DEV Community: Muhamad Kautsar

I Asked My AI Agent to Predict Every World Cup 2026 Match. Here's What Happened.

Muhamad Kautsar — Tue, 16 Jun 2026 06:11:29 +0000

The tournament started June 11. I had an AI agent running on my personal server. The obvious next step was obvious.

So I did it. I fed my AI agent — AkiraAI, which I built myself and runs 24/7 on my own server — live World Cup 2026 data and told it to predict every single group stage match. All 104 of them.

Some results were embarrassing. Some were eerily accurate. And one prediction genuinely made me stop and stare at my screen.

Here's the honest breakdown.

First, Why I Built My Own AI Agent in the First Place

AkiraAI isn't a wrapper around ChatGPT. It's a full agent I designed and deployed — web search, document generation, reminder systems, code management, the whole thing — running on a VPS I personally manage.

I built it because I got tired of switching between 12 different tools to get work done. One agent that actually does things, not just talks about them.

So when World Cup 2026 kicked off with 48 teams and 104 matches — the biggest tournament in FIFA history — it felt wrong not to put AkiraAI to work on it.

What I Actually Fed It

No, I didn't just ask "who wins the World Cup?" That gives you a generic answer every time.

Instead, I gave it:

Current FIFA rankings per team
Each team's qualifying form (last 10 matches)
Key injury reports as of June 11
Head-to-head records for each group stage matchup
Travel distance between matches (rest time matters more than people think)
Historical World Cup group stage patterns

Then I asked it to predict scorelines — not just win/draw/loss — for every group stage match.

The Results Were... Interesting

Where it was eerily accurate:

Iran vs. New Zealand. AkiraAI predicted a draw, 1-1. The real result: a tense draw with New Zealand's Elijah Just scoring twice and Iran equalizing through Mohammad Mohebbi. Not exactly 1-1, but the draw call with both teams scoring? Spot on.

Saudi Arabia in Group H. AkiraAI flagged them as an "upset candidate" based on their 2022 World Cup data where they beat Argentina. Sure enough, Abdulelah Al-Amri scored their first goal of the tournament against Uruguay.

Where it was completely wrong:

It underestimated Sweden badly. Viktor Gyokeres and Alexander Isak are in form that no historical dataset fully captures right now. AkiraAI had Sweden winning narrowly. They struck five. Five.

Haiti giving Italy a fright? It didn't see that coming at all. Neither did I, honestly.

The Part That Made Me Stop

After running all predictions, I asked AkiraAI a follow-up: "What's the single biggest variable you can't account for?"

Its answer: "Individual brilliance in high-pressure moments."

It explained that every model — no matter how much data you feed it — essentially averages out human performance. But World Cups aren't won by averages. They're won by a Messi at his peak, a Gyokeres who's unstoppable right now, a goalkeeper who has the game of his life.

That hit different. Because it's not just true for football. It's true for everything.

AI is extraordinarily good at seeing patterns. It's still terrible at predicting when someone breaks them.

What This Actually Taught Me About AI

Running this experiment for a week clarified something I'd been vague about:

AI prediction tools are confidence machines, not oracle machines.

They give you a probability with authority. That authority feels like certainty if you're not careful. Squawka's AI predictor, OddsFlow, ChatGPT bracket predictions — all of them produce clean, confident numbers. But football doesn't care about clean numbers.

The best way to use AI for this? Not as a predictor. As a filter.

Use it to quickly eliminate the 70% of matches that are genuinely predictable (heavy favorites vs. minnows). Then spend your actual thinking time on the 30% of matches where the model uncertainty is highest — those are the games that'll define the tournament.

Is Spain Actually Winning This?

ChatGPT says Spain. Most AI models say Spain. AkiraAI also leans Spain based on FIFA rankings, recent form, and their qualifying dominance.

Personally? I'm not so sure. France and Brazil are lurking. England has a realistic path. Argentina are the reigning champions and Lamine Yamal is 18 years old playing like he's been here before.

I'll let AkiraAI keep tracking as the knockout rounds approach. I'll share updates as results come in and predictions get tested against reality.

The Bottom Line

I built an AI agent. I pointed it at the World Cup. Here's what I actually learned:

AI is a brilliant analyst. It's a mediocre prophet.

The data it surfaced — travel schedules, rest patterns, head-to-head records — genuinely made me understand some matches better than I would have without it. But every time a Sweden striker is on fire, or Haiti pushes Italy to the edge, the model shrugs.

That gap between "pattern recognition" and "human unpredictability" is where football lives. It's also where the best AI research is happening right now.

I'll keep running the predictions. And I'll keep being wrong in interesting ways.

Follow along if you want to see how this plays out — I'll post updates as the knockout stage hits.

📖 Artikel ini pertama kali terbit di Medium: https://medium.com/p/5c5f573ecfbf/submission?redirectUrl=https%3A%2F%2Fmedium.com%2Fp%2F5c5f573ecfbf%2Fedit&submitType=publishing-post&postPublishedType=initial — ikuti saya di sana untuk tulisan lengkap lainnya.

I Built My Own AI Agent. Here's What Nobody Tells You.

Muhamad Kautsar — Tue, 16 Jun 2026 04:39:25 +0000

Most people talk about AI agents like they're magic. I built one. It's not magic — it's plumbing.

Six months ago, I started building AkiraAI — a personal AI agent running 24/7 on my own server. Not a chatbot. Not a wrapper around ChatGPT. An actual agent: one that reads my emails, publishes articles, manages my calendar, deploys code, monitors my server, and sends me reminders on Telegram.

And building it taught me things I couldn't have learned any other way.

Everyone Talks About Agents. Almost Nobody Builds Them.

There's a weird thing happening in tech right now. Everyone is talking about agentic AI. Blog posts, YouTube videos, LinkedIn threads — all explaining what AI agents are.

But almost nobody is actually building one from scratch and running it in production.

That's the gap I fell into. And it's a very educational place to fall.

Lesson 1: An Agent Without Tools Is Just a Fancy Chatbot

This sounds obvious. It isn't.

When I first set up AkiraAI, I connected it to Claude and felt proud. It could answer questions really well. Great conversations. Very impressive.

It was useless.

An agent becomes real the moment it can act — not just respond. The first tool I added was web search. Suddenly, AkiraAI could look things up in real time. Then I added Gmail access. Then Google Drive. Then shell execution on the server.

Each tool added wasn't just a feature. It changed the nature of what the agent could do. It started doing things I hadn't explicitly programmed. That's when it clicked: tools are the difference between a parrot and an assistant.

If you're building an agent right now and you haven't given it tools yet — you haven't really started.

Lesson 2: Memory Is Harder Than You Think

I assumed memory would be simple. Store conversation history, feed it back in. Done.

Wrong.

The real problem is what to remember and when. Feed in too much context and you hit token limits fast. Feed in too little and the agent feels amnesiac — every session starts fresh, no continuity.

I ended up building a layered approach:

Short-term: last few messages in the session
Long-term: a knowledge file with key facts about me, my projects, my preferences
Lessons learned: a running log of mistakes the agent made, so it doesn't repeat them

The lessons-learned file was the most valuable. There's something almost poetic about an AI agent that keeps a journal of its own failures.

Lesson 3: Production Is a Different Planet

Building the agent on my laptop and running it in production on a server are two completely different experiences.

On my laptop, everything worked. On the server, I hit issues I never anticipated:

RAM spikes when Puppeteer (headless Chrome) fired up to post articles on Medium
Timezone mismatches that broke reminders by exactly 7 hours
Crashed processes with no auto-restart
API rate limits I didn't know existed until I hit them at 2 AM

Every one of these was a real production failure. Every one of them taught me something a tutorial never would have.

The teams that build great agents aren't the ones with the best prompts. They're the ones who treat the agent like real production software — versioned, monitored, with fallbacks when things go wrong.

Lesson 4: The Guardrails Problem

Early on, I wanted AkiraAI to be as autonomous as possible. Minimal friction. Just do the thing.

That lasted about a week.

I came back one day to find the agent had tried to restart a service it shouldn't have touched. Nothing broke — but it was close. I added a confirmation step for any destructive shell commands after that.

The irony of building an autonomous agent is that you spend a lot of time thinking about when it shouldn't act autonomously. The smarter the agent, the more carefully you have to define its boundaries.

This isn't a limitation. It's good engineering.

Lesson 5: The Moment It Became Real

There's a specific moment when a project stops feeling like a project and starts feeling like infrastructure.

For AkiraAI, it was a Tuesday morning. I woke up, made coffee, and saw a Telegram message from the agent. It had already:

Checked my Gmail and flagged two emails that needed responses
Published a new article to Medium and Dev.to
Sent me a reminder about a meeting
Reported that server RAM was at 68%

I hadn't asked for any of it. It just... did it. While I was asleep.

That's when I understood what people mean when they talk about agentic AI. Not AI that responds to you. AI that works for you.

What I'd Tell Anyone Starting Today

Start smaller than you think you should. Pick one task. Build the agent to do that one thing well. Add tools one at a time. Watch what breaks.

Don't skip the boring parts — the monitoring, the error logging, the confirmation prompts. That's not overhead. That's the agent becoming reliable.

And most importantly: run it in production as early as possible. The gap between "works on my machine" and "works at 3 AM while I'm asleep" is where all the real learning happens.

Building AkiraAI is the most educational thing I've done in the last two years. Not because it's impressive — but because it forced me to understand, at a deep level, how these systems actually work.

Everyone should build one. Not to show off. To actually understand what you're talking about when you say "AI agent."

Because right now, most people don't.

📖 Artikel ini pertama kali terbit di Medium: https://medium.com/p/fcf8890807b0/submission?redirectUrl=https%3A%2F%2Fmedium.com%2Fp%2Ffcf8890807b0%2Fedit&submitType=publishing-post&postPublishedType=initial — ikuti saya di sana untuk tulisan lengkap lainnya.

Stop Using AI as a Search Engine — Use It Like This Instead

Muhamad Kautsar — Tue, 16 Jun 2026 02:02:30 +0000

I built my own AI agent from scratch. Not just a chatbot — a full autonomous system that manages my email, publishes articles, deploys code, and reminds me of tasks, all running 24/7 on my personal server.

And here's the thing nobody tells you: building it taught me that almost everyone is using AI completely wrong.

Not "wrong" in a moral sense. Wrong in a this-is-like-using-a-Ferrari-to-go-to-the-mailbox sense.

The Way Most People Use AI

Type a question. Get an answer. Close the tab.

That's it. That's the whole workflow for 90% of people.

They open ChatGPT like it's Google. They ask "what's the capital of France" or "summarize this email." They get a response, say "thanks," and move on.

And look — that works. It saves a few seconds. Fine.

But you're leaving almost all the value on the table.

What AI Actually Is

Here's the mental model shift that changed everything for me:

AI is not a search engine. It's a thinking partner that can also execute.

A search engine retrieves. AI reasons. Big difference.

When you ask Google "how to fix a bug in my code," Google gives you Stack Overflow links. When you ask Claude or ChatGPT the same thing, it looks at your specific code, reasons about what's wrong, suggests a fix, explains why it works, and anticipates the next problem you're about to hit.

That's not retrieval. That's cognition.

And when you stack that cognition with actual execution — like I did with AkiraAI — the gap between "user" and "operator" becomes massive.

The Three Levels of AI Use

After building and running an AI agent for months, I see three tiers:

Level 1 — The Lookup User
Uses AI to find answers they could've Googled. Gets maybe 10% more productive. Thinks AI is "okay but overhyped."

Level 2 — The Prompt Engineer
Crafts specific prompts, uses system instructions, iterates on outputs. Gets 2–3x more done. Starts to see the real power.

Level 3 — The Operator
Builds workflows. Connects AI to real systems. Lets it run autonomously. Gets 10x+ leverage. This is where things get weird (in a good way).

Most people are stuck at Level 1. The jump to Level 2 alone is life-changing.

What Using AI "Right" Actually Looks Like

Here's what changed for me when I stopped using AI as a search engine:

Think first, then prompt

The worst prompts are vague questions. "Help me with my startup." That's not a prompt — that's a prayer.

The best prompts come after you've already thought for 5 minutes. You show up with context, constraints, and a specific outcome you want. The AI refines and executes. You get results that feel like they came from a senior collaborator, not a random generator.

Give it a role and a goal, not just a question

Instead of: "Write me a blog post about productivity."

Try: "You're a tech writer targeting American developers aged 25–40. I want an 1,000-word article that challenges the assumption that more AI tools = more productivity. Use a personal, slightly contrarian voice. Start with a hook that mentions a specific mistake."

Night and day difference.

Use it to pressure-test your thinking

This is the one most people skip. Before you publish, ship, or send anything — paste it into the chat and say: "Tear this apart. What's weak? What's missing? What would a skeptical reader push back on?"

I do this with articles, business ideas, and even code architecture. The AI doesn't always catch everything, but it catches enough to make the final output significantly better.

Let it handle the repetitive so you can focus on the creative

The real unlock isn't using AI for hard problems. It's using AI to eliminate the 60% of your day that's medium-difficulty, repetitive, and soul-draining.

Email drafts. Meeting summaries. First-pass research. Boilerplate code. Status updates.

Clear that out, and suddenly you have hours for the work that actually requires you.

The Operator Mindset

When I built AkiraAI, I stopped thinking about AI as a tool I use and started thinking about it as infrastructure I run.

It's always on. It doesn't forget context between sessions. It acts when I need it to, without me having to remember to ask.

That shift — from using AI to operating AI — is where the real leverage lives.

You don't have to build your own agent to get there. But you do have to stop treating AI like a smarter search bar.

Where to Start

If you're at Level 1 right now, here's one concrete thing to try this week:

Pick one recurring task you do at least three times a week — writing, research, review, whatever. Build a reusable prompt for it. Include your role, your audience, the format you want, and the tone. Save it somewhere.

Then run every instance of that task through the prompt, refine as you go, and pay attention to what you're learning about how to direct AI well.

That's the beginning of the operator mindset. It compounds fast.

The people who figure this out now are going to have a serious advantage — not because AI is magic, but because they learned to use it as a system instead of a shortcut.

You already have access to the same tools. The only difference is how you use them.

The World Cup, AI, and the Death of the 'Perfect' Internet: Why June 2026 Is Breaking Every Rule

Muhamad Kautsar — Mon, 15 Jun 2026 16:16:58 +0000

The World Cup, AI, and the Death of the 'Perfect' Internet: Why June 2026 Is Breaking Every Rule

Something strange is happening online right now — and it's changing everything about how we consume content, connect with each other, and understand the world.

🏆 The World Cup Is Back — And It's Chaos (In the Best Way)

The 2026 FIFA World Cup is officially here, hosted across the United States, Canada, and Mexico — and the internet is absolutely losing its mind.

But here's what's fascinating: the moments going viral aren't the goals. They're not the saves or the star players.

They're the humans.

A German soccer fan discovering the American South for the first time. A Boston cop's heartfelt fan video that moved millions. Senegal's ball bouncing off a pitch in a way that broke Twitter. These are the moments defining this World Cup online — and they tell us something profound about what people actually want from the internet in 2026.

We're done with polished. We want real.

The stadiums are massive. The production is slick. But what people screenshot and share? A confused German guy eating his first biscuit with gravy. A kid in the stands crying happy tears. A coach's three-word message that hit harder than any press conference speech.

This is the World Cup of authentic moments — and it's a mirror for everything happening on social media right now.

🕰️ "2026 Is the New 2016" — Why Everyone's Living in the Past

Scroll through Instagram or TikTok right now and you'll notice something weird: everything looks like 2016.

Chunky sneakers. Low-rise jeans. Flip phones (yes, really). MySpace-core aesthetics. The "2026 is the new 2016" trend has exploded with over 37 million posts across platforms, and it's not slowing down.

But why?

Because 2016 was the last year the internet felt manageable. Before the algorithm completely took over. Before every post was optimized for engagement. Before we all became mini-brands performing for metrics.

People aren't just nostalgic for the fashion — they're nostalgic for a version of the internet that felt human.

And that nostalgia is driving one of the biggest behavioral shifts we've seen online in years: people are actively rejecting algorithmic content in favor of raw, unfiltered expression.

The most-shared posts right now aren't high-production content. They're blurry photos. Unedited videos. Texts that went wrong. Real conversations. The internet is having a collective breakdown against its own perfectionism — and it's beautiful.

🤖 AI vs. Authenticity: The Battle That's Defining 2026

Here's the tension that's splitting the internet right now:

AI can create anything. But can it create meaning?

We're in a moment where AI-generated content is everywhere — and people are developing a sixth sense for detecting it. The uncanny valley isn't just visual anymore. It's emotional. Readers can feel when something was written by an algorithm chasing engagement versus a human who actually had something to say.

The backlash against AI slop has become one of the defining conversations of 2026. And paradoxically, it's making authentic human content more valuable than ever.

The creators winning right now aren't the ones using AI to generate more content faster. They're the ones using AI as a tool while keeping their voice, perspective, and humanity front and center.

The formula isn't: AI + Volume = Success

The formula is: Human perspective + AI assistance + Radical authenticity = Viral

Here's what that looks like in practice:

Proof-based content is exploding. Don't just say something — show the receipts, the process, the failures, the real numbers.
"I was wrong about this" posts consistently outperform confident hot takes.
Behind-the-scenes content — messy desks, failed experiments, rough drafts — gets shared more than polished final products.
Vulnerability is the new flex. Not performed vulnerability, but actual "I don't have this figured out" honesty.

📱 TikTok Is Now a Search Engine — And It's Changing How America Thinks

If you're still thinking of TikTok as a place teenagers dance, you're about five years behind.

Gen Z isn't Googling anymore. They're TikToking.

Restaurant recommendations. Medical questions. Political news. Travel guides. Historical research. Career advice. It's all happening on TikTok now, and the implications are enormous.

What's working on TikTok-as-search-engine:

Answer a specific question in the first 3 seconds
Use the exact words people are searching for (not SEO jargon — actual human language)
Show, don't tell — demonstrate the answer visually
Leave a "curiosity gap" that makes people comment or search more
Consistency beats perfection — 3 okay videos a week crushes 1 perfect video a month

🔮 What This All Means for Anyone Creating Content in 2026

1. Be more human, not less.
In a world drowning in AI-generated content, your biggest competitive advantage is being genuinely, unapologetically yourself.

2. Specificity is the new virality.
"Social media tips" gets ignored. "How I got 50K followers posting only on Tuesday mornings" gets shared.

3. Ride cultural moments, but add perspective.
Don't just repeat what everyone else is saying. Add your angle, your experience, your counterintuitive take.

4. Build for trust, not just traffic.
The creators with the most engaged audiences right now are the ones who've built genuine trust over time.

The Bottom Line

June 2026 is a weird, chaotic, beautiful moment on the internet. The World Cup is reminding us that the most shareable moments are human ones. The nostalgia wave is telling us we miss when the internet felt real. The AI authenticity debate is pushing creators to double down on their humanity.

The creators who embrace authenticity, specificity, and genuine human connection are going to win.

Not because it's trendy. But because it's what people have been starving for all along.

What's the most authentic piece of content you've seen go viral this month? Drop it in the comments!

The World Cup, AI, and the Death of the "Perfect" Internet: Why June 2026 Is Breaking Every Rule

Muhamad Kautsar — Mon, 15 Jun 2026 16:01:04 +0000

The World Cup is back. Olivia Rodrigo just dropped a new album. TikTok is being used as a search engine. And somehow, everyone online is acting like it's 2016 again.

June 2026 is arguably the strangest, loudest, most culturally saturated month the internet has seen in years — and if you're trying to understand what's actually happening in American culture right now, buckle up.

The World Cup Effect: America Has Finally Caught Football Fever

For decades, soccer (or football, depending on who you ask) was America's "almost sport" — always on the edge of mainstream but never quite breaking through.

That changed on June 11, 2026.

With the FIFA World Cup officially kicking off across the United States, Canada, and Mexico, something shifted. Fan zones are packed. Office Slack channels have turned into match commentary threads. TikTok's For You Page is flooded with stadium vlogs, penalty kick tutorials, and — inevitably — deeply unhinged sports takes.

But here's what's really interesting: the World Cup isn't just a sports story. It's a cultural reset.

For the first time in a long time, Americans from completely different walks of life — different cities, different political views, different generations — are finding something to collectively talk about, argue about, and celebrate. In an era where the internet feels increasingly fractured, the World Cup is functioning as one of the last remaining shared experiences.

That's powerful. And brands, creators, and media companies are scrambling to capitalize on it.

The Nostalgia Bomb: Why Everyone Is Acting Like It's 2016

Scroll through Instagram or TikTok right now and you'll notice something odd: celebrities and regular people alike are posting throwback photos, resurfacing old memes, and talking about Pokémon Go, the Mannequin Challenge, and the peak era of EDM like they just happened yesterday.

Welcome to "2026 is the new 2016" — the nostalgia trend that has taken over the internet.

The #2016 hashtag has already surpassed 37 million posts on Instagram and 1 million on TikTok. John Legend. Reese Witherspoon. Your college roommate. Everyone is doing it.

Why now? Psychologists and cultural critics point to a simple truth: nostalgia spikes during times of uncertainty. When the present feels overwhelming — economically, politically, existentially — people retreat to a time that felt simpler. And for Millennials and older Gen Z, 2016 was the last year the internet felt genuinely fun and low-stakes.

There's also something poetic about the timing. Ten years ago, we were naive about what social media would become. Now, a decade later, we're simultaneously more cynical and more desperate for that original sense of digital community.

The AI Reckoning: Smarter Tools, Bigger Questions

In 2025, AI-generated content surpassed human-written content online for the first time in history.

Let that sink in.

By June 2026, artificial intelligence isn't a buzzword anymore — it's infrastructure. AI is writing articles, generating images, editing videos, composing music, and even managing social media accounts. Platforms like Meta's Vibes and OpenAI's Sora are emerging as entirely AI-native social spaces.

But here's the twist: people don't fully trust it.

Nearly a third of American consumers say they're less likely to engage with a brand that uses AI-generated advertising. The backlash to AI slop — content that is technically competent but emotionally hollow — has created a massive opportunity for something that has always been valuable but is now priceless:

Authenticity.

The most-watched, most-shared, most-trusted content in America right now isn't polished. It's not perfect. It's founders talking directly to their phone cameras. It's creators showing their mistakes. It's raw, unscripted, human moments that no AI can convincingly replicate.

The irony of the AI era is that the more automated content becomes, the more we crave the real thing.

The Search Engine Is Dead. Long Live TikTok.

Here's a stat that would have sounded insane five years ago: Gen Z is more likely to search for information on TikTok than on Google.

In June 2026, this isn't a quirky generational habit — it's a fundamental shift in how information flows. People are searching TikTok for restaurant recommendations, medical advice, product reviews, tutorials, and news. Instagram Reels and YouTube Shorts are following the same pattern.

This matters enormously if you're a creator, a brand, or anyone trying to reach an American audience in 2026.

The rules have changed:

Searchable captions matter more than clever taglines
Problem-solving content outperforms entertainment-only content
Consistency beats virality — showing up daily in someone's search results is more valuable than one viral moment
Community management is now sales — how you respond to comments and DMs directly affects purchasing decisions

If you're still thinking about social media as a broadcast channel — a place to push out polished content and count likes — you're already behind.

What This All Means for the Rest of 2026

June 2026 is a cultural inflection point, and the signals are clear:

1. Shared experiences are making a comeback. The World Cup, major album drops (Olivia Rodrigo on June 12, Charli XCX's recent release), and returning TV series (House of the Dragon Season 3 on June 21) are creating synchronous cultural moments in an era that's been dominated by fragmented, algorithm-driven individualism.

2. Authenticity is the new luxury. In a world drowning in AI-generated content, being genuinely human — imperfect, vulnerable, direct — is the most differentiated thing you can be.

3. Nostalgia is a survival mechanism. The "2026 is the new 2016" trend isn't just cute — it's a cultural signal about collective anxiety and the human need to find stability in memory.

4. The platform hierarchy is being redrawn. TikTok as search engine. AI-native platforms emerging. Social media as commerce. The internet of 2026 barely resembles the internet of 2020, and the pace of change isn't slowing down.

The Bottom Line

The internet in June 2026 is chaotic, nostalgic, AI-saturated, and World Cup-obsessed — and somehow, underneath all of that, people are hungrier than ever for real connection.

The creators and brands that will win in this environment aren't the ones with the biggest budgets or the most sophisticated AI tools. They're the ones who understand that technology is the medium, but humanity is the message.

And right now, that message is resonating louder than ever.

Follow for more cultural analysis, digital trends, and the occasional hot take on what's actually happening in America's internet. New articles every week.