If you treat ChatGPT like a search engine, you’ll get search-engine answers. If you treat it like a thinking partner with infinite patience, you’ll get a business advantage.
This is the foundation lesson. Every other course in the school builds on what’s here.
What ChatGPT actually is
ChatGPT is a large language model — a system that predicts the next word given the previous words. The magic isn’t intelligence in the human sense; it’s pattern-matching at unprecedented scale. It has read more than any human ever will. It knows how arguments are structured, how documents flow, how decisions get made.
What it cannot do is want anything. That’s your job. You bring intent. It brings execution at the speed of typing.
The three layers of every prompt
Every prompt that works has three things, in this order:
- Role — who is the model being right now?
- Context — what does it need to know?
- Task — what specifically do you want?
Most people skip 1 and 2. They write “write me a blog post about AI” and get sludge. Now compare:
You are the founding marketer at a B2B SaaS startup. Your audience is busy CTOs who skim. We sell observability tooling and our differentiator is a 5-minute setup. Write a 600-word blog post titled “Why your incident response is broken (and how to fix it in 5 minutes)” — opening with a story, ending with a CTA to a free trial.
That prompt produces output you’d actually publish.
Context windows: what fits in the room
A context window is everything the model can “see” at once — your prompt, your attached files, its own response so far. Modern models hold 100k–2M tokens (roughly 75k–1.5M words). That means you can paste:
- A full investor deck
- All your customer call transcripts from last month
- Your entire pricing page
- A competitor’s blog archive
…and ask synthesis questions across all of it. This is the unfair advantage. Most people still think in chat-bubble interactions. Power users build context-rich prompts that no employee could match in speed.
The five workflows that compound
Once you understand the three-layer prompt and context windows, every business workflow becomes a variation:
1. The synthesizer
Paste a pile of unstructured input (calls, emails, reviews). Ask: “What patterns appear three or more times? What’s the most surprising thing here?” Pure gold.
2. The first draft
Brief, target audience, constraints, output. The first draft is rarely the final draft — but it eliminates the blank page, which is where most projects die.
3. The reviewer
Paste your work. Ask it to attack like a hostile reviewer. “Find the three weakest claims in this argument and explain why a skeptical reader would push back.”
4. The translator
Same idea, three audiences. “Rewrite this for: an investor, a junior engineer, my mother.” Forces clarity.
5. The simulator
“You are my ideal customer. I’m going to pitch you. Push back on objections I haven’t anticipated.”
What you should do next
Pick one of the five workflows above. Try it on something real you’re working on today — not a toy example. Then come back and try a second one. By the end of the week, two of them will be in your daily routine.
The system you’re building is not “use ChatGPT more.” It’s replace specific cognitive tasks with AI-augmented versions of the same task, in a measurable workflow. That’s what every other lesson in the school builds toward.
Expanded operator notes for this AI workflow
The useful question is not whether the product has more features than the alternative. It is whether the product makes a repeated decision easier to make correctly. Start by writing the decision in plain language: who needs to act, what evidence they need, what can go wrong, and what a satisfactory result looks like. This short statement becomes the boundary for the workflow. It also gives you a way to stop adding features that do not improve the outcome.
A realistic baseline
Record the current process for ten representative cases. For each case, capture the starting signal, the time until a person begins work, the time spent, the number of corrections, and the final business result. Do not use only the fastest case or the most difficult case. A median and a range reveal whether the process is consistently slow or merely unpredictable. Both problems can be addressed, but they need different fixes.
Suppose a team handles 240 cases each month. Each case takes 18 minutes, and the loaded hourly cost is $42. The direct monthly labor estimate is 240 × 18 ÷ 60 × $42, or $3,024. If a tool costs $180 and saves 30% of the time while adding 90 minutes of review each week, the first estimate is about $725 of gross monthly capacity before quality effects. That is a hypothesis, not a promise. Confirm it by measuring real cases for at least two cycles.
The baseline should include quality. Count duplicate records, incorrect classifications, missed follow-ups, reversals, and customer complaints. A process that becomes faster but creates one expensive mistake can have negative value. When the cost of a mistake is unknown, use a conservative range and make the uncertainty visible to the person approving the project.
Design the handoff
Every handoff needs a sender, a receiver, a timestamp, and a definition of done. If the receiver cannot tell whether the item is ready, the workflow will create messages rather than progress. Add a short status vocabulary and use it everywhere: waiting for input, ready for review, approved, blocked, and complete are usually enough for a first version.
Keep the original input beside the transformed output. This is especially important when a system summarizes, classifies, enriches, or rewrites information. A reviewer should be able to compare the result with the source without searching through several applications. The comparison may add seconds to a routine case, but it makes errors easier to correct and training easier to improve.
Define an escalation threshold. For example, routine items can pass when all required fields are present and the confidence check is above the agreed level. Items with a missing field, an unusual value, or a sensitive attribute go to a named owner. The threshold should be written down rather than left as intuition, because written rules can be reviewed and improved.
Worked example with exceptions
Imagine that a team receives 60 requests each week. Forty-five are routine, ten need one clarification, and five involve a decision that must remain with a manager. A sensible first workflow handles the 45 routine requests, creates a clarification queue for the ten, and leaves the five manager cases untouched except for a reminder. It does not pretend that every request has the same risk.
After four weeks, the team should compare the three groups. If routine requests are completed 40% faster with no quality loss, keep that rule. If the clarification queue keeps growing, improve the intake form rather than adding more reminders. If managers receive too many false escalations, adjust the threshold with examples from real cases. This approach treats exceptions as information about the process, not as evidence that the users failed.
Write down one example of a correct automatic result, one example that needs review, and one example that must stop. These examples are more useful in training than a long list of abstract rules. Review them whenever the audience, product, policy, or data source changes.
Security and continuity
Apply the smallest useful permission set. A reporting workflow rarely needs the ability to delete customer records, and a reminder workflow rarely needs full access to every project. Separate read, write, and administrative permissions where the product allows it. Review access when a person changes role and at least once per quarter for a critical system.
List the data that leaves the primary system. Include copied fields, generated text, attachments, identifiers, and logs. Remove fields that are not needed. If a vendor retention policy is unclear, do not use sensitive production data during the pilot. A clean test dataset makes the experiment slower at first but reduces the cost of an unexpected disclosure.
Prepare a manual fallback that can run for one working day. It should name the queue, the owner, the temporary form, and the reconciliation step used when the system returns. Test it at a quiet time. Recovery plans that exist only in a document are often missing a permission, an export, or a person who knows how to run them.
Review the economics after launch
At day 30, compare actual usage with the adoption assumption. At day 60, compare cycle time and correction rate with the baseline. At day 90, compare the business measure and the full cost, including review and maintenance. Keep a note about what changed outside the workflow, such as seasonality, staffing, or a new offer. That context prevents the team from assigning every movement to the tool.
Use a stop rule. If the workflow has low adoption, no measurable quality improvement, or more maintenance than the team can support, pause it and investigate. Removing a weak workflow protects attention for a stronger one. A successful operating model contains both launches and retirements.
Finally, share the result with the people who do the work. Show the baseline, the current measure, the remaining exceptions, and the next decision. People adopt systems they can understand. A short, honest review builds more trust than a celebration based only on the number of tasks processed.
Expanded FAQ
What is the best first metric? Start with the delay or effort that motivated the project, then pair it with quality. Cycle time alone can reward rushed work; quality alone can hide a process that nobody can sustain. A paired metric shows the trade-off.
Should every exception be automated later? No. Some exceptions are valuable precisely because they receive attention. Automate a case only after you understand why it is exceptional, how often it occurs, and what the consequence of a wrong decision would be.
How much documentation is enough? Enough for a trained colleague to explain the trigger, input, output, owner, failure path, and rollback without the original builder. A one-page procedure plus a short decision log is often sufficient for a small workflow.
What if the team cannot agree on the baseline? Stop and resolve the measurement definition before buying more software. Different definitions of “complete” or “qualified” will create apparent disagreement that no dashboard can fix.
When should the workflow be reviewed? Review weekly during the pilot, monthly for the first quarter, and quarterly after it is stable. Trigger an extra review after a major data-source, policy, staffing, or audience change.
How should a leader communicate the change? Explain the problem, the boundary, the human role, the expected benefit, and the way to report an error. Avoid claiming that the system is perfect. People are more willing to use a tool that has an honest correction path.
This expansion is designed to be used with the main guide above. Apply the same discipline to the next workflow: define the decision, measure the baseline, keep the exception path visible, and review the business result before expanding scope.