diegosouzapw

Establishes frontend standards for Next.js and React, guiding component development, state management, and UX best practices.

Facilitates comprehensive planning for various projects, focusing on technical and non-technical domains, ensuring structured execution.

Enhances UI with purposeful animations for Next.js, Tailwind, and React, improving user experience through effective motion design.

Creates accessible UI/UX design systems for SaaS apps, focusing on design tokens, component architecture, and responsive layouts.

Integrates with 200+ services using Apideck's Unified API for seamless data management across various platforms.

Guides development of cross-platform desktop apps using Tauri 2, TypeScript, React, and Rust, focusing on architecture and IPC.

Generates structured Product Requirements Documents for MÄÄK features, facilitating clear project planning and implementation.

Provides expert guidance for building Nock interpreters across multiple programming languages, optimizing virtual machine implementations.

Evaluates the effectiveness of care management programs by measuring clinical, utilization, and financial outcomes for informed decision-making.

Facilitates complex multi-agent workflows by delegating tasks to subagents, tracking progress, and generating summary reports.

Expertly designs and manages multi-agent systems, focusing on collaboration patterns and autonomous workflows for complex AI applications.

Provides patterns for building autonomous AI agents, including multi-agent systems and workflow orchestration strategies.

Facilitates the design and operation of multi-agent orchestration patterns for LLM systems, enhancing workflow flexibility and efficiency.

Generates structured AGENTS.md files for codebases, optimizing AI documentation and project setup for coding assistants.

Provides advanced multi-agent reasoning for complex questions, ensuring maximum accuracy through structured analysis and expert debate.

Provides operational patterns for optimizing LLM inference performance, cost, and reliability in production environments.

Covers the full lifecycle of LLM development, from strategy selection to deployment and operations, ensuring cost and safety controls.

Facilitates a multi-AI feedback loop for comprehensive validation and decision-making in complex engineering tasks.

Provides operational guidance for building production-ready prompts in LLM applications, focusing on structured outputs and safety.

Enables the development of advanced retrieval-augmented generation systems with hybrid search and evaluation techniques.