Tag: software-engineering
Page 9 of 48 • 518 posts total
-
MCP servers: Least-privilege auth for MCP in a real enterprise
A field-tested take on least-privilege auth for MCP in a real enterprise with MCP servers: what it rewards, where it breaks, and how to keep the workflow honest.
-
AI coding workflows: Scorecard question: did this PR have to exist?
A field-tested take on the scorecard question: did this PR have to exist? with AI coding workflows: what it rewards, where it breaks, and how to keep the workflow honest.
-
Prompt engineering for code: Structured outputs: JSON schemas that keep agents honest
A field-tested take on structured outputs: JSON schemas that keep agents honest with Prompt engineering for code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cline and Roo Code: Building an internal guardrails library on top of Cline
A field-tested take on building an internal guardrails library on top of Cline with Cline and Roo Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
JetBrains AI Assistant: When the IDE already knows the answer and the agent just needs to ask
A field-tested take on when the IDE already knows the answer and the agent just needs to ask with JetBrains AI Assistant: what it rewards, where it breaks, and how to keep the workflow honest.
-
Windsurf: What Windsurf teaches about the ergonomics of agent IDEs
A field-tested take on what Windsurf teaches about the ergonomics of agent IDEs with Windsurf: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: Resetting indexes when completions start feeling stale
A field-tested take on resetting indexes when completions start feeling stale with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
Google Gemini: Pairing Gemini with Code Assist for refactors that span a whole module
A field-tested take on pairing Gemini with Code Assist for refactors that span a whole module with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Keeping the human in the loop by requiring explicit acceptance
A field-tested take on keeping the human in the loop by requiring explicit acceptance with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Hooks that enforce lint, test and security gates before any write
A field-tested take on hooks that enforce lint, test and security gates before any write with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
GitHub Copilot: Constraining the agent with .github/copilot-instructions.md for reproducible behaviour
A field-tested take on constraining the agent with .github/copilot-instructions.md for reproducible behaviour with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.