Articles
In-depth articles on AI, web development, cloud native, and indie hacking.
Mid-month seat changes are not just the current seat count times the days remaining. This article freezes billing intervals, price versions, and seat events to make proration reproducible from non-overlapping segments, stable operation IDs, and provider receipts while handling unknown outcomes and post-invoice corrections.
What was this price last week? Ordinary tables keep only current values; temporal tables retain history. This article explains audit logs, versioned rows, valid-time ranges, PostgreSQL temporal extensions, the SQL:2011 standard, CDC alternatives, and when temporal tables are warranted versus when an audit log is enough.
A model's self-reported confidence does not make a reply safe, and a low human-escalation rate may simply indicate missed escalations. This article combines evidence sufficiency, risk tiers, queue capacity, and ownership generations into an evaluable policy for automated replies and human handoffs.
The best way to understand an Agent is to build a minimal one yourself. This under-100-line TypeScript implementation explains the ReAct (Thought → Action → Observation) loop, tool calls, stopping conditions, and error recovery.
HTTP 200 does not prove that AI output remains usable. This article turns fixed tasks into low-risk black-box probes, covering scoring contracts, isolated execution, OpenTelemetry metrics, Prometheus alerts, and false-positive rollback.
Keyword search cannot handle vague questions or synonyms; semantic search fills the gap. This guide uses Next.js and pgvector to add complete semantic search to a content site, covering indexing, queries, hybrid retrieval, frontend highlighting, and incremental updates in a production-ready design.
Head-based random sampling often drops low-frequency model failures and long-running Agent anomalies. This article covers Trace aggregation, tail-sampling policies, Collector capacity sizing, sampling validation, and overload rollback procedures.
Use MCP to let Claude Code read issues, open PRs, inspect CI, edit files, and submit changes. This guide covers the official remote MCP server, a self-hosted local server, configuration, practical workflows, and safe token permissions so AI-assisted development can close the loop in GitHub.
Changing a tokenizer affects token IDs, length budgets, special tokens, and cache semantics. This article presents a verifiable migration process based on artifact fingerprints, golden corpora, compatibility levels, dual-track routing, and versioned data.
AI writing assistants are easy to imagine but easy to get wrong — most become 'one-click filler generators.' From requirements to launch, this article explains how to design a genuinely useful assistant: assist not ghostwrite, structured streaming, a human-AI editing loop, and trading 'one-click generation' for 'better the more you write.'
Tool-call failures can originate in selection, arguments, authorization, dependencies, state, or user confirmation. This article provides an actionable taxonomy and metric design to turn vague Agent errors into fixable engineering problems.
Deep research—one question, multiple search rounds, and a synthesized report—is one of the most valuable agent use cases and cannot be solved by single-pass RAG. This article builds a LangGraph research agent that decomposes questions, searches in parallel, reads full text, fills gaps, and writes a report while explaining state graphs, tool calls, and loop