Tagged: developer-tools
6 posts and 2 projects
Posts
AL Perf v2 Drops Friday. Here's What Changed.
Version 2 sends the call tree, source code, SQL queries, and code structure to the AI. The result: findings that reference specific methods, call counts, and time percentages. Here's what changed and how well it works.
AL LSP for Agents: Now in VS Code, and a New Home
The AL Language Server wrapper now works with GitHub Copilot in VS Code, not just Claude Code. Plus: enriched hover with field and action properties, configurable code quality diagnostics, and a repo rename.
One-Click Performance Analysis Inside Business Central
A BC extension that adds an 'Analyze with AL Perf' button to the Performance Profiler page. One click gives you hotspots, anti-pattern detection, and AI-powered insights without leaving Business Central.
CentralGauge Benchmark Update: Why the Numbers Changed
A transparency report on significant fixes to the CentralGauge AL code benchmark infrastructure, including bugs in code extraction, broken tasks, and vague specs, along with updated LLM rankings.
How I Benchmark LLMs on AL Code
An in-depth look at CentralGauge, an open source benchmark for evaluating LLM performance on AL code generation for Business Central, covering task design, scoring methodology, and cross-model comparison results.
Native AL Language Server Support in Claude Code
Announcing native AL Language Server Protocol integration for Claude Code, giving the AI assistant real code intelligence for Business Central development including symbol navigation, references, and call hierarchy.
Projects
WezTerm Evo
ActiveA WezTerm fork with a built-in tmux CC protocol server, per-pane headers, and tab layouts, designed for Claude Code agent team workflows
WezTerm Bell for Claude Code
MaintainedA tiny Rust binary that triggers WezTerm visual bell and toast notifications from Claude Code hooks, with project-aware per-pane targeting