Tag: software-engineering
Page 33 of 48 • 519 posts total
-
MCP servers: Testing MCP servers with the same rigor as customer-facing APIs
A field-tested take on testing MCP servers with the same rigor as customer-facing APIs with MCP servers: what it rewards, where it breaks, and how to keep the workflow honest.
-
AI coding workflows: When taking the keyboard back was the real productivity move
A field-tested take on when taking the keyboard back was the real productivity move with AI coding workflows: what it rewards, where it breaks, and how to keep the workflow honest.
-
Prompt engineering for code: Honest taxonomy of prompts, as discovered in practice
A field-tested take on the honest taxonomy of prompts, as discovered in practice with Prompt engineering for code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cline and Roo Code: Plan mode budget that caught a runaway loop early
A field-tested take on a plan mode budget that caught a runaway loop early with Cline and Roo Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
JetBrains AI Assistant: First safe refactor that felt genuinely new
A field-tested take on the first safe refactor that felt genuinely new with JetBrains AI Assistant: what it rewards, where it breaks, and how to keep the workflow honest.
-
Windsurf: Onboarding a new hire with Windsurf already installed
A field-tested take on onboarding a new hire with Windsurf already installed with Windsurf: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: First code review after a heavy Cursor day
A field-tested take on the first code review after a heavy Cursor day with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
Google Gemini: First attempt at Vertex evaluations for code tasks
A field-tested take on a first attempt at Vertex evaluations for code tasks with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Measuring what Codex actually merged, not what it attempted
A field-tested take on measuring what Codex actually merged, not what it attempted with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Learning to pause the agent on purpose
A field-tested take on learning to pause the agent on purpose with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
GitHub Copilot: Onboarding a junior engineer with Copilot already in the seat
A field-tested take on onboarding a junior engineer with Copilot already in the seat with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.