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: python
Orchestrate researcher and coder agents with LangGraph
Scaffold a LangGraph multi-agent app with soul prompts, Ollama models, Tavily search, handoff tools, and Postgres checkpoints for orchestrator-led workflows.
2200 wordsRead articleYour First Tool-Using AI Agent with LangChain
Build a small LangChain math agent in Python: initialize a chat model, register tools, let the LLM choose which function to call, and see multi-step tool use.
1062 wordsRead articleTyped Decision Models vs LLM Calls: Latency and Stability at the Boundary
A 240-call experiment comparing Jev's native probabilities with an LLM's self-reported ones, and how to turn that signal into a LangChain model router.
2630 wordsRead articleEnforcing Agent Rules in Code: PreToolUse, PostToolUse and Stop Hooks
Learn why authorisation for LLM agents belongs in deterministic tool-call hooks, how to deny calls safely, and how to wrap a dispatcher without recursion.
2721 wordsRead articleFrom Plain Text to Validated Objects: Picking a LangChain Output Parser
Compare StrOutputParser, JsonOutputParser, StructuredOutputParser and PydanticOutputParser in LangChain chains, and learn how much structure each one really guarantees.
5418 wordsRead articleServing a LoRA Fine-Tune Locally: Verify, Fuse and Avoid Silent Failures
Prove a LoRA adapter actually improved a small model, fuse and serve it behind a local OpenAI-compatible API, and catch the failures that return confident wrong output.
2570 wordsRead articleReviewing Large AI Refactors: Why Passing Tests Miss Deleted Intent
Learn why AI-assisted refactors silently remove load-bearing code, why green tests do not catch it, and five review practices that make large refactors safe to ship.
1618 wordsRead articleComposing Speech, Vision and Generation Models into Multimodal Apps
Learn the six building blocks of multimodal AI, how speech, vision and generative models chain into pipelines, and which open tools and projects to start with.
2531 wordsRead articleA Hand-Rolled LangChain Tool Loop for Comparing Live Stock Metrics
Build a small LangChain stock-comparison assistant step by step and learn the create, bind, invoke and execute loop that lets an LLM request live data instead of guessing.
1667 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.