Original title: how non-developers automate work like engineers (without writing code)…
Original author: Damian Player
Compiled by: Peggy, BlockBeats

Editor’s note: While most people still view AI as a “more efficient search tool,” Perplexity is starting to put work into action.

This article centers on a repeatedly overlooked distinction—why, with the same use of AI, some people only get an answer, while others immediately receive deliverables they can turn in. The key isn’t model capability; it’s how you use it: whether you treat it as a conversation window, or as an execution system that can be commanded 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. Combined with the ability to connect enterprise tools and to lock in personal context and style examples, 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 one step; it can run continuously, execute across tools, and even proactively propose additional tasks. This means the relationship between people and tools is shifting from “using” to “managing and delegating.”

In this shift, the real dividing line is no longer whether you use AI, but 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 everything becomes obvious, here’s a way you can start early.

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

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

Most people open Perplexity, type a question, get an answer, and then close the page. They’re missing the crucial part. Perplexity Computer isn’t for answering questions—it’s for executing tasks.

Stop asking questions and start handing over the real work.

Why most people fail

CFOs, lawyers, consultants… They open the tool, type in a question, get a decent answer, and think: “Oh, a more advanced Google.” Then they spend another 90 minutes cleaning up the same spreadsheet they already cleaned last Monday.

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

Question-style prompt: “What risks are in this contract?”

Task-style prompt: “Review this contract. Check every statement for publicly available sources; flag vague wording, missing clauses, and parts that could lead to legal liability; list the five most critical risk points with specific clause citations; output a Word document with tracked changes.”

The 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.

Set up this system in just 10 minutes

First, connect the tool. Click connectors in the sidebar. Perplexity can connect 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 kind of company. I regularly produce content X, Y, Z. Please remember this background in every session.” It will keep those details long-term.

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

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

10 minutes—do this first.

A real example: that Monday that no longer costs 90 minutes

Every Monday, a financial analyst receives a data export—150 rows—with a messy format: duplicate data, three different date formats, and ratings written as words instead of numbers. Before she can start analyzing, she spends 90 minutes cleaning the data every week. The same issue, repeated every week.

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

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

Then she asked one more question: “Are there any improvements I haven’t asked for, but that would make this even more useful?”

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

She set both, then closed the page.

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

This is the same 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 gave it only one task: identify the companies running ads on competitor podcasts, find the actual sponsors responsible, 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 ago, wrote a cold email quoting his specific statements from the show, and sent it directly. Greg didn’t say “send”—the system judged the task complete and executed it on its own.

Then it proactively suggested: monitor competitor podcasts—once a new brand starts running ads, immediately notify and include the corresponding contact. “Contact them when the budget just starts.”

In the end, this workflow completed research in parallel 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 issues against custom criteria, rank them, and generate a shareable website report. What would normally take the team a week was completed while recording the episode.

All of this was done live, not as a demo, and not from a pre-scripted workflow.

How to use it for specific work

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

The result: a real-time interactive dashboard including $130.5B in revenue, a 75% gross margin, a 114.2% growth rate, a full income statement, and a profit margin trend forecast from fiscal year 2021 to 2028—all with filtering and shareable link support.

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

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

Legal scenario:
“Review this contract. Check every statement one by one to see whether it’s supported by publicly available sources; flag vague wording, missing standard clauses, and parts that could create legal liability under [specific state] contract law; list the five most critical risk points and include specific clause citations; output a Word document with tracked changes.”

A reviewer had uploaded a proposal claiming that the market year-over-year growth was 43%. Perplexity Computer found the true data was only 4% and stopped the problem before signing.

Marketing scenario:
“Analyze [competitor 1], [competitor 2], [competitor 3]’s best-performing content over the past 30 days; identify the content formats and topics 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 competitive analysis—no manual research required.

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

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

Model Council: three judgments in 60 seconds

When you face a decision with real consequences, you only need to ask once. Perplexity will simultaneously call Claude, ChatGPT, and Gemini, and a “synthesizer” will summarize their consensus and disagreements.

· Areas where all three agree: high-confidence conclusions

· Areas where there’s disagreement: 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 made.

Many companies pay consulting firms to put analysts in a meeting room to reach a conclusion.

Here, you only need one instruction.

The truly core capability

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

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

After each task is done, remember to ask one more question: “Are there any places you can improve this result that I haven’t asked for?”

It points out blind spots almost every time. And it uses them every time.

Start here

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

Input 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 and whose outputs are similar every time: describe it in terms of the “final deliverable,” send it. Observe the execution process. If it’s a repetitive 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 everyone else’s is real.

This is how to close the gap.

[Original link]

Click to learn about Law Rhythm (律动) BlockBeats hiring

Welcome to join the Law Rhythm BlockBeats official community:

Telegram subscription group: https://t.me/theblockbeats

Telegram group chat: https://t.me/BlockBeats_App

Twitter official account: https://twitter.com/BlockBeatsAsia