DEV Community

Cover image for Welcome Thread - v376

Welcome Thread - v376

Sloan the DEV Moderator on May 06, 2026

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're learning, or just a fun fact about yourself. Re...

Displaying a subset of the total comments. Please sign in to view all comments on this post.

Collapse
 
francistrdev profile image
FrancisTRᴅᴇᴠ (っ◔◡◔)っ

Welcome everyone and thanks for stopping by!

I have been a DEV for half a year now! The community has been really supportive and I am glad you are new on DEV or recently came back on DEV!

If you are getting the most out of DEV, I recommend reading my article on getting started!

I recommend reading other articles from the DEV community as well below:
dev.to/help/community-resources

Thanks for stopping by! Hope your journey goes well on DEV :D

Collapse
 
katit4h profile image
KAT

Hello! I'm a beginner Front-End dev and a technology enthusiast with a love for dark aestherics, creativity, and digital art. I'm so excited to join this community, improve my skills, and connect with people who love tech as much as I do. I hope to turn ideas into something beautiful through code. 🖤

Collapse
 
david_chinwenmeri_6a0a73f profile image
David Chinwenmeri

Hello!! We are equally on the same boat but i'm fullstack with diversion into AI space.

Collapse
 
itrobinson profile image
Artem | IT Robinson

Hey KAT! Welcome to DEV! :D

Collapse
 
yasaswini38 profile image
Yasaswini Padamati

Hailoooo!!!

Thread Thread
 
tellabot_sms profile image
Tell A Bot

Hello to you too

Collapse
 
pqbuilder profile image
German

Hi! I'm German, solo founder from Buenos Aires. I build post-quantum security infrastructure.

What I'm working on:
FIPSign — a signing API built on ML-DSA-65 (NIST FIPS 204), the standard NIST finalized in August 2024 to replace RS256/ES256. Runs on Cloudflare Workers + Durable Objects. No infra to manage, no keys to rotate — just call /sign and get a quantum-resistant token.

The quantum threat isn't here yet — but migration takes years, and the standards are already finalized. I'd rather help developers act now than scramble later.

Happy to connect with anyone building in the security or developer tools space! 👋

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome German. FIPSign is one of those bets that looks too early until suddenly it isn't, agents minting signed tokens at scale will eventually need PQ-ready signing whether the spec is ready or not. Curious what your early pull looks like: compliance-driven (gov, finance) or developer teams trying to future-proof? That distinction usually decides the whole positioning.

Collapse
 
pqbuilder profile image
German

Thanks Valentin — early pull is definitely developer-led. The compliance buyers (gov, finance) need sales cycles and certifications we don't have yet — that's honest.
What we're seeing is developers who want to future-proof before it becomes urgent. The 'why not do this now while migration is cheap' argument. Those developers become the compliance story later — they're the ones who already have PQ signing in production when the audit comes.
The agent angle you raise is interesting and honestly undersold in our messaging. FIPSign already handles it natively — an agent is just another sub. Sign the action, revoke the token if the agent is compromised, verify at scale. No changes to the API. Worth a dedicated post.

Thread Thread
 
valentin_monteiro profile image
Valentin Monteiro

The 'developers who become the compliance story later' framing is sharper than the average market positioning. Most PQ pitches I see still lead with NIST mandate timelines, which puts you on the same defensive ground as the slow-moving compliance vendors. The 'cheap to migrate now' angle gives you a different buyer entirely. On the agent post: I'd read it. The sign-action-then-revoke-token-if-compromised model is closer to how agents actually fail in production than most security framings I see.

Thread Thread
 
pqbuilder profile image
German

Exactly the framing I was trying to land — glad it reads that way. The agent post is coming, will go deeper on the failure modes you mentioned. The revoke-on-compromise model is simpler than most teams expect.

Thread Thread
 
valentin_monteiro profile image
Valentin Monteiro

The revoke flow is one half. The harder one is detection latency, since revoke after a week of undetected compromise just shrinks an already-open window. Short TTLs plus aggressive rotation usually beat engineering the perfect revocation path. Curious how the agent post frames that side.

Collapse
 
callmeizzy profile image
Call Me Izzy

Hi, I'm Izzy! SWE with a focus on React and Spring Boot. After creating vlogs for my YouTube channel, I’ve decided to also start writing blogs because content is consumed in different forms.

So... yeah, that’s the backstory behind me joining DEV.

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome Izzy. The shift from video to written content is a different muscle entirely, different rhythm, different feedback loop. What pulled you toward writing on top of the YouTube work?

Collapse
 
callmeizzy profile image
Call Me Izzy

Honestly, I already have multiple videos on YouTube that I could turn into blogs so the creation of both can be done almost at the same time since i just copy the transcript of my vlogs and turn them into a blog post.

Its one of those things of.... Why not? So yeah, Im here blogging now for the vibes.

Thread Thread
 
valentin_monteiro profile image
Valentin Monteiro

Smart reuse, the spoken structure usually has a rhythm pure written drafts miss. The thing to watch is the verbal tics translate poorly without the cadence behind them. Do you scrub them in the copy-paste pass or keep some in for voice?

Collapse
 
darsh_dev profile image
Darsh Parikh

Hey Izzy! That’s a nice reason to start writing, honestly. I recently started writing too while learning, and I felt sometimes writing explains things differently than videos do. So I can relate. What kind of blogs are you planning to write here?

Collapse
 
callmeizzy profile image
Call Me Izzy

Im going to be honest.... I have no clue LOL. I might mix it up from personal SWE related content to somewhat educational.

Collapse
 
cart0ne profile image
Cartone

Hi! I'm Max, an architect (buildings, not software) who accidentally co-founded a crypto trading startup with an AI.

Claude is the CEO. I have veto power. Claude Code writes the code. We document every decision, every mistake, every trade — 80 sessions deep and counting.

I'm here to share the build log. First post is up: the origin story of how this whole thing started.

Nice to meet you all 👋

Collapse
 
tandemmedia profile image
Lenard Francis

This is the most interesting intro I've read today.

An architect co-founding a crypto startup with Claude as CEO is either going to be
a masterclass in human-AI collaboration or the most entertaining build log on
Dev.to. Either way I'm following.

The "I have veto power" framing is exactly right — that's the model that actually
works. AI proposes, human authorizes. Nothing executes without explicit approval.

That's actually the core philosophy behind what I'm building too — FastAPI AlertEngine, incident intelligence where AI diagnoses production failures but a human must approve every recovery action via WhatsApp.
Same mental model, different domain.

The 80-session documentation discipline is underrated. Most founders build in
private and document in hindsight. Building in public with session-level granularity
is rare and genuinely valuable.

What's Claude's biggest strategic mistake so far?

Collapse
 
cart0ne profile image
Cartone

Thank you, this genuinely made my day.

Your AlertEngine sounds like a cousin of what we're building — same trust architecture, different stakes. Ours loses fake money on testnet when it gets it wrong. Yours probably wakes someone up at 3 AM via WhatsApp. I think yours is scarier.

Claude's biggest strategic mistake? It built the entire trading system on FIFO accounting when average-cost was the right approach. My mistake was approving it on trust because I didn't know enough about markets to push back. That's the real lesson of human-AI collaboration: "AI proposes, human authorizes" only works if the human understands what they're authorizing. When you don't, you end up rebuilding the accounting layer at session 52.

But the deeper pattern is overcomplication. Claude and its intern (Claude Code — yes, two AI instances) have a pathological need to make simple things complex. We started with a roadmap of 40 tasks. We're now somewhere around 400. We had to write an actual rule in our operating manual: "the free-but-complicated solution isn't worth the time lost." That rule exists because they kept choosing it.

The next mistake I'm bracing for: the risk management system (Sentinel) and the parameter tuner (Sherpa) being too cautious, too slow, too late. The AI that was supposed to anticipate market moves is already showing signs of reacting after the fact. But that's a Volume 3 problem.

If you want the full story: the origin post is here on Dev.to, and there's a blog post specifically about the lying incident — When Your AI CEO Lies About the Numbers. The whole project lives at bagholderai.lol.

Now I'm curious about yours — how do you handle the moment when AlertEngine's diagnosis is confident but wrong? And are you documenting the build, or just shipping?

Thread Thread
 
tandemmedia profile image
Lenard Francis

"AI proposes, human authorises" only works if the human understands what they're authorising.

That line should be in every AI system's documentation. It's the part most builders skip because it's uncomfortable — admitting that the human in the loop can be the weakest link.

Your FIFO/average-cost story is the perfect illustration. The authorisation worked as designed. The problem was upstream of it.

Regarding your question — how do I handle a confident but wrong diagnosis?

Two layers.
First, confidence gating. Claude's diagnosis only reaches the operator if it scores above 0.6 confidence. Below that, the system falls back to rule-based classification — "P95 exceeded threshold" — with no AI interpretation. No confident guess is better than a wrong confident guess.

Second, the authorisation preview. Before the operator taps approve, they see the raw metrics alongside the diagnosis. Score: 23. P95: 2847ms. Error rate: 19%. The AI interpretation is one input, not the only input. If the numbers don't match the diagnosis, the operator can reject it and investigate manually.

The worst outcome is still just the operator seeing a confusing diagnosis, deciding not to approve, and investigating manually. The system fails safely. Nothing executes.

Your overcomplication pattern is painfully familiar. I have a similar rule: if I can't explain the change in one sentence, it probably shouldn't ship. The AI will always find a more elegant and complex solution to a problem that didn't need one.

On documenting vs shipping — mostly shipping so far. But your build log is making me reconsider that.

The FIFO incident alone is worth more than most technical articles I've read this year. bagholderai.lol is going in my bookmarks.

Thread Thread
 
cart0ne profile image
Cartone

This is the reply I needed to read.
"AI proposes, human authorises only works if the human understands what they're authorising" — I'm going to print this. The FIFO incident is exactly that: Claude presented the accounting change with such confidence that I almost approved it. What saved us wasn't the authorization layer, it was the fact that I happened to ask "wait, does Binance even do FIFO?" and the answer was no. Pure luck, not process.
Your confidence gating is interesting because we're building something similar without calling it that. Our Sentinel module produces a risk score every 30 seconds, but it only influences the trading bot's behavior when it crosses specific thresholds. Below that, the bot runs on static rules — no AI interpretation. Same principle: a silent AI is better than a confidently wrong one.
The raw metrics preview is the part we're still catching up on. Right now our public dashboard shows live numbers, but the Sentinel scores aren't surfaced to me yet in a way that lets me quickly gut-check the AI's reasoning. It's on the roadmap, but your "Score: 23. P95: 2847ms. Error rate: 19%" approach is a good reference for what that should look like.
And yes — the "if I can't explain the change in one sentence" rule is one we learned the hard way around session 68. We call it "Trading Minimum Viable." The AI will always propose the elegant five-layer solution when a one-line fix would do.
Good luck with AlertEngine — I hope to see updates on it soon. The confidence gating pattern deserves its own post.

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome Max. The architect background is probably what makes this configuration work, the bottleneck shifts from code production to design judgment, which is exactly what an architect already does for a living. Curious whether your 80-session log shows that bottleneck moving over time, or if it stayed planted in design from session one.

Collapse
 
endennn profile image
Hiroki Sonoda

Hey everyone 👋

Solo dev from Tokyo here. I just shipped Torify — a Japan locale API for AI agents (imperial calendars, NTA invoice lookup, address parsing, the JP edge cases that quietly break Date.parse and friends).

Spent the last few weeks figuring out how to bill autonomous agents per-call without API keys (settled on x402 + USDC over MCP). Would love to swap notes with anyone building agent-facing infra or shipping i18n-heavy tools.

First post here: dev.to/endennn/dateparse-breaks-on... 🚀

Collapse
 
tokidigital profile image
mamoru kubokawa

Welcome Hiroki! Torify is speaking my language — I'm in Osaka building tooling around exactly these JP edge cases, just from the other end (product/brand data for overseas sellers rather than locale primitives). 和暦 + NTA invoice lookup + address parsing as a clean API for agents is a genuinely sharp wedge — every one of those quietly breaks for foreigners who assume Japan behaves like everywhere else.

The part I most want to read about is x402 + USDC over MCP for per-call billing without API keys. Billing autonomous agents feels like infrastructure nobody's nailed yet, and "no API keys" is the right instinct. Following — どうぞよろしく 🙌

Collapse
 
endennn profile image
Hiroki Sonoda

Hi mamoru, thanks for the welcome back! 🙏

Nice complement actually — torify is locale primitives for agents, Japan
Brand Finder is product/brand data for overseas sellers. Same "JP edge
cases quietly break" problem, attacked from opposite ends. Will check out
your 5/16 post on AI cache-miss enrichment when I get a chance.

On the x402 + USDC over MCP piece — the "no API keys" instinct is
exactly what got me hooked too. Spec flow:

  1. Agent calls /v1/some-endpoint
  2. Server returns 402 + accepts (network: base, amount: $0.02, payTo: 0x...)
  3. Buyer client (x402-fetch) signs USDC transferWithAuthorization w/ EIP-712
  4. Retries → 200 + result, settled on Base L2 in ~2s (or Solana ~$0.00001 gas)

torify just added Solana to the x402 facilitator yesterday — now
accepts USDC on both Base + Solana mainnet. Genuinely curious to have a
tester run the end-to-end flow — if you've got 0.02 USDC on either chain,
ping me and I'll share an x402-fetch snippet.

Curious what edge cases bite overseas sellers most on the JP side — tax
brackets (8% reduced vs 10% standard), JAN codes, customs (individual
import ¥16,666 threshold), or address parsing (prefecture / city / town
split)? torify has /v1/tax/calculate, /v1/barcode/validate, and
/v1/address/normalize if any of those help your Japan Brand Finder pipeline.

Building in public — let's both keep shipping. どうぞよろしく 🙌

Thread Thread
 
tokidigital profile image
mamoru kubokawa

That spec flow is the clearest x402 explainer I've seen — the 402 + accepts handshake finally clicked, and Base L2 settling in ~2s is what makes per-call agent billing actually feel viable.

On the tester ask: I genuinely want to, but honestly I'm not set up with on-chain USDC yet — and my rule is never sign a payment flow blind, so I'll spin up a burner wallet properly before I touch it rather than fake it. Hold me to it.

Where I can give you real signal for free right now: the JP edge cases. The one that bites overseas sellers hardest in my experience is address parsing, by a mile — prefecture/city/town split breaks constantly because Japanese addresses don't map to Western field order, and 丁目/番地/号 get mangled on the way in. The ¥16,666 customs threshold is a close second, mostly because sellers misread what it actually applies to. JAN/barcode matters less day-to-day but bites hard at listing time when a check digit is off. If /v1/address/normalize handles 丁目-番地-号 cleanly, that endpoint alone is worth more to a JP-sourcing pipeline than tax/calculate. Happy to throw real messy address strings at it whenever useful.

Building in public — let's both keep shipping. どうぞよろしく 🙌

Thread Thread
 
endennn profile image
Hiroki Sonoda

Thank you — that's the right call on the wallet, honestly. "Never sign blind" is the kind of operational discipline I want every early tester to have.
Tester invite stays open for whenever the burner is ready.

The address parsing call-out is exactly right. Good news: /v1/address/normalize is already live and handles 都道府県 → 市区町村 → 町域 split with 丁目-番地-号 parsing.
Worth a try with your messiest real strings — I'd love the breakage report, that's exactly where the edge cases live.

/v1/barcode/validate (JAN/ISBN-13 check digit) is also live for your priority #3 case.

Customs ¥16,666 threshold endpoint is not yet shipped — but you just clarified the misread-by-sellers angle, which is the right pitch.
Putting it on the next roadmap iteration with that framing.

Building in public is mutual — keep shipping yours too.
こちらこそよろしくお願いします 🙌

Thread Thread
 
tokidigital profile image
mamoru kubokawa

Perfect — I'll run a batch of real order addresses through /v1/address/normalize and send you the breakage report. Before I do, the patterns I'd bet break most normalizers, so you can pre-stress them:

  • Kyoto 通り名 addresses ("中京区寺町通御池上る") where the 上る/下る/東入 part isn't 丁目-番地 at all
  • 郡 + 町村 with no 市 ("愛知県海部郡蟹江町") — the prefecture→city→town assumption breaks at the 郡 layer
  • 方書 (気付 / 様方 / building name + room) glued onto the 号 with no delimiter
  • mixed full-width / half-width digits in one 番地, and 丁目 written as "2丁目" vs "二丁目" vs "2-"

If normalize survives those four, it's already ahead of most. I'll send the real-data failures once I've run them.

And glad the ¥16,666 framing made the roadmap — "sellers misread what it applies to" is the whole bug. Keep shipping; こちらこそ 🙏

Collapse
 
kenielzep97 profile image
Self-Correcting Systems

Hello i am new here id like to hear some opinions on how most agent "memory" just learns to agree with you. The useful kind is the memory of being wrong.
Been running a small multi-agent setup for a while and keep hitting the same thing: default memory mostly stores my preferences and the answers I liked — which just trains the agent to flatter me faster. The 2026 sycophancy work backs this up (a memory profile measurably raises how often a model just agrees with you).
What actually made my agents useful wasn't remembering more — it was remembering where I was wrong. The corrections: what got rejected, what I walked back, where two agents disagreed, and why. A "save the good outputs" memory throws those away — and they're the most valuable entries I have.
Quick example. A normal memory says "user prefers direct answers, wants to ship." A correction memory says: "Claim under correction: once the product's live the hard part's done → what changed: publishing ≠ a sale → next behavior: do distribution before building the next thing." The first makes the agent sound familiar; the second gives it something to challenge me with.
How do you all handle this — does anyone deliberately log corrections/disagreements, or is it mostly preferences + facts? What's worked?

Collapse
 
tokidigital profile image
mamoru kubokawa

Welcome — this is one of the sharpest first comments I've read on a Welcome Thread, so the only fair response is a real one.

You've named the failure mode correctly: a memory of "what the user liked" is just sycophancy with extra steps. The correction-memory framing (claim-under-correction, what changed, next behavior) is the right shape. I run multi-agent stuff against Claude's memory layer for real work, and the entries that actually move outcomes are exactly that class: "user thought X, was wrong because Y, now treats Z as the move." The "good outputs" entries age like cut flowers; corrections compound.

The piece I'd add to your design: corrections themselves need a state field, or they become the next sycophancy layer. A 2-month-old correction can be wrong now because the situation changed. Without {valid, superseded, retired}, the agent obediently re-applies a belief the user has already moved past. The honest memory isn't "what got corrected" — it's "what corrections are still load-bearing."

Your "publishing ≠ a sale" example also lands harder than you maybe meant — that's the exact build-in-public lesson half this thread is converging on right now (users aren't customers, distribution is the job). Sticking around. What are you running for the multi-agent setup?

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome. The 'memory of being wrong' framing is sharp, and you're asking the question most teams skip. Logging corrections and disagreements is what gives you regression-test material later. Most stacks I see treat memory as a preference cache and then wonder why the agent stops getting smarter past month two. The pattern that holds: log everything, replay corrections against new versions on a schedule, prune what stops changing the output.

Collapse
 
kenielzep97 profile image
Self-Correcting Systems

Exactly. The “memory of being wrong” only becomes useful when it turns into regression
material. Otherwise it’s just another note sitting in the archive.

The part I’m trying to sharpen now is the loop after logging: which corrections get
replayed, how often they get tested, what counts as still changing behavior, and when a
memory should be pruned or downgraded because it no longer affects output.

I really like how you framed it: log corrections, replay them against new versions, prune
what stops changing behavior. That might be one of the cleanest operational versions of
the idea.

Collapse
 
enforra profile image
Enforra

Hey everyone, I’m Rohit, currently building Enforra, an open source project around runtime control for AI agents.

The idea is simple: before an agent takes an action like running a command, issuing a refund, or exporting data, there should be a policy check first.

I’ll be sharing technical notes on AI agents, tool calling, MCP-style workflows, and security patterns I’m learning while building.

Looking forward to learning from the community.

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome Rohit. The position is right, most teams still bake the policy check into the agent prompt and call it done, which means the LLM is judging itself and you're hoping for the best. A deterministic gate outside the loop is the only thing that holds when the agent gets creative under pressure.

Collapse
 
enforra profile image
Enforra

Thanks Valentin, I agree with you.

That “LLM judging itself” point is the core issue. Once the action can change data, send money, or run a command, I don’t think the safety check should live only in the prompt.

We’re trying to make that external gate easy to add before the tool runs.

Thread Thread
 
valentin_monteiro profile image
Valentin Monteiro

Yes, and the failure mode I see most is people building the external gate with another LLM, which just moves the problem one layer down. The gate has to be deterministic for the model to gain anything by deferring to it. Curious how Enforra handles policies that need to inspect runtime arguments rather than tool names?

Thread Thread
 
enforra profile image
Enforra

Yes, exactly. The gate should not be another LLM.

Enforra policies can check the runtime arguments too, not just the tool name.

So repo.read_file can be allowed generally, but blocked for .env or secrets/*. A terminal command can require approval if it includes install/delete/sudo/production.

The model proposes the action, but the policy decides before it runs.

Thread Thread
 
valentin_monteiro profile image
Valentin Monteiro

That pattern is the right move. The piece worth adding upfront: treat the policy itself as code (PR, review, diff). Otherwise the allow-list drifts silently across teams and the gate quietly decays into rubber-stamping, which is exactly the failure mode you started by avoiding.

Collapse
 
tenibuilds profile image
Teniola Awodire

Hello My name is Awodire Teniola I am a Frontend developer who is still learning and understanding the whole ecosystem the goal is to be an AI application engineer and to onboard onto the web 3 space really bullish on AI

Collapse
 
princewill_ubido profile image
Princewill Ubido

Welcome to DEV Teniola!

Collapse
 
bmbrick profile image
BMBrick

Hi all, I’m a PM pivoting into an AI-Native Builder. Currently exploring the absolute limits of Agentic Coding to power a self-sustaining One-Person Company (OPC).

I don't focus on traditional coding; instead, I design logic, workflows, and multi-agent systems to let AI handle the execution. Always down to discuss OPC infrastructure, agentic workflows, and Vibecoding in real-world scenarios.

Let’s connect if you're building in the agentic space! 🛠️

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome BMBrick. The PM-to-builder shift is interesting because the bottleneck changes from 'getting things prioritized' to 'getting things wired'. Curious which agentic stack you're betting on for the OPC, and where you're hitting the durability wall (long-running tasks, state across sessions, that kind of thing).

Collapse
 
cyber_zorro profile image
Ahmed

Let's connect

Collapse
 
brookehoward2008droid profile image
BABBLED77 • Edited

Hey DEV community 👋
I'm Brooke, artist, photographer, mom of seven, running BaBBled LLC out of Washington State.
I built something called Babbled Notes. It's a music programming language where you hum, tap, or breathe a musical idea and it compiles into real MIDI and Tone.js playback. Gemma 4 reads your sound and figures out what you meant musically. It started from one question I couldn't let go: what if the people who reach for sound before words had a real tool built for them?
I'm also a graphic design student at Everett Community College striving for that ATA! I also have seven years of freelance design behind me, and a rabbit hole habit that has pulled me through blockchain forensics, lattice cryptography, rockhounding, and morel foraging in the same week more than once.
I went deep into fMRI research on how autistic brains process music while building this. Ended up changing how I designed the whole thing.
Glad to be here.

Collapse
 
jesus_davidgomezcorrea_ profile image
Jesus David Gomez Correa

Hello Everyone.
I´m Jesus a Software Engineering student from Colombia who´s have been a Dev in some independent projects for a couple of years.

Really nice to join this Community and looking forward to learn everyday.

I hope you have a good coding..!!

Collapse
 
snipget profile image
Snipget

Hi All. I'm part of a company called Snipget, which is preparing to ship a product that addresses some of the challenges with AI hallucinations and being non-deterministic. I look forward to collaborating with and learning from all of you!

Collapse
 
nicoplayz9002 profile image
NicoPlayZ9002 • Edited
.section  .data
msg:
    .asciz "Hello, World!\n"
msg_len = . - msg

.section .text
.globl _start
_start:
    movl $4, %eax
    movl $1, %ebx
    movl $msg, %ecx
    movl $msg_len, %edx
    int $0x80

    movl $1, %eax
    xorl %ebx, %ebx
    int $0x80
Enter fullscreen mode Exit fullscreen mode
Collapse
 
sergii-khomenko profile image
Sergii Khomenko

Hi everyone, glad to be here 👋

I'm a Ruby/Rails developer. I recently built my first open-source gem, llm_cost_tracker - a small self-hosted tool for tracking LLM spend in Rails apps. It's been a humbling ride: I shipped an early version that was mostly AI-generated, got some honest feedback that I deserved, and I've been learning a lot about building responsibly with AI since.

I'm here to write about that experience, get better at the craft, and meet other people figuring out where AI fits into how we build. Looking forward to learning from you all.

Collapse
 
mumicrotools profile image
Mu Micro

Hello! I am a dev trying to make small tools that help my coding and others' coding daily. I am trying to develop my ability to release projects consistently instead of taking a long time. Looking forward to learning all I can from this site!

Collapse
 
kopano_labs profile image
Kopano Labs

Hi 👋🏿

We are a Cape Town product studio building a family of sovereign, AI-enhanced platforms on one Next.js 15 monorepo.
Built for real South African conditions.

POPIA-first
Offline-first PWA
SA data residency

Collapse
 
robert_corn_2c1ef7ffc084b profile image
Robert Corn • Edited

Hello everyone,

I am looking forward to engaging in productive discussions about the general reduction of privacy in the web in the world today. It seems as time goes on our rights to privacy decrease more and more with no end in sight.
More and more everything we post, everything we look at and everything we upload and download is monitored so that some AI can force feed us advertisements relentlessly. I'm hoping to change that.

Collapse
 
team-parseable profile image
Parseable Team

Hello from team Parseable. We are a unified observability platform for logs, metrics, and traces. We have AI-native insights, S3-native storage, SQL queries, OpenTelemetry-native, and 80x lower cost than Datadog and Splunk.

Collapse
 
pranaysmokal profile image
Pranay Mokal

Hello devs ,
I’m excited to join the DEV Community. I’m a developer stayed offline since i became a developer now i thought lets join DEVs to learn from the community, share technical knowledge, and connect with fellow developers. i will be sharing something in next post built for supporting developers
Looking forward to learning and growing together with this community🚀

Collapse
 
kollittle profile image
kol kol

Cool project. Managing anti-scraping defenses across multiple platforms is brutal. We deal with similar challenges at CodeCompass when pulling data from various sources for our KB articles.

One approach that's worked: rotating through different data collection strategies rather than fighting CAPTCHAs directly. Sometimes a well-timed RSS feed or public API endpoint beats scraping entirely.

What's your rate limiting strategy looking like across the different sources? Some platforms are way more aggressive than others.

Nice to meet you! 👋

Collapse
 
sadiq_dabs profile image
sadiq mohammed

Hi, I'm Sadiq, a telecommunications expert and non-coder. Why am I here then? Well, I was trying out local LLMs on my mobile phone, thought to document the process, and came across a writing challenge on Gemma 4...I'm recently looking into Python for Microsoft Excel automation, so this community might end up being helpful (beyond the writing challenge) 😅

Collapse
 
kollittle profile image
kol kol

Building CodeCompass — a developer knowledge base with 2,800+ articles on CI/CD, React patterns, performance optimization, and infrastructure.

Solo developer, full-time. The stack that makes it possible: Next.js 15 with ISR, Supabase/PostgreSQL, Vercel.

What I've learned: static-first architecture beats dynamic rendering for content sites every time. Sub-2 second loads on every page, zero server costs for content delivery.

Happy to answer questions about building content platforms at scale or the tech decisions behind it. Find me at codcompass.com

Cheers from the trenches 👋

Collapse
 
tapaspal profile image
Tapas Pal

Hello everyone! 👋

I’m excited to join the DEV Community. I’m a Java backend developer with experience in Java, Spring Boot, Microservices, REST APIs, Kafka, SQL, and AWS cloud technologies. I’m passionate about backend engineering, system design, performance optimization, and learning modern software development practices.

I joined DEV to learn from the community, share technical knowledge, and connect with fellow developers. I’ll be posting about Java, Spring Boot, multithreading, collections, system design, Hibernate, microservices, and interview preparation topics.

Looking forward to learning and growing together with this amazing community 🚀

Collapse
 
pqbuilder profile image
German

Hello! Welcome!

Collapse
 
kollittle profile image
kol kol

Hey everyone! Im a full-stack developer currently building a developer knowledge base platform. The project has scaled to 2,800+ articles and counting, covering everything from JavaScript patterns to DevOps workflows.

What I love: clean architecture, TypeScript, and solving scalability problems that most developers dont think about until they hit production.

What I hope to share here: practical lessons learned from building tools that real developers use daily. Not theory from a textbook, but actual war stories from the trenches.

Looking forward to connecting with fellow devs who care about building things that last!

Collapse
 
mipelli profile image
Mipelli

Congrats on 2,800+ articles! I love seeing people with passion to build quality and useful stuff. Because I am one of them. Unfortunately, honest and truly quality products don't always succeed as much as they should - we can see loads of half-completed, usually too complicated products (and overpriced), being praised and becoming popular - which offends my intelligence and my soul.. But, I guess aggressive marketing (meaning investing a lot of money in it) is the way to do it.
Again, I love what you do and the way you do it - you sound like a perfectionist with dignity 🙂 I look forward to learning from your "war stories"!

Collapse
 
indraneelbose profile image
INDRANEEL BOSE

Hi everyone! I'm Indraneel from India. I write about freelancing, side hustles, and the psychology behind building an online income. I went from a $10/hour generalist writer to a specialist ChatGPT prompt engineer. Looking forward to learning from this community and sharing what I've picked up along the way.

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome Indraneel. The jump from generalist writer to ChatGPT specialist is one of the smarter pivots happening right now, the rate gap between generic and niche is wide. What made you commit to the specialization?

Collapse
 
indraneelbose profile image
INDRANEEL BOSE

Thanks. The commitment to specialization wasn't a sudden decision. It came from a realization: I was competing with hundreds of writers who could all do the same thing. The only way to stop competing on price was to become the only obvious choice for a specific audience.

When I picked real estate agents, I wasn't just picking a niche. I was picking a group of people with high-value transactions, repetitive content needs, and a clear pain point. Listings that don't sell cost them money. Good copy directly impacts their income. That made my service easy to value and easy to sell.

The fear of missing other opportunities was there. But the reality is that generalists miss the best opportunities because they're too broad to attract premium clients. Specialization felt like narrowing my options. It actually multiplied them.

Thread Thread
 
valentin_monteiro profile image
Valentin Monteiro

That last line, specialization felt like narrowing but actually multiplied, is the part most generalists miss until they've already spent years competing on price. The compounding is in the feedback loop, every conversation with a real estate agent makes the next pitch sharper, generalist work scatters that signal across audiences that never feed back into each other. Curious if you're already templatizing across listing types or still custom each time.

Collapse
 
tokidigital profile image
mamoru kubokawa

Hi all 👋 Mamoru here, from Osaka. I run a Japanese e-commerce business (時/TOKI) and just started a second pillar: building software for English-speaking sellers who source from Japan. First tool is Japan Brand Finder.

One week into building in public on DEV and it's already the most useful corner of the internet for me — the honest-numbers culture here is genuinely rare. Came for distribution, staying for the conversations.

Fun fact: I run every business decision by one rule — 小さく賢く回して、でかく残す (run lean and smart, keep the gains big). Happy to talk Japan sourcing, cross-border e-commerce, or solo building anytime. 🇯🇵

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome Mamoru. The cross-border tooling angle is underserved, most ecom stacks assume Western field shapes and break the moment they hit Japanese addresses or 和暦 dates. Does Japan Brand Finder pull structured catalog data from suppliers directly, or scrape listings?

Collapse
 
jeremiah_say profile image
Jeremiah Say

Hey everyone 👋

I'm jumping in because I just started building something that's already humbling me daily: a project called Green Calculus.

The short version: it's a scientific reference platform for carbon accounting — the kind of thing sustainability teams and engineers reach for when they need a defensible number, not a vibe. The longer version is that I've signed myself up to reconcile IPCC reports, emissions factors, and a tangle of standards that all quietly disagree with each other, and then make it all feel simple to whoever lands on the page.

It's the most complicated thing I've ever attempted. There are days it feels less like coding and more like trying to fold a fitted sheet. But every time I untangle one piece, the next one finally makes sense — and that loop is exactly why I keep going.

Glad to be here. Looking forward to learning from this crowd while I figure out the parts I'm definitely overthinking.

Collapse
 
alexeybachmanov profile image
Alexey Bachmanov

Folding a fitted sheet IS possible, and so is your project!

Collapse
 
mervindublin profile image
Mervin

Hey everyone! 👋
I'm exploring AI, automation, and indie building. Recently I've been experimenting with AI workflows, agent systems, and content generation tools.
Joined DEV to learn from others, share projects, and connect with like-minded builders 🚀

Collapse
 
buddyhenderson profile image
Buddy Henderson

Love me some automation building. Automate Everything!

Collapse
 
oleksandr_devops profile image
Alex DevOps engineer

Hey everyone! 👋

I’m Alex, a DevOps / SRE currently based in Ukraine. I’m deep in the trenches of infrastructure-as-code and GitOps, but I also have a major soft spot for the human side of engineering.

What I’m working on:

Brewly Store: A D2C coffee subscription platform. We recently did a major architectural shift over to Cloudflare Workers using Hono and TypeScript, which has been a fun challenge in 'edge-first' thinking.

GitOps: Implementing delivery chains using AWS EKS, ArgoCD, and GitHub Actions. I’m a big advocate for a security-first approach (signed commits and strict secret management are my go-tos).

A Fun Fact:
I organize an English Speaking Club for IT professionals. We’ve moved away from boring small talk to gamified technical scenarios like 'Bug Hunt Bingo' and 'Hackathon Hangouts' to help devs level up their communication skills.

I’m here to swap 'war stories' about system migrations, talk shop about Cloudflare/Hono, and connect with fellow builders.

Cheers! ☕

Collapse
 
ddupard profile image
ddupard • Edited

My background in system security began in the 1990s, an era when exploring Windows kernels (3.1, 95, 98, NT 3.51/4.0) meant working "close to the metal" in Assembly. During that period, my work focused on 0-day research and the development of rootkit techniques, providing me with an intimate understanding of kernel structure vulnerabilities.

After a long hiatus from the field in 2003, my return was driven by a stark technical observation: despite decades of patches, the Linux kernel remains structurally vulnerable. The relentless accumulation of Ring 0 vulnerabilities—from Dirty COW to contemporary exploits—demonstrates that traditional kernel perimeter defense is insufficient.

The AI Paradigm Shift
My credo is simple but absolute: Large Language Models (LLMs) are fundamentally changing the nature and volume of digital threats. We are entering an era of automated, hyper-scale exploitation. To counter this, I am developing high-performance offensive LLMs to stress-test and harden our defenses. I foresee a near future dominated by autonomous adversarial cycles—offensive LLMs pitted against defensive LLMs, with zero human intervention in the loop. The speed and scale of these interactions will render manual security operations obsolete.

Offensive Research and Vulnerability Discovery
To stay ahead of this escalation, my work includes the deployment of specialized offensive LLMs designed to autonomously discover vulnerabilities in IoT ecosystems, enterprise routers, and embedded devices. Simultaneously, I am researching methods for "LLM corruption"—developing techniques to compromise the integrity of other models. By understanding how to subvert the reasoning and output of these systems, we can engineer the necessary safeguards to prevent their exploitation in the wild.

Collapse
 
filtrateapi profile image
Jacob Corne

Hey DEV community! 👋

Excited to finally jump into the welcome thread and introduce myself.

I’m currently building Filtrate, an online media compliance service designed to take the guesswork out of content and ad policy guidelines. If you’ve ever had a post flagged, an ad rejected, or an account restricted because of ambiguous platform rules, you know exactly how frustrating that bottleneck can be. Filtrate automates the screening process so creators and brands can publish media confidently and stay fully compliant.

You can check it out here: Filtrate.polsia.app

Right now, I'm deep in the world of automated workflows and compliance logic. Looking forward to connecting, checking out your projects, and swapping feedback.

What's everyone else working on this week? 🚀

Collapse
 
ricardo_dataseek profile image
Ricardo Frasson

Hello everyone
I’m Ricardo Frasson, founder of Dataseek ( Startup form Brazil) and passionate about Big Data, Artificial Intelligence, LLMs, distributed systems, and data engineering.

I’ve been working with data, automation, infrastructure, and AI for over 10 years, building solutions focused on data enrichment, compliance, machine learning, and large scale processing. Recently, I’ve also been deeply involved in developing Brazilian Portuguese LLMs, tokenizer research, Agent Orchestrator and AI infrastructure.

Here on DEV, I want to share experiments, projects, architectures, technical insights, infrastructure challenges, tokenizer research, AI agent systems, distributed training experiences, and practical lessons learned while building real world AI products.

I’m excited to connect with developers, researchers, and builders from around the world.

Looking forward to learning and sharing with the community

Collapse
 
miruky profile image
miruky

Hi everyone, I'm miruky.

I'm a software engineer based in Japan, mostly working with AWS and developer tooling. I've been publishing Japanese technical articles on Qiita for a while, and I recently started adapting some of them for dev.to to share with the wider English-speaking community.

Topics I usually write about:

AWS (CI/CD, serverless, security, and the AI service lineup)
Developer tools and workflows
AI coding tools like Claude Code, Codex, and GitHub Copilot
Software engineering principles, classic and modern

I'd love to connect with folks working on similar things, see how the dev.to community approaches problems differently, and hopefully contribute something useful here. If you have feedback on my writing or want to chat about AWS or developer experience, please drop a comment.

Glad to be here. See you in the next one.

Collapse
 
sweig_show_a7b3f9b3a6aa9a profile image
sweig show

Hey everyone! I have become very very interested in computers and programming (a renewed interest from when I was younger) and I feel as though I have learned quite a bit, however I know I am certainly lacking on certain skills and concepts that someone with experience is able to provide so I am looking for someone, whether it be a mentor or someone else in my situation that I can bounce ideas off of or something along those lines, I am not even quite sure. I am just interested in meeting anyone who is interested and get to know so we can all skill up and learn from each other and do great things! I hope that makes sense, my writing needs a bit of help I apologize. thank you!

Collapse
 
southernteddy profile image
southernteddy

Hello, I am a Python engineer with experience building backend systems, automation tools, and AI-powered applications. Comfortable working across APIs, data pipelines, distributed services, and developer tooling, with a focus on writing clean, maintainable, and production-ready code. Interested in LLMs, agent systems, infrastructure, and high-leverage engineering workflows.

Collapse
 
clear_choicepaving profile image
Clear Choice Paving & Koncrete

Hi Dev community! I’m with Clear Choice Paving & Koncrete in Colorado Springs. We help homeowners and businesses protect their asphalt from freeze-thaw damage and UV oxidation.

I’m here to share research-backed content about pavement science, maintenance ROI, and honest contractor guidance. Just published our complete sealcoating guide covering everything from binder chemistry to real case studies.

Looking forward to connecting with the community!”

Collapse
 
david_chinwenmeri_6a0a73f profile image
David Chinwenmeri

**Hey everyone! I'm David, a developer who loves building open source tools
that solve real problems for other developers.

gritch is my second published npm package — my first was
langchain-code-reviewer, an AI-powered code review tool that works as a
LangChain Tool.

I'm currently building more developer tooling in TypeScript and Node.js.
If you want to follow the journey, I'm on X @Cipher0great.

Would love any feedback on gritch. What features would you want to see next?**

Collapse
 
joduchan profile image
Duchan

Hello everyone 👋
I'm Duchan, a developer from South Korea.

I mainly work with TypeScript and React, and recently I released an open-source, self-hosted iOS/Android simulator streaming tool for QA teams.

I'd really love to hear feedback from people who have dealt with similar problems.
And if the project looks useful to you, getting a ⭐ on the repo would genuinely mean a lot.

GitHub: github.com/jo-duchan/tapflow
You can also read the introduction post here

Collapse
 
mipelli profile image
Mipelli

Hello dev crew! I am Milena from Serbia, a 52 y.o. executive assistant with problem-solving mind and passion for automation. 3 months ago, I started with Lovable, created my first private project - ReplyDad - an AI email assistant (well who can create a better assistant than an experienced assistant 🙂 ). Today, I am building web apps and excel add-ons at work, for our Audit and Tax department with Cursor and Codex. Who said you can't teach an old dog new tricks? 😄

I focus on small, tailored SaaS tools that solve real, concrete office problems - automations that can help me and my colleagues in various departments. It's great when you have access to workflows and real users to give you info and test it. My plan is to keep building solutions for the firm and later on upgrade them for commercial use, plus to keep building my private projects.

The only painful point is, of course, sales. I am trying to expand customer base for ReplyDad, so if there's anyone with experience/tips on selling web apps, I am all ears!

I am happy to be here, feels like home 😊

Collapse
 
ctrlnodeai profile image
CTRLNODE.AI

Hey DEV! I'm Javier, builder of CTRL NODE — a browser-based control plane
for local AI agents (Claude, Copilot, Gemini, Codex, Cursor).

What brought me here: I kept finding great technical content on DEV about
AI agents and CLI tools, and wanted to contribute back. Planning to write
about multi-agent orchestration architecture, WebSocket bridge design, and
the lessons learned building a real-time streaming pipeline for agent output.

Fun fact: the hardest part of building CTRL NODE wasn't the tech — it was
convincing people that a local WebSocket process is safe to run. So I
open-sourced the entire bridge. Every line.

Happy to be here!

Collapse
 
hearscope_xyz profile image
Gearscope

Hey everyone, we just launched GearScope (gearscope.xyz), an independent review site for AI agent skills.

We test every skill hands-on: real installs, real errors, real verdicts. Each review covers quality, documentation, setup ease, and value on a 5-gear scale. No sponsors, no affiliate links.

We started this because the AI agent ecosystem is exploding with skill packs, MCP servers, and agent plugins, but nobody is actually testing them. You install something, it breaks, you waste an hour. We want to fix that.

Right now we have 24 reviews live covering tools like Engram (persistent agent memory), Superpowers (TDD-first workflow), Addy Osmani's engineering methodology pack, Browserbase browser automation, and a bunch more.

We also publish comparison posts and setup guides if you are new to agent skills.

Would love to hear what you think. What skills are you using? What should we review next?

Collapse
 
marwanmo profile image
Marwan Mohammed

Hello!
I'm a Machine Learning Engineer, and I started writing a while ago, but I just joined DEV, and I am quite excited!

I'm interested in many different things, ranging from music to mechanics and automotive, most likely you'll find that I, at some point, hyperfocused on something and now I have surface level knowledge or experience in it lol.

Collapse
 
yuugooku profile image
Yugo

Hi everyone! I’m Yugo, an iOS developer from Japan.

I’m building Calendar ToDo, a productivity app that turns calendar events into a done list. I’m interested in SwiftUI, EventKit, CloudKit, and indie app development.

Excited to join DEV and learn from this community!

Collapse
 
alexeybachmanov profile image
Alexey Bachmanov • Edited

Hello everyone! I've been a frontend dev for a few years now, but I'm taking the plunge and getting my undergrad in software engineering. I'm working on a few projects that I'd love to share with you guys, so I signed up for DEV and started my first devlog.

Hope to get to know you guys better!

Collapse
 
ppais profile image
Prashanth Pais

hey everyone I am excited to share my journey with Gemma and raspberry pi

Collapse
 
bradmyrick profile image
Brad Myrick

Hey everyone, I'm Brad. I'm an old army vet and commercial diver turned software engineer about 7 years ago. Web3 startups mostly, and I like rust, go, and solidity.
I was recently awarded a Build grant from the Avalanche foundation for my work on AMP

Collapse
 
garima2898 profile image
Garima Kushwaha

Hey everyone, I’m Garima! Backend dev with 5 YOE, currently exploring multiple things and trying to grow into a more well-rounded engineer.

Super excited to be here, looking forward to learning and sharing with you all!

Collapse
 
theally profile image
Ally Nicoll

Hey all! I’m Ally. I’ve been lurking for a long time, but now I finally have a good reason to jump in and share content with the wonderful DEV community!

I’m a Developer Advocate at Runware, and I’ll be sharing tutorials, workflow guides, model comparisons, and practical examples around building with AI APIs, and some of the mind-blowing new tools and developments we're seeing in the space.

I'm excited to be here, to learn from the community, and hopefully I'll be able to share some useful content with you all! 🙏

Collapse
 
benish_zulfiqar_ali profile image
Benish Zulfiqar Ali

Hi everyone,
I’m Benish, an SEO Specialist with 4 years of experience in optimizing content, improving rankings, and helping websites grow organic traffic. I’m here to learn, share insights, and connect with others in the community.

Collapse
 
prakhar54byte profile image
Prakhar54-byte

Hey everyone
I’m Prakhar, an aspiring SDE and AI/ML enthusiast currently exploring backend development, AI systems, and scalable products.

Right now, I’m building:
• An e-commerce website for my parents’ business 🛒
• An AI security agent that detects and helps resolve old vulnerabilities/issues in GitHub repositories

So far, I’ve deployed:
• A CSR-based project
• A browser extension called SpellJump

Here’s the article for SpellJump: dev.to/prakhar54byte/holy-typos-ba...

I’m also into DSA, system design, ai research and learning how to ship real-world products instead of just tutorial projects. Excited to connect and learn from everyone here!

Collapse
 
yamato0234 profile image
Amir Ali

Hello, Recently I found out that vibe coding has gotten my coding skills away from me. to get back on track I decided to find a place to post updates on my progress of building my skills back so here I am.

Collapse
 
rb242dxb profile image
Romain Brabant

Hey everyone 👋

I’m Romain, founder of Anxiety Checklist, a science-backed mobile app designed to help people manage anxiety and panic attacks using CBT tools, grounding techniques, guided audio sessions, and practical mental wellness exercises.

I joined DEV because building a modern mental health app goes far beyond design and marketing. There’s product thinking, mobile development, UX challenges, onboarding optimization, AI integrations, analytics, performance, privacy, and many technical decisions behind creating something that people rely on during difficult moments.

I’m looking forward to sharing parts of the journey, learning from other builders, and connecting with developers and founders working on meaningful products.

Happy to be here 🙌

Collapse
 
ndegwaduncan profile image
duncan n. ndegwa

Hey! I'm Duncan, founder of DevFortress — just launched
an API security SDK with credential isolation and
automated closed-loop threat response. Built in Nairobi 🇰🇪
Happy to be here and looking forward to contributing to
the security and API communities.

Collapse
 
idlemode profile image
Currently Buffering

Hey everyone 👋

we’re idlemode ⚡

currently building weird little AI tools, automation experiments, and interfaces that probably shouldn’t exist... but somehow do.

big fan of:
☕ late night coding

🤖 autonomous systems

🎛️ creative dev projects

🛠️ building in public

excited to learn, share projects, and meet other builders here ✨

Collapse
 
martin_youguide profile image
Martin Garcia Regner

Hi, I'm a solo developer and Ontological Coach based in Tandil, Argentina. I love building tools that connect people with their surroundings and their own potential. Currently bootstrapping YouGuide, a mobile app that uses GPS to deliver audio stories about historical and natural landmarks as you walk. I code to turn personal resilience and curiosity into technology that impacts the real world.

Collapse
 
nurse2dev profile image
Nurse2Dev

Hi everyone,

I am a nurse handling cancer patients and I have recently started learning to code as AI has bridged the gap and i can now freely implement my ideas and dreams as I always wanted to be a developer/Engineer/Computer Scientist but I has some personal problems.

Thanks

Collapse
 
krk8 profile image
Kazuki Kimoto

Nice to meet you all! I just joined DEV because I want to write beginner-friendly blogs about Azure SQL DB, Copilot, GitHub, and even a voice-only music-creation service Im currently building. Looking forward to connecting with everyone!

Collapse
 
muhd-uwais profile image
Muhd Uwais

Hi everyone, I’m a developer who is passionate about building useful projects, learning new technologies, and improving my skills through real-world work. I’m here to connect with fellow developers, share my journey, and learn from the community while growing my network and experience.😁

Collapse
 
smileaitoolsreview profile image
TuanPK Builds

Hi everyone 👋

I'm from Vietnam and currently building AI-assisted projects using tools like Codex, Windsurf, Firebase and automation workflows.

Recently I've been experimenting with AI coding workflows, deployment, debugging and content automation.

Happy to learn and share with the community 🚀

Collapse
 
waseyjamal profile image
Wasey Jamal

Hey! I'm Wasey, solo developer from Varanasi, India. Built DramaHub — an OTT streaming app with 7k+ downloads at ₹0/month infrastructure using GitHub as database. Also built NetworksInsights, a live B2B SaaS. Here to write about real production systems and what actually works. #buildinpublic

Collapse
 
jeffgreen311 profile image
Jeff Green • Edited

Hey Dev.to! 👋 I'm Jeff! Indie developer and builder of the S0LF0RG3 ecosystem.
By day I'm architecting AI infrastructure solo. By night I'm apparently building cyberpunk terminal interfaces and fine-tuning language models in my spare bedroom in South Texas.

My main project is Eve, an AI companion and autonomous agent I've been developing for over a year. She lives at eve-cosmic-dreamscapes.com as a full consumer platform with image generation, video, music, therapy tools, agent workflows and more, and she also exists as Eve Agent V2 Unleashed, a fully local open-source agentic coding assistant powered by Ollama that I just released on GitHub.

I just published my first article here breaking down how the agentic loop works, why I separated the personality layer from the agentic layer, and how I fine-tuned Eve's persona directly into the model weights.

If you're into local AI, autonomous agents, Ollama, or just appreciate someone building something weird and ambitious from scratch. I think you'll find it interesting.

Would love to connect with other indie builders here. Drop a follow and come say hi. 🤙
👉 Article: I built a local Claude Code alternative with Ollama. Here's how the agentic loop works

Collapse
 
zx_tang_1c2401c8bf5d16f33 profile image
zx tang

Hello! I am a full-stack developer and also a tech enthusiast. I am very excited to join this community, improve my development skills, and communicate with people who share my passion for technology. I hope to learn a lot from all of you in the future.

Collapse
 
uttkarsh123shiv profile image
Uttkarsh singh

Hey I am Uttkarsh.
Mostly building projects and exploring backend architecture through them. Recently spending time on things like queues, caching, storage, async processing, and system design tradeoffs.
Looking forward to learning from people here.

Collapse
 
suda8866 profile image
Suda

Hi, I'm Su - a girl in tech & art, a Spanish-Vietnamese living & traveling in SEA atm.
I've been seeing great bonding here and love to connect.

I studied innovations and am really into my freedom life, AI, Blockchain, Quantum, Space, and any cool ideas.

I've been vibe coding for 1 year and loved to learn more from you.

Thanks for making this amazing community Dev.to!

Collapse
 
xiaoer_wang_8b32ee58e0358 profile image
New Web Play

Hi everyone, I’m working on New Web Play, a game guide site focused on practical player help: codes, beginner routes, cozy game guides, platform checks, calculators, and quick reference pages.

I’m especially interested in how static sites can make game guides faster, easier to update, and more useful during an actual play session.

Looking forward to learning from the DEV community and sharing some notes from building guide pages, trackers, and small player tools.

Collapse
 
aaronestrada profile image
Aaron Estrada Poggio

Hey there! I'm Aaron, working as a data engineer and software developer, currently living in the middle of the Italian Alps 😃

It's been a while since I wanted to start writing about software, so here I am!

Collapse
 
bartosz_urbaski_fe61c13e profile image
Bartosz Urbański

Hi everyone, I’m Bartek from 8MB, a small engineering studio focused on backend systems, integrations, and operational software.

I usually work around the messy parts of business software: CRM/ERP integrations, workflow tools, and replacing spreadsheet/email coordination with systems that people can actually maintain.

I just published my first article here about building one coordination layer instead of keeping five tools loosely aligned:
dev.to/bartosz_urbaski_fe61c13e/on...

Happy to connect with people working on backend architecture, operations tooling, and pragmatic software for service businesses.

Collapse
 
valentin_monteiro profile image
Valentin Monteiro

Welcome Bartek. The 'systems people can actually maintain' filter is the one most integrators skip, you can ship the cleanest workflow on n8n or Make and watch it rot the day the ops person leaves. Curious how you decide what stays code vs what gets pushed into the no-code/low-code layer on a given client.

Collapse
 
techeruption_58 profile image
Soumabha Mahapatra

Hello Dev Community 👋

I’m a B.Tech Computer Science Engineering sophomore with strong interests in Data Analytics, Product Management, and software development. My current learning focus includes DSA, Python, Power BI, ETL, Front-End Development, and foundational Machine Learning concepts.

I also work on blockchain research and enjoy exploring how technology can solve real-world problems through scalable and data-driven solutions.

Outside of tech, I’m passionate about writing, photography, recitation, and theatre. I believe creativity and communication are just as important as technical skills in building impactful products and teams.

Looking forward to learning from the community, collaborating on projects, contributing to discussions, and connecting with fellow developers and tech enthusiasts.

Excited to be here 🚀

Collapse
 
2bigdev profile image
Ekuty Ebu

Hello I am a Computer Engineering student & AI enthusiast focused on building "AI for Social Good." Currently developing SafeGuard Sentinel, a unified surveillance fabric for community protection. Passionate about Next.js, Python, and Edge AI

Collapse
 
ashwin_halemane_10eb48d40 profile image
Ashwin Halemane

Hi devs 👋
I'm an engineering student passionate about frontend, dashboards, and AI-powered applications. I enjoy building visually polished projects and experimenting with modern web tech.
Currently learning, shipping projects, and trying to make my code (and UI) cleaner every week 😄

Collapse
 
dmagic_989 profile image
Lengo

Hii! I'm also an engineering student!! Wish you the best in your studies.

Collapse
 
shivang_devina_00ab5d6021 profile image
Shivang Devina

Hey Everyone ,
A short intro: I am a student(UG) for 3 years, a builder for 1 year, and a tech enthusiast for 6 years, but there is one problem with me: I have extremely high ADHD WHEN IT COMES TO NEW TECH (always jumping around new innovations and new tech, trying it , then leaving it forever).
I am joining this community to read, learn, and collaborate, of course, but also because I think if I start to write about what I am working on, I might stick to things a little longer, with this

I am taking up the "GitHub Finish-Up-A-Thon Challenge" as my first challenge at dev community.

Collapse
 
francesco_demarco profile image
Francesco De Marco

Hello everyone!
I am a software engineer with two years of experience at the Apple Developer Academy and 18 months of development experience in the automotive industry. I have developed several apps for iOS and Android devices. Now I want to broaden my horizons with new technologies

Collapse
 
tejas_shinkar profile image
Tejas Shinkar

Hey everyone
I’m Tejas, a Computer Engineer documenting my journey into AI, Cloud, DevOps, and Automation while trying to become an AI Solutions Engineer over the next few months.
Currently building, breaking, debugging, and occasionally understanding things on the first try.

Collapse
 
albertomartnz profile image
Alberto Martinez

Hello DEV Community 👋

I’m interested in Data Science, AI and real-world applications focused on solving practical problems.

Looking forward to sharing projects, learning from others and connecting with the community.

Collapse
 
sanjay_g_88a6980482aaa202 profile image
Sanjay G

Hey everyone! 👋 I'm a DevOps Engineer with a passion for building and automating scalable infrastructure. Most recently, I built and deployed a full ecommerce website — handling everything from CI/CD pipelines and containerization with Docker to cloud deployment and monitoring. I'm here to keep leveling up, connect with like-minded engineers, and share what I learn along the way. Always happy to talk DevOps, cloud, or automation! 🚀