By Cheval John | Vallano Media
This article was created with the assistance of artificial intelligence.
The final version was reviewed, edited and fact-checked by the author

Graphics created with AI-assisted design tools.
Visual concepts, editorial direction, composition, and final creative decisions were developed by Vallano Media.

For most of my career, writing meant doing nearly everything myself.

Research the story.

Find the sources.

Take the notes.

Organize the information.

Write the draft.

Rewrite the draft.

Check the facts.

Edit the copy.

Come up with the headline.

Prepare the article for publication.

Then start all over again with the next story.

That process was familiar because it was the way I had always worked.

It was also exhausting.

Journalists often wear several hats, especially when they work independently or in smaller organizations.

A reporter may also become the researcher, editor, publisher, social-media producer and, depending on the project, even the person creating graphics.

For a long time, I simply accepted that as part of the job.

Then artificial intelligence changed the way I thought about the work.

Not because AI could suddenly do everything for me.

It could not.

What changed was that I began to realize I no longer had to perform every part of the process in exactly the same way.

I could direct the workflow.

That was a much bigger change than simply learning how to use a chatbot.

The First Stage: Asking Questions

My early use of artificial intelligence was not sophisticated.

Like many people, I started by asking questions.

I treated AI almost like a conversational search tool.

Ask something.

Get an answer.

Ask another question.

Move on.

There was nothing particularly strategic about it.

At that point, I was using AI.

I was not yet working with AI.

That distinction would become important.

The real change began when I stopped thinking only about individual questions and started thinking about the entire process.

What happens before I write?

What happens after I write?

Where do mistakes usually occur?

Which parts take the most time?

Which parts require judgment?

Which parts are repetitive?

Which parts could benefit from another set of eyes?

Once I began thinking that way, AI stopped being only a question-and-answer tool and started becoming part of a workflow.

The Work Did Not Disappear

It is easy to describe AI as a labor-saving technology.

Sometimes it is.

But that description can be misleading.

The work did not disappear.

The work changed.

Instead of spending all of my time manually performing every task, I increasingly spent time deciding what needed to happen, what AI could assist with and what still required my direct attention.

That sounds subtle.

It is not.

Consider research.

A traditional workflow might involve opening a series of tabs, reading articles, taking notes and trying to identify connections manually.

An AI-assisted workflow might help organize documents, compare information or identify questions more quickly.

But somebody still has to decide which sources are trustworthy.

Somebody still has to notice when important context is missing.

Somebody still has to recognize when two sources appear to contradict each other.

And somebody still has to decide what belongs in the final story.

That person is still me.

AI can reduce some forms of manual work while creating another responsibility: supervision.

From Doing Everything to Directing the Workflow

This is the part I did not understand when I first started using AI.

I thought the main benefit would be speed.

Write faster.

Research faster.

Edit faster.

Those benefits are real.

But the deeper change has been learning how to direct the work.

The shift was not from working to supervising.

It was from performing every task manually to deciding which tasks I should still perform, which AI could assist with and where human approval had to remain.

One workflow may be focused on research.

Another may challenge the argument.

Another may examine factual claims.

Another may help transform a completed article into a different format.

Another may help evaluate whether the final product still sounds like me.

Some of those workflows are simple and manually triggered.

Others are more structured.

Not every useful AI workflow needs to be autonomous.

The point is not to remove the human from the process.

The point is to build a process where the human knows when to step in.

I Did Not Start With a Master Plan

The strange part is that this happened gradually.

I did not sit down one morning and announce that I was going to build a collection of AI-assisted workflows.

Much of it came from trial and error.

I encountered a problem.

I tried something.

Sometimes it worked.

Sometimes it did not.

I needed a better way to verify information.

A workflow developed.

I needed a way to challenge weak arguments.

Another workflow developed.

I needed to repurpose an article without losing its meaning.

Another process emerged.

Some workflows worked immediately.

Others had to be changed.

Some became more useful after repeated use.

Some probably were not worth keeping.

Over time, those individual solutions began to form a system.

That is when I started realizing that I was no longer simply using AI.

I was designing ways to work with it.

The Journalist Becomes the Editor of the Output

Traditional journalism has always involved editing.

The difference now is that the journalist may also have to edit what the machine produces.

That means more than correcting grammar.

It means questioning assumptions.

Rejecting weak suggestions.

Checking sources.

Restructuring an answer.

Recognizing when the system has misunderstood the assignment.

Sometimes the most important thing I do is tell the AI:

No.

That is wrong.

That is unsupported.

That does not sound like me.

That is not the question I asked.

Try again.

Those moments matter because they reveal something that gets lost when AI is described as automatic.

The process is often interactive.

The final result may emerge from several rounds of challenge, correction and refinement.

That makes the human role different from traditional writing, but not less important.

In some situations, it can become more demanding because the journalist must supervise both the journalism and the AI-assisted process.

Direction Requires Knowing What Good Looks Like

There is another problem with telling people to simply “use AI.”

You have to know what you are trying to produce.

AI cannot compensate for having no standards.

If I do not know what a strong news story looks like, I cannot reliably judge whether AI has helped create one.

If I do not understand verification, I may not recognize an unsupported claim.

If I do not understand my own voice, I may allow AI to replace it with generic language.

Delegation only works if the journalist still understands the task well enough to judge the result.

That matters because over-delegation carries its own risk.

If journalists stop practicing the underlying skills of research, verification, writing and editing, they may become less capable of recognizing when AI has produced weak work.

AI can increase capability.

It does not automatically provide judgment.

The better I understand journalism, the better I can direct AI inside a journalistic workflow.

A Different Kind of Productivity

Before I began using AI seriously, productivity often meant working harder or working longer.

There were only so many hours available.

If an article took three hours, producing another article often meant finding another three hours.

AI changes that equation, but not as simply as the hype sometimes suggests.

The goal is not to produce as much content as possible.

The goal is to use saved time intelligently.

The most useful question is not:

“How much faster can AI make me?”

It is:

“What should I do with the time AI gives back?”

If AI helps reduce the mechanical parts of a task, I can spend more time checking the work.

I can challenge the argument.

I can examine another source.

I can rethink the headline.

I can decide that a story is not ready.

That is a much healthier definition of productivity than simply publishing more.

Speed only matters if the quality survives.

When the Workflow Fails

Directing AI-assisted work also means accepting that the workflow will sometimes fail.

AI may misunderstand the task.

It may give me information that looks useful but is not.

It may repeat itself.

It may introduce language that sounds polished but weakens the point.

It may send research in the wrong direction.

Those moments are not exceptions to the process.

They are part of the process.

The important questions are simple:

Did I catch the problem?

Do I understand why it happened?

Do I need to change the workflow?

That is how the system improves.

Not because AI becomes perfect.

Because the human process around it becomes better.

Building the System While Using It

One of the unusual things about my experience is that I built many of these workflows before I knew what to call them.

I was solving problems.

I was creating repeatable steps.

I was assigning specific roles to AI.

I was deciding where human approval had to remain.

Only later did I realize that what I had been building resembled structured AI workflows and, in some cases, agent-like systems.

Most of those systems were not fully autonomous.

They were usually manually triggered and specialized.

That distinction matters.

Not every useful AI workflow needs to operate independently.

Sometimes the value comes from building a repeatable process that helps the human work more consistently.

I had not learned the terminology first and then applied it.

I developed the practice first and learned the terminology afterward.

That may be one reason the systems felt natural.

They were built around real problems rather than abstract concepts.

The Managerial Shift

This change also affected how I thought about my role inside Vallano Media.

I was no longer simply writing articles.

I was increasingly managing a publishing system.

Research needed direction.

Verification needed standards.

Drafting needed oversight.

Graphics needed review.

Publishing needed coordination.

AI could assist with many of those functions, but I remained the person deciding how the pieces fit together.

That is where the shift from writer to director became clear.

The word “director” does not mean standing above the work.

It means coordinating it.

The work still has to be understood.

The standards still have to be maintained.

The final decision still has to be made.

But I no longer have to perform every task manually in order to remain in control.

What Other Journalists Can Learn From This

The lesson is not that every journalist needs dozens of workflows.

The lesson is simpler.

Start by examining the work you already do.

Where do you spend the most time?

Where do mistakes occur?

Which tasks are repetitive?

Which tasks require judgment?

Which tasks could be assisted without handing away editorial control?

Then test one small process.

Do not automate the entire newsroom.

Do not start with the highest-risk task.

Pick something manageable.

Maybe it is organizing notes.

Maybe it is generating questions to consider.

Maybe it is comparing two versions of a draft.

Maybe it is asking AI to challenge an argument before publication.

Then examine what happened.

Did it help?

Did it save time?

Did it introduce problems?

What still required human judgment?

That is how a workflow begins.

The Work Is Still Mine

AI has changed how I work.

It has not changed who is responsible for the work.

That was the lesson of Chapter 1.

Chapter 2 adds another layer.

Responsibility does not require doing everything manually.

Control does not mean refusing assistance.

The journalist can delegate parts of the process without delegating accountability.

That is the shift I am still learning to make.

From doing every task myself to directing a workflow.

From asking AI isolated questions to designing repeatable processes.

From thinking only like a writer to thinking more like an editor, manager and publisher.

The technology did not remove me from the process.

It changed where I add the most value.

And increasingly, that value comes from knowing what to direct, what to question, what to verify and when to say no.

Graphics created with AI-assisted design tools.
Visual concepts, editorial direction, composition, and final creative decisions were developed by Vallano Media.