Nano Banana 2.1: fourteen references, four that matter
The first time I used the full reference allowance, the image got worse. Fourteen images: the...
Tutorials
GPT Image 2.5: the quality knob is the expensive one, not 4K
I assumed 4K was the expensive thing. Then I read the price matrix properly: at 1K, max quality is...
Decide before Claude Code builds, check after it's done — two npx tools
When Claude Code builds an app for me, it decides things I never asked about: Does the data survive...
Who owns the LLM? 28 AIOps products compared
If you build AI features for an AIOps product, a customer will ask "can we use our own LLM?" sooner...
I was offered 292 AI skills. I installed 21.
Halfway through building ParkEase, I found a popular open-source pack for Claude Code: 292 skills, 68...
The Agent Industry Is Rebuilding SOA, Mistakes Included
Agentic architecture is repeating service-oriented architecture's two worst mistakes, the smart pipe and the synchronous chain.
PageSift 1.0: the Rust web content engine is feature-complete
Fifteen days, twenty-five releases. PageSift went public as 0.20 on October 20; today it ships...
What 586 Real Traces Taught Us About LLM Agent Determinism
What 586 Real Traces Taught Us About LLM Agent Determinism How temperature selectively...
The AI News Stopped Being About Models. Here's What That Means for Your Stack
This week's AI news was about proof, cost, and guardrails, not benchmarks. What that means for the systems you're building.
Prompt Versioning and Release Gates for LLM Apps
The fastest way I know to break a working LLM feature is to "just tweak the prompt" on a Friday....
Why our Messenger booking bot doesn't use an LLM to decide what to say (and went from 55% to 71% on real guest messages)
By Jonald Penpillo, AI developer and software engineer in General Santos City, Philippines. Most...
SKILL.md is the new package.json — and almost nobody scans it
Agent skills are just markdown files that an LLM will obey. Here's what malicious ones look like, how they were caught with a static analyzer, and why the MCP config file is the mo...
Building a Portuguese (PT-BR) Audio & Video Transcription Pipeline with Whisper Large-v3, Pyannote Speaker Diarization, and MCP
Transcribing multi-speaker audio and video in Brazilian Portuguese (PT-BR) comes with unique acoustic...
Putting Claude Code and Codex progress on the iPhone Lock Screen with Live Activities
When a coding agent such as Claude Code or Codex runs on your computer and you walk away, two...
What Building an AI Essay Grader Taught Me About the AP Lang Rubric
I spent the last few months building an AP Lang essay grader — a tool that takes a student's essay...
Your AI Agent Can Query the Database. Give It a Business Map First
An agent can successfully query a database and still give you the wrong answer. Ask, “How many...
Don't let an unattended model rewrite its own prompt
Unattended LLM pipelines fail in ways a person would normally fix by editing the prompt. If the...
Plan Mode Saves Your Plan Where Only One Agent Can Find It. Commit PLAN.md Instead
Claude Code keeps plans in ~/.claude/plans and sweeps them after 30 days by default. Copilot CLI files plan.md under its session. Put the plan on the branch.
How we built an AI calorie counter that understands Brazilian food from a photo
Notes from building ContaCal, a photo-based calorie logger for Brazilian meals. The pipeline, the hard parts (regional dishes, portions, lunchboxes) and the limits we tell users ab...
System design for physical AI: predictive maintenance across five fleet records
An open pit mine in Saudi Arabia: sixteen objects over five systems of record, heat rated edge units at the bucket, GLM 5.3 on one node the operator owns.
Spec-Driven Development na prática: testando o fluxo em um projeto de ML
Apliquei as fases do Spec Kit em uma tarefa de um projeto de previsão do Brasileirão e conferi o resultado contra a própria spec.
Your AI bill grew 4x and nobody can tell you which step did it
A team I talked to last month had a 4x jump in inference spend over one quarter. Not a crisis — they...
Claude Code Skills Deep Dive (0): From Repeated Prompts to Callable Capabilities
TL;DR: A Skill packages instructions, checklists, and multi-step workflows into an on-demand...
Postman Desktop Added Itself to Claude Code and Codex. Its Installer Trusts Its Own Hook
A Postman desktop update added its plugin to Claude Code and Codex for an existing user. Its installer is built to approve its own Codex hook. How to check.