Typescript, Python, LLMs, evaluation methods, AI agents, AI limitations

Personalization Strategies, Product Management, Stakeholder Management, LLM Initiatives, AI-driven Products, Search Recommendation Algorithms

Integrations, User Research, Requirements Analysis, System Architecture, Solution Design, AI products, Microsoft Teams, project management, LLMs, AI Agents, B2B SaaS enterprise software, PRD development, api documentation, engineering coordination, workflow automation, enterprise AI applications, AI product development, data flows

product analytics tools, fine-tuning, modern AI capabilities, LLMs, product management, experimentation, RAG, AI ML products

Software Engineering, Ui Ux Design, LLM-based systems, MCP Memory, Claude, Multi-Agent, CI CD, platform engineering, Context Engineering, evaluation systems, Subagent, Manus Codex, autonomous workflows, Tool Use, Source Control, KV Cache, Agile development practices, Agent Loop, Code Cursor, GitHub Copilot, building testing frameworks, Reasoning, Cowork, Planning, AI agents, agent products, Prompt Engineering, LLM API, developer tooling

user interviews, qualitative evidence, product data, delivery effort, Product Design, success measures, product experiments, user journeys, Product Development, AI agents, customer discovery, technical capability

Databases, Apis, Workflows, Distributed Systems, System Architecture, AI products, Insurance, Trading, LLMs, Payments, failure modes, Privacy, third-party partners, Banking, Regulatory Requirements, financial rails, Kyc, Remittance, Transaction Monitoring, limits, Licensing, evaluation frameworks for ML or LLM-powered products

Devops, Cursor, Code, Testing platforms, AI Agents, Codex, Copilot, Claude, AI Native engineering platform, Deployment environments, AI Coding, Knowledge platforms

Excel, Powerpoint, LLM applications, prompt engineering, AI solutions, RAG architectures