Charrette AI Room

If keeping up with your industry means checking the same sites each morning, TrendRadar can gather and filter their headlines into a report. Start with a few RSS feeds and clear keyword rules, then add AI features when you know what you want them to do. sansan0’s TrendRadar is an open-source news and trend monitor. This article covers that project, including a small test of its English keyword matcher. The useful first goal is a brief you would actually read: relevant sources, a manageable topic and links worth opening. Key Takeaways TrendRadar combines trending lists and your chosen RSS feeds, with optional AI filtering, translation and analysis. Plain keywords match parts of words. In our small test, AI also matched rail and training . The starter rules below use whole-word matches and one exclusion. They were checked with nine invented English headlines. Collection, AI analysis and notification delivery need separate setup. Our trial tested the keyword module, rather t...

To fix AI design slop, give the agent a specific visitor, a decision to support, real content and checks it must pass. Then inspect the rendered page and request concrete changes. “Make it more modern” leaves too much open. For a meeting-room page, “put capacity and hourly price beside each room” gives the agent a visible job. This guide includes a copyable brief and a constructed before-and-after example. The example uses the same fictional room facts in two static HTML pages. It illustrates how to review a change; it does not measure which AI tool designs best. Key Takeaways Describe the visitor's task before choosing a visual style. Give the agent facts and a clear order of importance. Compare the rendered versions at the same screen size. Check specific text contrast, controls and mobile behavior before calling the page finished. What counts as “AI design slop”, and how do you make the fix checkable? AI design slop means a generated page that looks finished but ...

REA, short for Reverse Engineer Anything , gives an AI agent tools to inspect software and collect evidence about how it works. It can help answer a concrete question, such as where an export file is created or which function handles a button. The useful part is being able to check the answer. A confident explanation alone leaves you guessing whether the agent found something in the app or filled a gap. For this article, we created a tiny JavaScript example and inspected it with REA. The tool found the file connection, reported no parsing failures, and still left a return value unresolved. That combination is a useful lesson in reading AI analysis. Key Takeaways REA connects an AI agent to software inspection tools. The agent turns their results into an explanation. Start with one feature and a specific question. A complete static scan can still contain unknown values. Keep code ...

To gamify boring tasks, turn one small piece of work into a mission with a purpose, a clear finish, and visible evidence. Try the 15-minute template below on a task you already need to do. “Update the spreadsheet” can sit on a to-do list for days. “Find the three missing dates so tomorrow’s meeting can start with a decision” gives you somewhere to begin. The second version still involves a spreadsheet. It also gives you a role and an outcome worth reaching. The running game Zombies, Run! offers a useful example of this kind of design. A LongBlack profile of the game prompted the workplace exercise in this article. Key Takeaways Give one task a small, useful outcome and name who benefits from it. Define what “done” looks like before starting the timer. Keep a visible result and a precise next step for your next session. Treat this template as an experiment. Its effect on w...

When two AI assistants edit the same folder, neither one knows what the other just did. That isn't a bug in either tool. Anthropic's documentation for Claude Code says it plainly: "Each Claude Code session begins with a fresh context window" ( Anthropic, Claude Code memory docs ). Anthropic's engineering team describes the same starting point for long-running agents: "each new session begins with no memory of what came before" ( Anthropic Engineering, long-running agents ). I'm an architect who designs buildings, not a professional developer. I run Claude Code, Codex and a few other assistants on one shared project folder, and that folder isn't a git repository. There's no commit history to tell me, or them, who changed what. So I built a shared worklog to fill that gap. Below is what it looks like, the two commands that drive it, and the rules that keep it honest. Key Takeaways Each Claude Code session starts with a fresh context windo...