculations and standards citations
  • Red flags: confident tone, missing units, fake references
  • Building a personal verification habit
  • What AI may draft, check, and decide — and what it may not
  • Confidentiality and IP boundaries in prompts and uploads
  • Judging vendor AI claims as a buyer
  • Team exercise: write your organization's AI usage rules

More in Track K — Platform, AI & IT Enablement

Full Course Catalog