The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Not Every Problem Needs an AI Agent
AI agents are what everyone wants to build right now. Sometimes that's the right call. But a lot of the time, a plain background job would do the same work cheaper, faster and more reliably, with nothing to hallucinate.
Before I build anything, I ask two questions:
Does the task follow the same rules every time?
If yes, it's automation, not AI. Keeping inventory in sync across Amazon and eBay (what I built for Packit), sending invoices, generating reports. A background job does it the same way every time, and you can test it.
Is a mistake expensive?
If the input is messy (emails, calls, documents, free text), that's where an AI agent earns its place. Reading a support email and routing it. Understanding what a caller wants, like the voice automation platform I built for a company in Germany.
And if a wrong answer costs money or a customer, I put a human in the loop: the agent does the work and drafts the action, and a person approves refunds, price changes or anything customer-facing.
Most good products end up using all three: automation for the predictable parts, AI where the input is messy, and a human where mistakes are expensive.
Not sure which one your idea needs? Book a free build audit: calendly.com/roshaanali-business
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
I built Tests Wise: paste a URL, get a test plan and watch AI run the tests live.
Most small teams ship without a written test plan. Not because they don't care because writing one takes a day nobody has. And running it takes another.
Tests Wise does both:
Paste your site's URL (works with sites behind a login).
AI agents explore up to 8 pages in a real browser and figure out what each one does.
You get prioritized test scenarios steps, expected results, priority as an Excel your QA team or client can use right away. In English or Spanish.
Then an AI agent executes those scenarios live in a real browser, driven through Playwright MCP, and reports what passed, what failed and why, with a screenshot of each step.
Everything is automated software: no scripts, no selectors, no CI to wire up.
Under the hood: FastAPI + PostgreSQL, Redis/RQ workers, Playwright for the crawl, Claude for scenario design and for driving the browser via Playwright MCP, LangGraph for the pipeline. Deterministic exploration, LLM only where it adds value — a full run on an 8-page site costs a few cents.
It's free to try, no card needed: https://app.tests-wise.com/
Demo below 👇 I'd love to hear which site you'd throw at it first.
A screenshot per step is a smart touch, makes failures easy to show a client. How long does a full run take for 8 pages?
Design and development are getting easier with AI.
But the real difference is how you guide it.
Give AI the right direction, references, and clear instructions, and you can turn your ideas into reality much faster.
AI does the heavy lifting. Your vision makes it special.
What do you think? 👇
#AI #WebDesign #WebDevelopment #ClaudeAI
Nice work!
42% of failed startups built something nobody needed.
That is from one CB Insights analysis of 101 founder post-mortems.
Not bad code. Not bad luck. Nobody needed it.
If you are building an AI product...this is the cheapest fix you will ever make...
Ask these 5 questions BEFORE you build...
1. Who exactly has this problem?
Everyone is not an answer. Name a job title.
2. How are they solving it today?
If they are not solving it at all, it may not hurt enough.
3. What does it cost them?
Hours, money or missed deals. Get a number.
4. Would they pay for a fix this month?
Ask for a pre-order or a pilot, not a compliment.
5. Who have you talked to this week?
Aim for 5 real conversations before writing a line of code.
Copy-paste prompt to prepare your interviews:
I am building [product] for [job title]. Write 10 customer interview questions that uncover how they solve [problem] today, what it costs them, and what they have already paid for. No leading questions.
Compliments do not validate a product.
Payments and pilots do.
Save this before your next build sprint.
Follow me to meet again
Daily learn with me (Maryam Tehsin)
Such an important reminder! 👏 It's easy to focus on building a product, but understanding the customer's real problem should always come first. Real feedback is worth more than compliments!