AI Blog
Deep dives into AI Agents, Agentic RAG, and the future of autonomous software development.
TechLangSmithPrompt ManagementAI EngineeringLangChainProduction AI
Stop Deploying to Fix a Bad Prompt - Use Prompt Hub
Hardcoded prompts have no rollback path. LangSmith Hub gives you push/pull versioning, tag-based promotion, and runtime updates without redeployment.
Simon BudziakCTO
TechLangChainPrompt CachingCost OptimizationAI EngineeringProduction AI
Prompt Caching Across Claude, GPT, and Gemini = Stop Paying for the Same Tokens Twice
Cut LLM API costs up to 90% by caching repeated context. How prompt caching works across Claude, GPT, and Gemini - and when it doesn't.
Simon BudziakCTO
TechLangChainContext ManagementAI EngineeringProduction AILLM
Model-Aware Context Management with LangChain's model.profile
Stop hardcoding context limits. Use LangChain's model.profile to drive dynamic summarization and capability gating based on the actual model.
Simon BudziakCTO
TechLangChainLangGraphLangSmithPre-Production AIAgent SkillsMulti-Agent Systems
Building a Real-World Pre-Production LangGraph Agent with LangChain Agent Skills
Building a pre-production research agent in 6 days using langchain-agent-skills—production-ready patterns for state, errors, deployment.
Simon BudziakCTO
BusinessAI StrategyPoC DevelopmentAI AgentsAI ROICost ReductionRapid DevelopmentLangChainBusiness Value
How We Made AI Agent PoCs 87% Cheaper in 6 Days Instead of 3 Months
Most companies burn $100K+ and 3-4 months on AI agent PoCs. We deliver the same value in 7 days for $16K. Here's the business model that makes it possible.
Bart LuderaCEO
Use caseLangSmithAgent BuilderMCPProduction AIAI Tools
LangSmith Agent Builder + MCP: What Worked, What Broke
A practical breakdown of building production agents with LangSmith Agent Builder and MCP tools—where the promise met reality, and how to actually get MCP tools working.
Bart LuderaCEO
TechLangChainLangGraphLangSmithAI AgentsProduction AIClaude CodeOpen Source
Agent Skills for LangChain: Making AI Assistants Context-Aware
An open-source collection of production-ready skills for building LangGraph agents with Claude Code, Codex and other AI assistants.
Simon BudziakCTO
TechLangGraphAgent LightningLangSmithAI AgentsProduction AIPrompt Optimization
Optimizing LangGraph Agents with Agent Lightning and APO (Automatic Prompt Optimization)
How to optimize LangGraph agent prompts using Microsoft's Agent Lightning framework with APO, including real integration challenges and solutions.
Simon BudziakCTO
BusinessLangChainLangGraphLangSmithAI AgentsMeetupPolandWorkshop
First Official LangChain Meetup in Poland: AI Agents Workshop in Krakow
Join us for the first official LangChain x Lubu Labs meetup in Poland. Hands-on LangGraph workshops, production best practices, and networking with AI builders in Krakow on February 19th.
Bart LuderaCEO
Use caseLangGraphLangSmithHealthcare AIProduction AIMedical ComplianceAI SafetyLangChain
Shipping a Clinical-Grade Patient Education Agent: Why Observability is Non-Negotiable in Healthcare AI
How we built an AI agent to help patients understand their health test results, and why LangGraph's explicit control flow and LangSmith's audit trails made it shippable in a regulated environment.
Simon BudziakCTO
BusinessAI AgentsE-commerceAgentic CommerceLangChainAI Automation
9 AI Agent Use Cases Reshaping E-commerce in 2026
How autonomous AI agents are transforming e-commerce through personalization, support automation, and agent-to-agent commerce—moving beyond chatbots to active participants in the customer journey.
Bart LuderaCEO
Use caseLangSmithLangChainProduction AIObservabilityLLM EvaluationAI Agents
Shipping an AI SDR Chatbot with LangSmith: What Actually Helped in Production
A real-world story of deploying an AI SDR chatbot for a loyalty platform - and how LangSmith traces, feedback, and evaluations made it shippable.
Simon BudziakCTO
BusinessAI EngineeringEnterprise AIProduction AILLMsAI AgentsVC Insights
Enterprise AI in 2026: From Hype to Hard Value
Why 2026 may finally be the year enterprise AI moves from experimentation to measurable business value, and why most vendors will not survive the transition.
Bart LuderaCEO
TechAI EngineeringLLM FrameworksProduction AILangChainLangGraphLlamaIndexRAG
AI Framework vs. Custom Stack: What Actually Works in Production?
A pragmatic guide to choosing between AI frameworks versus building custom orchestration for production-ready AI systems.
Simon BudziakCTO