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: llm
Prompt Engineering: Steer LLMs Without Fine-Tuning
Use roles, few-shot examples, chain-of-thought, and format constraints to guide models — and know when prompting alone hits a ceiling versus fine-tuning.
748 wordsRead articleTools vs Skills vs MCP: Three Layers of an AI Agent
Tools expose actions, skills encode workflows, and MCP standardizes external connections. A clear mental model for designing agent architectures without mixing the layers.
1495 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 articleJev: How a Non-Generative AI Model Turns Text Into Decisions
Learn how Jev's numeric "System One" AI model works, why it's faster and cheaper than LLMs, and where it fits alongside generative AI in production systems.
1629 wordsRead articleUnderstanding AI Agents: Tool Calling, MCP, and the Agent Loop
Learn how tool calling, MCP, and agent loops fit together to form the real architecture behind agentic AI systems, beyond the buzzwords.
3643 wordsRead articleSix AI Concepts That Tell You What to Check Before Trusting an Answer
Tokens, context windows, temperature, hallucination, RAG and agents explained as verification tools, so you can spot errors, control cost and judge AI product claims.
2235 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 articleDiagnosing LLM Output Problems: When to Prompt, Retrieve or Fine-Tune
A symptom-first way to decide whether a weak AI feature needs a better prompt, a retrieval layer or fine-tuning, and why training a model on facts backfires.
1607 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.