#llm-engineering

7 Articles

All posts tagged with #llm-engineering

LLM EngineeringFeb 17, 20267 min read

Prompt Engineering at Scale: From One-Off Prompts to Managed Prompt Systems

The first prompt you write for a production system is a string in your code. The fiftieth prompt is a liability if it changes without testing, if it diverges be...

#prompt-engineering #llm-engineering #prompts #production #ai-infrastructure

Agentic SystemsJan 22, 20267 min read

Multi-Agent Orchestration: Task Routing, Approval Flows, and State Handoffs

A single agent trying to do everything is both expensive and fragile. Expensive because you're running a general-purpose model with a large context window for t...

#multi-agent #orchestration #agentic-systems #llm-engineering #task-routing

AI InfrastructureJan 8, 20266 min read

Observability for AI Agents: What to Monitor When Your Code Calls an LLM

When a traditional API call fails, you check the status code, look at the error message, and fix it. When an LLM-powered agent produces a wrong answer or behave...

#observability #langfuse #ai-agents #monitoring #ai-infrastructure #llm-engineering

LLM EngineeringNov 19, 20257 min read

Tool Calling Patterns for Reliable AI Agents: Error Handling and Fallbacks

Tool calling is the part of LLM applications where the model makes decisions that have real-world effects. When it goes wrong and it will the agent either produ...

#tool-calling #ai-agents #llm-engineering #error-handling #reliability

LLM EngineeringNov 5, 20256 min read

LLM Structured Output Validation: From Fragile Strings to Typed Schemas

Every LLM integration starts the same way: you ask the model to "respond in JSON" and then write a JSON.parse() call to get the data out. This works in developm...

#llm-engineering #structured-output #typescript #zod #openai #validation

LLM EngineeringOct 22, 20256 min read

Python for TypeScript Engineers: Building AI Systems Across Both Ecosystems

I spent 15 years writing TypeScript. Then AI happened, and a significant fraction of the tooling, research implementations, and production frameworks I needed t...

#python #typescript #llm-engineering #ai-development #crossover

Agentic SystemsOct 8, 20256 min read

The Software 1.0 → 3.0 Shift: What It Actually Means for Engineers

In 2017, Andrej Karpathy wrote a post called "Software 2.0" that described a shift in how we write software. Instead of writing explicit instructions (Software ...

#software-paradigm #ai-engineering #agentic-systems #career #llm-engineering

All Tags

#ai-tools (17)#ai-agents (12)#claude-code (12)#ai-engineering (11)#developer-productivity (9)#llm-engineering (7)#mcp (6)#production (6)#llm (5)#automation (4)#productivity (4)#agentic-systems (4)#career (3)#ai-infrastructure (3)#typescript (3)#multi-agent (2)#orchestration (2)#developer-tools (2)#cursor (2)#rag (2)#architecture (2)#nextjs (2)#reliability (2)#2026 (1)#agent-architecture (1)#subagents (1)#ai-strategy (1)#enterprise-ai (1)#ai-adoption (1)#change-management (1)#ai-coding (1)#code-quality (1)#technical-debt (1)#vibe-coding (1)#ai-kit (1)#open-source (1)#cli (1)#portfolio (1)#hiring (1)#skills (1)#vector-database (1)#workflows (1)#protocol (1)#chatbot (1)#tutorial (1)#agentic-workflows (1)#solo-developer (1)#langchain (1)#crewai (1)#frameworks (1)#claude-cowork (1)#marketing-automation (1)#prompt-engineering (1)#prompts (1)#web-apis (1)#browser (1)#development-pipeline (1)#react (1)#ollama (1)#local-llm (1)#task-routing (1)#hooks (1)#async-agents (1)#observability (1)#langfuse (1)#monitoring (1)#ai-workflow (1)#frontend-development (1)#sitecore (1)#jss (1)#content-sdk (1)#xm-cloud (1)#migration (1)#headless-cms (1)#multi-tenant (1)#i18n (1)#predictions (1)#copilot (1)#memory (1)#vector-databases (1)#tool-calling (1)#error-handling (1)#developer-experience (1)#debugging (1)#structured-output (1)#zod (1)#openai (1)#validation (1)#python (1)#ai-development (1)#crossover (1)#software-paradigm (1)#code-review (1)#github-copilot (1)#development (1)