Research

Create a concise system prompt for a tool-using AI agent with clear boundaries and behavior.

Review an AI agent architecture for prompt injection, over-permission, and unsafe tool behavior.

Evaluate whether a RAG retriever is finding the right evidence before changing the model.

Choose a chunking strategy based on document structure and user query behavior.

Evaluate whether you need a vector database and what requirements should drive the choice.

Run a structured research process that triangulates sources and separates fact from inference.

Design or review a Django application using pragmatic production patterns.

Review React code for correctness, state design, performance, accessibility, and maintainability.

Review an API contract for clarity, consistency, security, and long-term maintainability.

Review a proposed software architecture for complexity, coupling, reliability, and evolution risk.

Turn requirements and code behavior into a risk-based test suite.

Turns a broad question into a rigorous research plan with subquestions, sources, and synthesis steps.

Codes qualitative material into themes while preserving evidence and uncertainty.

Builds an evidence-backed competitor landscape focused on strategy, product, and market signals.

Review code like a senior engineer, focusing on correctness, maintainability, security, and tests.

Diagnose slow PostgreSQL queries and recommend evidence-based fixes.

Design a fast, reliable CI/CD pipeline with safe promotion and rollback.

Design a production Azure architecture from workload, security, and operational requirements.

Review code for security vulnerabilities with exploitability and business impact in mind.

Investigate suspicious data and identify where quality problems enter the pipeline.

Create clear API documentation from an implementation or specification.