DEV Community: Abdullah Huseynli

Why we designed PotenAI's output as a roadmap, not a report

Abdullah Huseynli — Fri, 31 Jul 2026 22:06:06 +0000

Most assessment tools treat the report as the finish line. Score the user, generate a summary, done. We built PotenAI differently on purpose.

After the structured assessment, our AI doesn't just output a description of the user's strengths — it generates a roadmap: a sequence of concrete, specific next steps tied to that person's actual results. Technically, this meant treating the AI output less like a text-generation problem and more like a planning/recommendation problem — the model has to reason from "here's what this person is strong at" to "here's a realistic, ordered sequence of actions," which is a meaningfully different generation target than a descriptive paragraph.

We're still refining the scoring and roadmap-generation layer, and would love input from anyone who's worked on recommendation systems, structured LLM output, or planning-style generation.

Bootstrapped, pre-launch, building in public. Waitlist is open — join now to get early access the moment we launch.

🌐 nopick.site

📝 Medium

A career report that tells you who you are isn't enough — we learned this the hard way

When we started building PotenAI, the plan was simple: replace static personality quizzes with something smarter — a structured assessment, analyzed by AI, that actually understands a person's strengths.

But early feedback taught us something we hadn't fully accounted for: knowing your strengths doesn't automatically tell you what to do with them. A report that ends at "here's who you are" is still just a more sophisticated version of the same dead end every other test leaves people at.

So we added what we now consider the core of the product: after the assessment, PotenAI generates a personalized roadmap — real, actionable next steps for education, career direction, or entrepreneurship, built directly from that person's results.

We're building PotenAI in public, bootstrapped, still shaping this based on real feedback from real people facing this decision. If you've ever finished a personality test and thought "okay, cool, now what?" — this is for you.

Join the waitlist now, and you'll be the first to know the moment PotenAI launches.

🌐 nopick.site

Why we chose "structured assessment + AI analysis" over a chatbot for PotenAI

Abdullah Huseynli — Sat, 25 Jul 2026 19:44:39 +0000

When we started building PotenAI, the obvious move seemed like a chatbot — user talks to an AI, AI figures out their career fit through conversation. We actually prototyped this direction early on.

We moved away from it. Here's why.

Open-ended conversation is hard to keep focused, and it's even harder to turn into a consistent, comparable output. Two users answering the same underlying questions in a free-form chat can produce wildly different signal quality — one gives you three paragraphs, another gives you "idk, I like people I guess." That's not a great foundation for something we want to be reliable enough for a real career decision.

So instead, PotenAI is built around a structured assessment: a defined set of questions designed to extract specific signal about strengths, work style, and motivations. The AI's job isn't to conduct a conversation — it's to analyze the structured response data and generate a personalized roadmap: concrete next steps for education, career direction, or entrepreneurship. Structure in, intelligence in the analysis layer, personalization in the output.

The technical challenge that's kept us busy: making the analysis feel genuinely personalized rather than templated. It's easy to build a scoring system that buckets people into 8 categories. It's harder to build one that produces output specific enough that two different users with similar-but-not-identical answers get meaningfully different roadmaps.

We're early — two founders, bootstrapped, building in public. Would love thoughts from anyone who's worked on structured data extraction, recommendation systems, or AI products that need to feel personal without becoming unpredictable.

Following along or curious about early access? → nopick.site

Why we're building PotenAI with adaptive AI instead of static assessments

Abdullah Huseynli — Thu, 23 Jul 2026 20:50:21 +0000

Most career/personality tools follow the same pattern: fixed questions → fixed scoring → fixed report. It's efficient to build, but it treats every user like they fit into 16 boxes.

We wanted something closer to how a good mentor actually works — asking follow-up questions based on what you just said, probing deeper on ambiguous answers, adjusting the whole assessment path in real time.

So we're building PotenAI on adaptive AI conversations instead of static forms. The technical challenge has been fascinating: keeping the conversation focused, avoiding generic LLM output, and turning open-ended answers into structured, comparable insights.

We're still early and would love thoughts from other builders — especially anyone who's worked on structured extraction from open-ended conversation, or AI products in the assessment/EdTech space.

Following along or want early access? → nopick.site

Building an AI Product That Starts With Questions

Abdullah Huseynli — Wed, 22 Jul 2026 20:53:58 +0000

Many AI products focus on generating answers.

We're building one that starts by asking better questions.

Every response becomes part of a broader analysis designed to help users understand their strengths, work style, career compatibility, and development opportunities.

Why Static Personality Tests Aren't Enough

Abdullah Huseynli — Wed, 22 Jul 2026 20:53:38 +0000

Most assessments end with a label.

But labels don't help someone decide what to study, where to work, or whether to start a company.

We're exploring a different approach with PotenAI.

Instead of assigning personality types, AI analyzes structured user responses to generate practical, personalized career insights.

Building an AI Product That Starts With Questions

Abdullah Huseynli — Sun, 19 Jul 2026 23:40:55 +0000

Many AI products focus on generating answers.

We're building one that starts by asking better questions.

Every response becomes part of a broader analysis designed to help users understand their strengths, work style, career compatibility, and development opportunities.

The Biggest Career Problem Isn't Lack of Opportunity

Abdullah Huseynli — Sat, 18 Jul 2026 22:47:59 +0000

It's lack of clarity.

People spend years wondering:

What am I actually good at?
Which career fits me?
Should I start a business?
Which skills should I develop?

We're exploring whether AI can help answer those questions through personalized analysis instead of generic advice.

That's what we're building with PotenAI.

We're Building AI That Starts With Questions, Not Answers

Abdullah Huseynli — Sat, 18 Jul 2026 22:47:32 +0000

Large language models are great at generating text.

But understanding people requires asking the right questions first.

That's the philosophy behind PotenAI.

Users complete a structured assessment, and AI analyzes their responses to identify patterns that may reveal strengths, work preferences, career compatibility, and development opportunities.

We're still validating the idea and would love to hear feedback from the developer community.

Why Most Career Tests Fail to Help People Make Better Decisions

Abdullah Huseynli — Sat, 18 Jul 2026 22:43:10 +0000

Most career assessments tell you who you are.

Very few help you decide what to do next.

That difference matters.

While building PotenAI, we've been asking ourselves one question:

How can AI move beyond labels and provide practical, personalized recommendations based on someone's actual responses?

Instead of generating another personality report, we're exploring ways to connect strengths, work preferences, and decision-making patterns to concrete career suggestions.

What would make you actually trust an AI-generated recommendation?

Why Static Personality Tests Aren't Enough Anymore

Abdullah Huseynli — Fri, 17 Jul 2026 19:13:06 +0000

People change.

Skills evolve.

Interests grow.

Yet most personality and career assessments remain static.

We're exploring a different approach with PotenAI—using AI to create personalized conversations that help users better understand their strengths and career direction over time.

The first version is currently under development.

Join our early access community:

https://nopick.site

We're Building AI That Helps People Understand Their Career Direction

Abdullah Huseynli — Fri, 17 Jul 2026 19:08:10 +0000

AI is transforming almost every industry.

But one question keeps coming back:

Can AI help people make better career decisions?

At PotenAI, we're exploring exactly that.

Our goal is to help users better understand:

their strengths
career fit
hidden talents
long-term growth opportunities

We're building the first version and learning from every piece of feedback.

Early access is now open:

https://nopick.site

Why Finding Your Strengths Is Harder Than Learning New Skills

Abdullah Huseynli — Fri, 17 Jul 2026 19:07:17 +0000

Learning a new skill has never been easier.

Understanding what you're naturally good at is a different challenge.

Most career decisions are made with limited information about ourselves.

That's one of the reasons we're building PotenAI.

Instead of static personality tests, we're exploring how AI can help people identify their strengths, career compatibility, and growth opportunities through adaptive conversations.

The first version is currently in development.

If this idea resonates with you, we'd love to have you on our early access list:

https://nopick.site