MCP Colors: Systematically deal with prompt injection risk
A method using color-coding (red/blue) to classify MCP tools and systematically mitigate prompt injection risks in AI agents.
A method using color-coding (red/blue) to classify MCP tools and systematically mitigate prompt injection risks in AI agents.
Explores integration methods between Microsoft Copilot and ServiceNow, covering Copilot 365, Copilot Studio agents, and MCP servers.
Explores software design philosophy of minimizing user effort, using Google Calendar as an example of optimizing for common cases while supporting edge cases.
An engineer argues that software development is a learning process, not an assembly line, and explains how to use LLMs as brainstorming partners.
An overview of using a basic test web page to learn web application testing techniques, including DOM inspection and selector usage.
A developer built a unified task dashboard using Next.js, Vercel Edge Functions, and live API calls to aggregate data from ClickUp, Notion, and Google Calendar.
Automerge is a local-first sync engine for building collaborative, offline-capable applications, preventing data conflicts.
An overview of the Software Test Pages, a free web application for practicing technical web testing, automation, and learning web technologies.
Explores the new [UnsafeAccessorType] feature in .NET 10, which improves access to private members in code compared to earlier .NET versions.
Introduces the Azure Local Well-Architected Review Assessment, a tool to evaluate and improve hybrid cloud architecture based on Microsoft's framework.
Explores the psychological barriers engineers face when evaluating programming languages outside their expertise, based on Steve Francia's insights.
Martin Fowler's blog fragments on LLM browser security, AI-assisted coding debates, and the literary significance of the Doonesbury comic strip.
An overview of alternative LLM architectures beyond standard transformers, including linear attention hybrids, text diffusion models, and code world models.
An overview of alternative LLM architectures beyond standard transformers, including linear attention hybrids, text diffusion models, and world models.
Explains how stack ranking helps teams prioritize work effectively by forcing tough decisions on what to work on next.
A tutorial on creating a Bash script using Awk and fzf to search, install, and remove Arch Linux and AUR packages from the command line.
Updated SQL Server diagnostic queries for November 2025, including new columns and query hints for performance analysis.
Announcement of htmx 4, replacing XMLHttpRequest with fetch() and introducing breaking changes with a detailed upgrade plan.
Argues against the common advice to replace Kafka with Postgres, explaining they are different tools for different problems.
Argues against oversimplified advice to replace Kafka with Postgres, explaining they are different tools for different problems.