How to Use AI to Take Over Your Workflow (No Coding Required)

Author: Damian Player; Compiled by: Peggy, BlockBeats

Editor’s Note: While most people still see AI as a “more efficient search tool,” Perplexity is starting to put it to work.

This article focuses on a repeatedly overlooked difference—why, when using the same kind of AI, some people only get an answer, while others directly receive deliverables they can act on. The key isn’t model capability; it’s how you use it: do you treat it like a chat window, or like an execution system that can be directed and scheduled?

A new class of tools represented by Perplexity Computer replaces “asking” with “tasks” as the core interaction. From contract review and competitive analysis to data cleaning and report generation, users no longer describe the problem—they directly define the final deliverable. Coupled with connections to enterprise tools, and with personal background and style examples being solidified, this capability evolves from one-off outputs into reusable, automatically runnable workflows.

More importantly, the boundaries of automation are being redefined. It’s no longer just about helping you complete a step; it can run continuously, execute across tools, and even proactively propose additional tasks. This means the relationship between humans and tools is shifting from “using” to “managing and delegating.”

In this shift, the real dividing line isn’t whether you use AI—it’s whether you’ve started using it to “deliver results.”

Below is the original text:

People who figure this out will gain an asymmetric advantage. Soon, everyone will learn how to do it. But before it all becomes obvious, here’s a way you can start early.

Over the past year, developers have already been running autonomous AI agents in the background (such as Claude Code, OpenClaw, etc.). They can do their own research, build products, and deliver complete outputs without having humans constantly watch over them or repeatedly prompt them back and forth. But you’ve probably never been able to use this—unless you know how to use a terminal and write code.

And Perplexity Computer changes that. For the first time, non-developers can use the same capabilities. All you need is a browser and a task you can give it to complete.

Most people open Perplexity, type in a question, get an answer, and then close the page. They miss the key point. Perplexity Computer isn’t for answering questions—it’s for executing tasks.

Stop asking questions. Start handing the real work over to it.

Why most people fail

CFOs, lawyers, consulting advisors… They open the tool, enter a question, get a decent answer, and then think, “Oh, an upgraded Google.” Then they spend another 90 minutes cleaning the spreadsheet they cleaned last Monday.

The problem isn’t the tool—it’s the way they use it. They treat it like a chatbot.

Question style: “What risks does this contract have?”

Task style: “Review this contract. Check every statement one by one to confirm whether all assertions have public sources to support them; flag any ambiguous wording, missing clauses, and parts that could create legal liability; list the 5 most critical risk points and include specific clause citations; output a Word document with tracked revision marks.”

Same contract. One approach gives you a checklist so you have to read it yourself; the other gives you a finished product you can send to your client.

Just build this system in 10 minutes

First, connect the tool. Click connectors in the sidebar. Perplexity can connect to 400+ applications: Gmail, Google Drive, Slack, Salesforce, Notion, SharePoint… Connect whatever you actually use.

Then let it know who you are. Enter it once: “I’m in a certain role at a certain type of company. I regularly produce X, Y, and Z content. Please remember these background details in every conversation.” It will keep this information over the long term.

Next, tell it what “good” looks like. Find 2–3 deliverables you’re most satisfied with, upload them, and input: “These are my best work samples. Please learn their format and tone; use them as reference when generating content going forward.”

That way, it isn’t guessing your style—it’s reverse-deconstructing the successful path you’ve already validated.

10 minutes. Start with this one task.

A real example: that Monday that doesn’t consume 90 minutes anymore

A financial analyst receives a data export every Monday—150 rows, messy formatting: duplicate data, three different date formats, and ratings written as words instead of numbers. Before she can analyze it, she spends 90 minutes every week cleaning the data. Same question, repeating every week.

She gave it one instruction: clean this file, remove duplicates, standardize the date format, convert textual ratings into numbers; analyze the cleaned data; generate an interactive dashboard with filtering features and provide a share link; output a PDF report comparing before and after cleaning; save all files to the “Monday Reports” folder in Drive.

After 4 minutes: a clean dataset, an interactive dashboard, a share link, a PDF report—everything appears in her Drive.

Then she asked one more question: “Are there improvements I haven’t asked about that could make this even more useful?”

The system suggested two things: first, set the task to automatically run every Monday at 7:00 AM; second, add a task to generate Tuesday management briefings based on the underperforming segments.

She set both, and closed the page.

After that, every Monday it runs automatically—whether her computer is on or not.

This is the capability developers have been using over the past year. Now, you can use it in your browser.

What people are already using it for

@gregisenberg did a live test on the @startupideaspod podcast.

He only gave it one task: identify the companies that run ads on a competitor podcast, determine the true people responsible for sponsorship, and write a personalized email to each person.

The system found Ramp’s Vice President of Growth, pulled the podcast episode he participated in two weeks earlier, wrote a cold email referencing his specific comments from the show, and sent it directly. Greg didn’t say “send.” The system judged that the task was completed and executed it on its own.

Then it proactively suggested: monitor the competitor’s podcast; as soon as a new brand starts running ads, immediately notify and attach the corresponding contacts—“contact them when the budget is just starting.”

Ultimately, this process in parallel completed research for 96 potential customers and scheduled follow-up emails for Day 3 and Day 7.

On the Marketing Against the Grain show, the team used it to audit the entire HubSpot product pages: automatically crawl the whole site, score using custom standards, sort issues, and generate a shareable website report. What would have taken a team a week was completed while recording the episode.

These were all done live—not a demo, not a pre-script.

How to use it for specific work

In the finance domain, a portfolio analyst gave just one task before Nvidia’s earnings release.

The output was: a real-time interactive dashboard including $130.5B in revenue, a 75% gross margin, a 114.2% growth rate, a complete income statement, and a profit margin trend forecast from fiscal year 2021 to 2028—fully supporting filtering and share links.

No Excel, no manually hunting for data—done in 5 minutes.

Perplexity can directly call data sources like SEC filings, FactSet, S&P Global, PitchBook, and more—no API key and no extra authorization needed; it’s built into the system.

Legal scenarios:
“Review this contract. Check every statement to see whether it’s supported by public sources; flag ambiguous wording, missing standard clauses, and parts that could lead to legal liability under [specific state] contract law; list the 5 most critical risk points and include specific clause citations; output a Word document with tracked revision marks.”

A reviewer once uploaded a proposal claiming that the company’s market同比 growth was 43%. Perplexity Computer found the real figure was only 4% and stopped the issue before the contract was signed.

Marketing scenarios:
“Analyze [Competitor 1], [Competitor 2], and [Competitor 3]’s top-performing content over the past 30 days; find the content formats and themes with the highest engagement; identify content gaps; generate a 30-day content calendar based on these gaps and save it as a Google Doc.”

Set it as a scheduled task. Every Monday, it automatically generates the latest competitor analysis—no manual research required.

Operations scenarios:
“This is our Q1 CSV data. Please clean the data; analyze revenue by region and product line; identify the three biggest issues; generate one-page action recommendations; create a one-page PPT for the briefing; save all files to the project folder.”

Five deliverables, one instruction. When you’re in the meeting, it has already finished.

Model Council (Model Council): Get three judgments in 60 seconds

When you face a decision with real consequences, just input one question. Perplexity will call Claude, ChatGPT, and Gemini at the same time, and a “synthesizer” will summarize their consensus and differences.

· Parts where all three agree: high-confidence conclusions
· Parts with disagreements: need further judgment

Someone asked whether product pricing should be $297 or $497. The three models gave different answers, but the synthesizer found their only shared conclusion was: don’t go below $297. The decision is done.

Many companies pay consulting firms to lock analysts in a meeting room to reach conclusions.

Here, you only need one instruction.

The real core capability

To get practical value from Perplexity Computer, 80% depends on one thing: whether you can clearly describe the “final output.”

Not the technical setup. It’s whether you’re clear enough about what you need to deliver. Don’t describe the steps—describe the result.

After each task is completed, remember to ask one more thing: “Is there anything I haven’t asked that could make this outcome more useful?”

It points out blind spots almost every time. You use it every time.

From here

Open Perplexity (Pro plan $20/month). Go to the Computer page, click connectors, and first connect Gmail and Google Drive.

Enter your three-sentence background introduction (just once). Upload 2–3 of your best work samples so it can learn your style. Then choose a task you spent more than 2 hours on last week, where every output is similar each time: describe it using the “final deliverable” approach, then send it. Observe the execution process. If it’s a repeatable task, set it to run automatically before closing the page.

Developers have been using this setup for a year. The gap between their output and other people’s is real.

That’s the method for closing the gap.