Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: FastAPI
An Approval Dashboard for a Kubernetes Remediation Agent: FastAPI and React
Build a FastAPI backend with a kubectl allowlist and a React approval dashboard so an LLM remediation agent can fix incidents only after a human clicks Approve.
11 min readMulti-Agent Banking Flows on Kubernetes: LangGraph, a Registry and AgentGateway
Build FastAPI specialist agents, a LangGraph orchestrator with an LLM planner, deploy them to a cluster with a registry, then add routing and rate limits with AgentGateway.
17 min readGuarding Agent Tool Calls with Jev and LangGraph Before They Execute
Add pre-execution safety checks and post-execution completion review to a LangGraph agent, using Jev typed decisions to block risky actions like large refunds.
8 min readA RAG Project Is Not One Giant Python File: A Folder Layout That Scales
A RAG project shouldn't be one giant Python file. A folder layout for ingestion, chunking, embeddings, vector store, retrieval, prompts, API and tests.
9 min readBuild an AI Lead Qualification Agent in Python With FastAPI and Pydantic
Turn raw leads into qualified ones: structured LLM extraction, Pydantic validation, rule-based scoring, PostgreSQL storage, queues and a human review lane.
12 min readPython for a JS Dev: A Gmail and Calendar Agent With FastAPI and LangGraph
Learn Python by building a drafts-only personal assistant: FastAPI, Google OAuth for Gmail and Calendar, LangGraph tools, local Ollama models and SSE streaming.
10 min readParallel LangGraph Agents That Review Pull Requests via FastAPI Webhooks
How a webhook, Redis queue and four LangGraph agents turn a pull request into a scored, structured AI review in about 30 seconds, with ngrok for local testing.
12 min readAgentic RAG in LangGraph: Graders, Conditional Routing and Web Search Fallback
Move a linear LangChain RAG pipeline to a LangGraph StateGraph with LLM graders, conditional entry and edges, tests and a FastAPI endpoint that reports provenance.
7 min readMeasuring Real Value From an AI Incident Assistant, Not Guesswork ROI
Why AI-estimated savings mislead, and how baselines, controlled failures, evidence checks and blocked unsafe actions show whether an ops assistant helps.
10 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.