Wait.
You can build that?
Yes. And something just as useful for you.
Interactive websites. Workflows that do the repetitive work. AI you actually know how to use. Pick an idea and see where it can go.
“Make my website start a conversation.”
A little curiosity.
A reason to stay.
A hands-on experience that shows people what you can do.
The AI conversation
worth having.
Big AI. Sovereign AI.
Who’s making the decision for you?
Matt Murphy’s post gets to the question behind the tools: dependency or ownership. Start with his perspective, then explore our practical breakdown and five questions for your own AI setup.
Original perspective: Matt Murphy · @mattmurphyai
JABSystems field note inspired by his post.
Field Resources
Give your AI agent a stop rule.
Run four scripted scenarios and inspect completion, a decision cap, repeated calls, and a denied action before connecting real tools.
Try the local lab Local transcription / Practical field guideYour transcript is a draft.
Run Whisper on a synthetic English clip, inspect the actual transcript and timestamp files, and keep a listen-back review before treating the draft as a record.
Try the local walkthrough AI-assisted edits / Practical field guideThe AI edit you didn't ask for.
Keep an original draft and compare two fictional revisions with Git. Spot changed dates, owners, and approval language before accepting an edit.
Review the changes Free course · Certificate · DownloadablePrompt to Project — build practical AI skills from your first prompt to a finished project.
Work through 24 hands-on lessons, practice in the prompt lab, explore real project files, search the 77-term glossary, and earn a JABSystems certificate when you complete every checkpoint.
Start the course ↗Keep exploring · 11 more field guides & checklists
Search before you chat.
Inspect a local SQLite search baseline with three fictional notes, ranked excerpts, source IDs, and a missing-term test before adding AI answers.
Find the evidence Resource · AI handoffs · TutorialValid JSON can still be wrong.
Validate six fictional handoffs with JSON Schema, catch missing fields and a premature action, and see why a passing result still needs source review.
Read walkthrough Resource · Context budgets · TutorialYour prompt has a budget.
Count two fictional context files locally with tiktoken, preserve the essential facts, and learn why a text count is only part of an API request.
Read walkthrough Resource · Agent tools · TutorialBefore you connect an agent, read the tool list.
Inspect a local MCP demo, review its inputs, and learn why declared hints are not permissions. Includes tested commands and a connection checklist.
Read walkthrough Resource · Prompt evaluation · TutorialMake your prompt earn your trust. — build five checks with Promptfoo.
Grade fictional answers, catch two deliberate mistakes, and prepare an optional model trial. Includes a complete download and clear verification boundaries.
Read walkthrough Resource · Open source · TutorialBefore you prompt, fix the input. — inspect your document with MarkItDown.
Convert a fictional document to Markdown, check what survived, and try a source-grounded review prompt. Includes the actual HTML conversion output and clear limits.
Read walkthrough Resource · Local AI · TutorialLess chat. More decisions. — build a local AI ticket classifier.
Turn a sample request into Billing, Technical, or Other with Ollama. Get the complete PowerShell example, test your categories, and keep a person in the review loop.
Read walkthrough Resource · Tutorial · FreePrompt Patterns That Hold Up — a worked walkthrough.
Watch one weak prompt get rebuilt, pattern by pattern, until it survives real inputs. The companion example to the Prompting Checklist.
Read tutorial Resource · ChecklistSecurity Checklist — ship React + TS + SQL Server safely.
A practical, no-hype application security checklist. Open it on new projects or audit what's already live.
Open checklist Resource · ChecklistPrompting Checklist — write prompts that hold up under real inputs.
Role, task, format, examples, constraints, evals. Use it before shipping any AI step.
Open checklist Resource · ChecklistOptimization Checklist — make it fast, cheap, and quiet.
Model choice, caching, batching, latency, token spend, observability. Use it when "it works" needs to become "it scales."
Open checklistBeginner AI Training
For people who don't know where to start.
AI is everywhere, but most people are still unsure how to actually use it in a practical way. I offer beginner-friendly AI training for individuals, teams, and small businesses that want hands-on help getting comfortable with tools like ChatGPT, Claude, Gemini, and Copilot.
One 4-Hour Beginner Workshop
Best for a fast, hands-on introduction.
- AI basics and how these tools actually work
- Choosing the right tool for the right task
- Writing prompts that get useful results
- Email, document, and research workflows
- Safe and responsible AI usage
- Real-world examples from your industry
Five 1-Hour Sessions
Best for step-by-step confidence.
- Session 1: AI basics — what it is and how to think about it
- Session 2: Prompting — how to ask for what you actually need
- Session 3: Daily work use cases — email, docs, research
- Session 4: Building repeatable workflows
- Session 5: Safety, review, and what to do next
Got a “could you build this?” idea?
Tell me what you wish your website or workday could do. A rough idea is enough. I’ll help you figure out what’s possible and where to start.