Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: gemini
Build a simple GraphRAG pipeline with Neo4j, Gemini, and LangChain
Schema-constrained kitchen-mishap graph extraction, neighborhood queries, multi-hop paths, and read-only text-to-Cypher with Gemini.
1626 wordsRead articleComposing LangChain Pipelines with LCEL: Linear, Parallel and Branching
Learn to wire prompts, models and parsers into linear, multi-stage, parallel and conditional LangChain pipelines with the pipe operator, RunnableParallel and RunnableBranch.
9373 wordsRead articleHardening a Python LangChain Agent with Seven Built-In Middlewares
Learn how LangChain 1.0 middleware adds summarization, call limits, retries, model fallback, PII redaction and human approval to a Gemini agent without touching its core logic.
2604 wordsRead articleRouting Questions Across SQL Tools and Web Search with a Gemini Agent
How a LangChain tool-calling agent on Vertex AI picks between three SQLite text-to-SQL tools and live web search, plus the data, dependency and auth bugs to expect.
2833 wordsRead articleLetting Gemini Pick the Source: FAISS, Tavily and Direct Answers in LangGraph
Build a small LangGraph workflow in which Gemini routes each question to a FAISS knowledge base, Tavily web search or a direct answer, with structured-output routing.
3771 wordsRead articleCalling Claude, GPT and Gemini Through OpenAI-Compatible Endpoints
See what the Anthropic and Gemini OpenAI-compatible layers support, where they silently drop features, and when routing all three through one gateway makes sense.
1812 wordsRead articleComparing Frontier AI Agents: Astra, Flash, Fable, and Mythos
A breakdown of how the latest GPT, Gemini, and Claude model releases perform on real agentic tasks like coding, browsing, and tool use, not just benchmarks.
2160 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.