Engineering Automation with LLM APIs & Local Models

Hands-on building blocks for engineer-built automation: calling LLM APIs from scripts, structured output and tool calling, retrieval over your own documents, and running local/open models for IP-sensitive work — with cost and quality discipline.

Private cohorts & on-site

Format: 2-day (8:30 a.m.–4:30 p.m.)

Level: Intermediate–Advanced
Prerequisite: Basic Python or strong spreadsheet/scripting experience; no ML background required.

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.

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

The biggest productivity gains go to teams that build small, purpose-built automations — and engineers are the right builders. This hands-on course teaches the working subset of AI engineering that an engineer needs: calling LLM APIs from Python scripts, getting reliable structured output (JSON), tool/function calling, simple retrieval over your own documents, and evaluating output quality.

Day two covers the infrastructure decisions most courses skip: running local and open-weight models for IP-sensitive or offline work (what your laptop and workstation can actually run), routing between cloud and local models for cost, and the security boundaries — what data may never leave the organization. Attendees leave with a working script collection and a checklist for their first internal automation.

Ideal Learner

Engineers who script (Python/Excel macros) and want AI-powered tooling
Process, quality, and test engineers automating reports and checks
IT staff supporting engineer-built internal tools
Teams evaluating cloud vs. local AI for confidential engineering data

Learning Objectives

Call LLM APIs from Python with correct error handling and retries
Obtain reliable structured output (JSON) for downstream processing
Implement tool calling and simple retrieval over your own documents
Run local open models and decide cloud vs. local per use case
Evaluate, cost, and monitor small automations in production

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

Anatomy of an LLM API call
System prompts, context, and token budgets
Structured output: JSON modes and schema discipline
Error handling, retries, and rate limits

Document summarization and comparison
Report drafting with validated inputs
Classification and extraction for specs and test reports
Tool/function calling: when the model should compute, not guess

Running open models locally: hardware realities
Quantization and what quality it costs
Cloud vs. local routing for confidential work
What may never leave the organization

Evaluating output quality systematically
Cost tracking and model selection
Logging and monitoring small automations
Workshop: build your first internal automation