ICCT logo

Internal academy

ICCT Training Library

AI & Agent Workflows

Local Open Models with Ollama

Teach local AI workflows with Ollama so students understand open-model execution, offline-friendly setups, and the tradeoffs between hosted and local tooling.

Intermediate 3 credits 50+ guided hours 3 weeks Modules: 2 Projects: 2

Easy Interactive curriculum

Signal Lab for short, easy-to-digest learning

This course breaks big ai & agent workflows ideas into short missions, plain-language definitions, and interactive practice rounds. Teach local AI workflows with Ollama so students understand open-model execution, offline-friendly setups, and the tradeoffs between hosted and local tooling.

Class missions: 2 10 minutes per topic Lab + quiz + homework + game

Class mission

What local AI changes

Minutes: 20

Big idea: Understand the different operating model of open-weight tools. We keep it simple, hands-on, and easy to explain back.

10 min

Hosted AI vs. local models

Model means the brain-like engine an AI tool uses to answer and create things In this topic we use it for latency, privacy, cost, and convenience tradeoffs.

Quick picture: imagine using this in internal experiments.

Mission: use Model to practice latency, privacy, cost, and convenience tradeoffs.

Model Ollama Terminal Hosted AI
10 min

Ollama basics and model workflows

Ollama means a local model tool that lets AI run on your own computer In this topic we use it for running models, selecting sizes, and practical setup thinking.

Quick picture: imagine using this in offline-friendly demos.

Mission: use Ollama to practice running models, selecting sizes, and practical setup thinking.

Ollama Model Terminal Ollama Basics

Word wall

Terms made easy

Model

the brain-like engine an AI tool uses to answer and create things

Ollama

a local model tool that lets AI run on your own computer

Terminal

the window where command-line work happens

Hosted AI

one part of the lesson that helps students notice what the tool, page, or process is doing

Lab mission

Lab Mission

Document a decision guide for when your class should use a hosted tool or a local model workflow.

  1. Look at one example from internal experiments and point to where Model shows up.
  2. Build one tiny version that uses Model and Ollama in the right place.
  3. Tell a teacher or partner what you changed, what worked, and what you would improve next.
Homework

Homework: teach Model in your own words, then create local setup guide with one example, one picture, or one tiny screenshot.

Quick quiz

Check understanding in a friendly way

Game mode

Term Match Sprint

Matches: 0 / 4

Match each word to the right meaning as fast as you can.

Words
Meanings

Pick a word, then pick the matching meaning.

Outcomes

What students should leave with

  • Set up and run local-model workflows with Ollama.
  • Explain the tradeoffs between hosted AI tools and local/open-model setups.
  • Use local models for drafting, coding support, and privacy-aware experimentation.

Reference map

Core topics to cover

Local inference Model selection Offline workflows Privacy boundaries Tooling around local models Performance tradeoffs

Module sequence

ICCT lesson flow

Module 1

What local AI changes

Lessons: 2

Understand the different operating model of open-weight tools.

Hosted AI vs. local models

latency, privacy, cost, and convenience tradeoffs

Ollama basics and model workflows

running models, selecting sizes, and practical setup thinking

Checkpoint lab

Document a decision guide for when your class should use a hosted tool or a local model workflow.

Module 2

Local productivity patterns

Lessons: 2

Use Ollama for useful work instead of novelty demos.

Local drafting and Q&A workflows

prompting, structured output, and reliability checks

Pairing with local tools and shells

terminal habits, scripts, and repeatable AI-assisted tasks

Checkpoint lab

Build a small local helper workflow for transforming notes or drafting structured output.

Capstone prompts

Projects students can actually ship

Hosted vs. Local Decision Matrix

Compare tool choice by privacy needs, cost, speed, and classroom practicality.

Local Workflow Demo

Show a repeatable Ollama-backed workflow for drafting, transformation, or simple coding support.