Skip to content
View bradleybeatz1313's full-sized avatar

Block or report bradleybeatz1313

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bradleybeatz1313/README.md

Brad Barroso

AI engineer and founder. I run agents in production, unattended, every day.

Portfolio: bradleybarroso.dev — 66 case studies, each with a live demo, an architecture diagram, and the evidence behind every claim.


What I build

  • Autonomous, self-healing agent systems that ship real work while I sleep: 11+ live agents, nightly pipelines, zero-touch operation. The Overnight Foundry builds, verifies, and deploys a new product every night.
  • Reliability engineering for agents. Locking, snapshots, rollback, verification gates, and evals. I treat flaky models the way a backend engineer treats flaky services.
  • Orchestration and tool use. Routing between specialists, wiring MCP tools, and giving a whole system one dependable entry point.

Ventures

AiVoicePhone Founder A 24/7 AI receptionist that turns missed calls into closed deals for small businesses. Case study →
TreCal Media Group Founder An AI agency delivering automation, lead generation, and customer-communication systems to realtors and small business owners. Case study →

Featured public work

Project What it does Links
AI Code Judge Runs AI-generated code candidates against tests, scores them on a weighted rubric, and explains the verdict. Live · Source · Case study
Smart Money Tracker Real-time whale prints, sharp-wallet activity, and ranked smart-money consensus across Kalshi and Polymarket. Live · Source · Case study
Prompt Injection Canary A transparent prompt-injection canary with privacy-bounded request logging. Live · Source
NeighborProof Postcards Approval-controlled postcard automation for outdoor-trade contractors. Live · Source
T3MP3ST An autonomous red-teaming platform: a multi-agent offensive-security meta-harness. Source
Prompt Optimizer Automatic prompt engineering for Claude with a 14-technique optimization framework, benchmarks, and templates. Source

Most production case studies ship from private repositories. The full index links every live system, and source is available on request.

Stack

Claude / Claude Code · MCP tool integrations · Next.js / TypeScript · Scheduled cloud routines · Notion as data layer · GSAP · Three.js · Stripe · Gmail · Ahrefs APIs · Custom CLI harnesses

Hardware and EDA

Before agents, circuits. I design, simulate, and validate PCBs with open-source EDA tools, and I build datasets from those simulations for AI training.

Project Tools Description
IoT Sensor Board KiCAD 8 4-layer ESP32-S3 environmental monitoring PCB
Analog Simulations Ngspice Parameterized analog circuit library
RF Analysis Suite Qucs-S LNA, bandpass filter, and mixer designs with S-parameter characterization
Motor Driver Board LibrePCB Dual H-bridge BLDC motor driver with current sensing and protection
EDA-AI Pipeline Python + Ngspice Automated netlist generation and labeling for circuit AI training

bradleybarroso.dev · LinkedIn · Open to AI engineering roles.

Pinned Loading

  1. prompt-optimizer prompt-optimizer Public

    Automatic prompt engineering for Claude - Desktop and Code editions. 14-technique optimization framework with benchmarks and templates.

    Python 1

  2. kicad-iot-sensor-board kicad-iot-sensor-board Public

    4-layer ESP32-S3 IoT environmental sensor PCB — KiCAD 8

    2

  3. awesome-agents-md awesome-agents-md Public

    The Rosetta Stone for AI coding agents — production configs for every popular stack

    2

  4. ai-undetectable ai-undetectable Public

    TypeScript 1

  5. ai-code-judge ai-code-judge Public

    Structured toolkit for evaluating and ranking AI-generated code — runs candidates against tests, scores them on a weighted rubric, and explains the verdict.

    Python 1

  6. polymarket-whale-watch polymarket-whale-watch Public

    Real-time Polymarket whale trade tracker — live feed, herd signals, leaderboard, trader drilldown

    TypeScript