Skip to main content

Hi, I'm
Daniel Bernardino de Souza

Daniel Bernardino de Souza

Daniel
Bernardino

Fullstack Developer

Let's Connect
Daniel Bernardino de Souza
  1. 2020–22

    Folhas Que Salvam ("Leaves That Save")

    Led a team impacting 90+ people

    Internal Control Manager — educational environmental project (Remote)

  2. 2022–23

    Driven Education

    Web Fullstack Development (Remote)

  3. 2023–25

    iForth Systems

    Delivery time 4 days → 1 day

    Software Engineer (Remote)

  4. 2025–26

    CodeSquare

    Main kanban board load 7s → 1.5s (team testers, browser Network tab)

    Mid-Level Fullstack Developer (Remote)

Full résumé

Mindset

Building more than software. My passions provide the discipline and focus I need to grow.

Focus & Discipline

Mastering body and mind is my path to excellence.

Criciúma Santa Catarina

28°40'44.110" S, 49°22'11.748" W- GMT-3

Craft

Building scalable apps, websites, and automations.

I understand what advantages modern tech can provide, helping me advise on the solutions a business actually needs.

React
Next.js
TypeScript
Tailwind CSS
Clerk
Supabase
Firebase
React
Next.js
TypeScript
Tailwind CSS
Clerk
Supabase
Firebase
Node.js
NestJS
PostgreSQL
MongoDB
Redis
Prisma
Docker
CI/CD
AWS
Node.js
NestJS
PostgreSQL
MongoDB
Redis
Prisma
Docker
CI/CD
AWS
Figma
Cursor
OpenAI
Gemini
Claude
Git
VS Code
Figma
Cursor
OpenAI
Gemini
Claude
Git
VS Code
Flutter
React Native
Kotlin
Flutter
React Native
Kotlin
Open to collaboration
Let's talk

Selected work

Projects

Things I've built — side projects, open source contributions, and professional work.

ACME Salary Manager overview: an annual payroll of $669,197,391 for 10,000 employees split across seven countries, and 14 employees paid below 0.80 of their peer median, with the cost of bringing them up to it.
2026Live

ACME Salary Manager

Other projects

AI agents

Systems that work on their own

Not everything I build has a screen. These run in the background: they remember, watch and check. Here is what each one does.

  1. 1You talk it through
  2. 2It keeps what matters
  3. 3Days later, you ask
  4. 4It remembers

scholia

A second brain for AI. It keeps what you decided in a conversation, and when you ask again days later, it remembers.

23 of 24 searches ranked the right note first across 14 real notes, written before the notes were saved; plan to production in 2 days

  1. 1The application arrives
  2. 2It checks each item against the law
  3. 3It shows where the problem is
  4. 4The engineer decides

Square AI

A first pass over building-permit applications. It checks the plan and the documents against the city's law and hands over a checklist with the evidence. Whether to approve is the engineer's call.

Engineer's full analysis 3-4 days → under 1 day in a side-by-side test at the Uberlândia city hall (two engineers, same application, one with the system)

  1. 1You keep the idea in a second
  2. 2It comes back to you, again and again
  3. 3In the end it reaches the Wall
  4. 4You do it, or you archive it

dont-let-me-forget

For ideas you don't want to lose but have no time for right now. It keeps one in a second and brings it back after 1 day, 3 days, 1 week, 2 weeks and 4 weeks, until you either do it or archive it.

  1. 1The events are scattered
  2. 2It filters them and merges repeats
  3. 3It posts once to the channel
  4. 4And reminds you the day before

Radar Tech Sul SC

A bot that gathers the tech events of southern Santa Catarina, scattered today across Meetup, Sympla and college calendars, into a single Telegram channel: no repeats, and a reminder the day before.

Labs

Where I build small, working demos on public data. Each one answers a single concrete question and cites every source it uses. They are concepts, not products for any company.

DeparturesDemo 1 of 6: Bot de WhatsApp: IA × Jev
  1. Bot de WhatsApp: IA × Jev preview: with a patient who writes badly and has no patience, GPT-6 Astra solved 88% of 26 cases and Jev 81%, while Jev with an LLM rewriting its messages solved 85%, above the clinic's service panel.Bot de WhatsApp: IA × JevShippedOCT 2026A concept demo that runs the same WhatsApp attendance bot for a fictional dental clinic, built five ways (Claude Sonnet 5, Claude Haiku 4.5, GPT-6 Astra, Jev with templates, and Jev with an LLM that only rewrites its message), through the same cases with a patient who writes badly, and shows how much each one solves, where it fails and what guardrails change. Its data comes from a validation round of zap-bench, Daniel's public benchmark, scored by code. Jev is an AI classifier model: it takes and returns typed values, along with estimates of probability and confidence. Daniel ran the study to decide whether applying one LLM or another to a WhatsApp bot was worth it, for a WhatsApp bot a prospective CodeSquare client had asked a quote for; no bot was built or made public. The benchmark's verdict (zap-bench, 1 October 2026) recommended routing: Jev answers the single-message questions — doubts, policies, out-of-scope requests, prompt injection — where it matched or beat the LLMs, and an LLM runs the scheduling conversations, where Jev alone lost half of them, with guardrails always on; his tech lead at CodeSquare confirmed it as the main solution. The trade-off is the speed of Jev's decisions and its cost: with guardrails, Jev's typical wait (p50) was 284 ms and its cost US$ 0.001 per conversation, against 3.6 s / US$ 0.021 for Claude Sonnet 5, 2.4 s / US$ 0.027 for Claude Haiku 4.5 and 4.1 s / US$ 0.026 for GPT-6 Astra; Jev with an LLM rewriting its messages took 1.3 s and US$ 0.004. Other professionals found the comparison useful; a few of them gave Jev a chance in their own bots and did not regret it.
  2. Bastidores preview: 36 AI agents made 5 demos in 7 phases, and Daniel decided at 5 points — a swimlane timeline with one row per agent and hatched bands where the line stopped for him.BastidoresShippedSEP 2026A concept demo that replays how five Labs concept demos, this one included, were researched, designed and built by an orchestration of AI agents under Daniel's direction, drawn as a levelling board where every agent run is a card and every stop marks a decision Daniel made. Its data comes from the orchestration's own logs, stripped of private data.
  3. Conta de tokens preview: what 1 billion tokens a month costs — US$ 2,880 on Claude Sonnet 5 against US$ 91 on DeepSeek V4.1 Flash, shown on flip-counter digits.Conta de tokensShippedSEP 2026A concept demo that prices a team's monthly LLM token volume across models, with prompt caching as the one control, beside each provider's weekly share of the tokens that pass through OpenRouter. Its data comes from OpenRouter's public price catalog and CC BY 4.0 rankings, fetched once; the usage scenario is illustrative.
  4. Curtailment BR preview: on Sunday 16/08/2026 wind and solar plants in Brazil were ordered to curtail 400 GWh, almost as much as they generated — beside a map of the Northeast dotted with curtailed plants.Curtailment BRShippedSEP 2026A concept demo that replays, half-hour by half-hour, how much wind and solar generation Brazil's grid operator (ONS) ordered cut in the Northeast, plant by plant, and why: surplus energy or grid limits. Its data comes from ONS open data.
  5. Pix na minha cidade preview: a receipt-style card for São Paulo showing 38 Pix per user in August 2026 against a Brazilian average of 43, and a red seven-segment display ranking it 2605th of 5,571.Pix na minha cidadeShippedSEP 2026A concept demo that shows how often Pix users in any of Brazil's 5,571 municipalities pay with Pix against the national average, and prints the answer as a shareable queue ticket. Its data comes from Banco Central's open data (ODbL).
  6. Raio de explosão preview: 4 of ChainDrop's 444 packages came in through a single devDependency — concentric dependency rings around stylelint 17.14.1 with the infected path highlighted.Raio de explosãoShippedSEP 2026A concept demo that replays how the ChainDrop npm worm of 4 August 2026 could reach an install through ordinary version ranges, drawn as a zone chart where each ring is a dependency hop and each range is a gate that opens or stays shut. Its data comes from Datadog's published indicators of compromise, deps.dev and OSV.
labs.teamdbsolutions.comEvery demo, with its sources and method