You buildAn agent workflow on your live pipeline
AI starter for small business
Pick the task that eats your week, build one assistant for it, put it to work, and see the hours it gives back.
Free
8 modules
2 weeks
Beginner
What you will learn
- Find the task in your week worth automating first, and time it honestly.
- Write prompts you can reuse, and check the output before it goes out.
- Draft customer and marketing work that still sounds like your business.
- Handle lead response, quotes, and the questions you answer every day.
- Deploy one automation with a human approval step and a log.
- Decide from the numbers whether to keep it, change it, or stop.
Course content
Method step 1, Profile
Find the task worth starting with, and write down what it costs you now.
- List where your week actually goes
- Time and cost your busiest task
- Shortlist the high-value use cases
Method step 2, Build
Prompts you can reuse, and the habit of checking the output.
- Verify before you send
- Your brand voice, written down
- Reusable prompt patterns
- Working with your own files and data
Method step 2, Build
Research, offers and content that still sound like your business.
- Customer research and the offer
- Content, email and social
- Local discovery and reuse
Method step 2, Build
Lead response, quotes, and the questions you answer every day.
- Lead response and qualification
- Proposals and quotes
- Common questions and support drafts
Method step 2, Build
Meeting notes, procedures and the reporting you keep putting off.
- Meeting notes and procedures
- Document drafting and vendor comparison
- Reporting and finding what you wrote before
Method step 3, Deploy
The assistant goes to work. Putting it to work completes the course.
- Triggers and actions, without code
- The human approval step
- Exceptions and logging
- Put it to work
Method step 4, Measure
Time it again, price it, and decide whether it earns its place.
- Time saved and output quality
- Operating cost, tool cost and privacy risk
- The keep, change or stop decision
Method step 5, Document
A second workflow, a simple policy, and the record that closes the course.
- Deploy the second workflow
- A one-page AI use policy for your business
- Maintenance calendar and next quarter
- Assemble the completion record
Requirements
- One task in your own week that takes too long.
- The tools you already run the business on.
- About two hours a week for two weeks.
- A willingness to time yourself before and after.
About this course
This course is for owners and operators running the business themselves. It is the shortest course here, and it is built to produce one measurable win rather than a broad survey.
The scenarios are drawn from real small businesses: a local service company, an independent consultant, a retail and e-commerce operation, and a nonprofit. They are there so the material feels like your week rather than a corporate training deck.
The method is the same one the longer courses run on, at a smaller scale. You time one task, build one assistant for it, put it to work, then time it again.
Finishing this is a reasonable place to stop. It is also the shortest route into the longer courses, and the workflow you deploy here is a working baseline for the one you build there.
Common questions
It is free. The first module of every course opens instantly, and one free account unlocks the rest of that course. Everything on this site is free to use.
A course completes when your workflow runs live and you have measured it. You record a baseline in module 1, launch the workflow into a working environment, then measure the same thing again. That pairing is what makes the completion record worth sharing.
Yes. The first module of every course plays for everyone, with a free account needed only from module 2.
Name, role, organization, and a few questions about the workflow you want to improve. It takes about a minute, and it is what lets the guided labs use your own workflow as the project.
One workflow you own, permission to change it, and the tools your team already uses. Applied AI infrastructure also assumes access to a GPU cloud account, and AI starter for small business runs on everyday business tools.
A one-page record inside the course. Before you launch, you note a baseline on time, cost, or quality. After you launch, you measure again. The sheet holds both numbers and the difference between them.
Instructor
Roan Weigert
Records all five courses
Hackathon judge and AI content creator, and host of the AI Insights San Francisco podcast. Writes this curriculum and records every core lesson.
Other courses
The other four courses
Each one takes a different kind of work through the same five steps. Pick the one closest to your job.
You buildAn ingest and rough-cut pipeline
You buildAn AI use policy your team runs onAI literacy, ethics and data compliance
A working AI policy for your team, covering what the tools may touch and who checks it.
You buildModel serving on GPU cloud
Start with module 1
Business AI readiness
Open to everyone, with no account. You finish it holding a workflow inventory and baseline.