Topic · ai-engineering

AI Engineering

Turning LLMs, Agents, MCP, RAG, real-time voice, and model APIs into runnable, observable, and iterative application systems.

What This Topic Solves

This topic focuses on how model capabilities move from demos into real systems: context, tools, latency, failures, cost, and observability.

Who It Is For

For backend-capable builders moving into AI application engineering and Agent toolchains.

Recommended Reading Order

01 LLM Production Engineering

Start with the gap between demo and production

02 AI Voice Module

Then inspect a real-time voice path

03 LLM Application Series

Fill in RAG, Agent, and tool-calling foundations

Related Projects

AI Voice ModuleEdge-cloud voice intelligence module
AscendLabTool site and AI workflow preview
AI Infra HandbookAI Infra learning and practice handbook

Related Series

LLM Application DevelopmentRAG, agents, and tool calling
AI Engineering & ResearchAI industry and engineering observations

Existing Entries

Voice Interaction Latency

Voice-path performance entry

LLM Production Engineering

Engineering checklist before AI apps go live

What Comes Next

Add posts on Agent/MCP tool governance, tracing, evaluation, and cost control.
Turn AI Voice Module reviews into a clearer series entry.