ALDC¶

AL Development Collection · Spec-driven AI for Business Central · Español

Ship Business Central extensions with AI agents that follow your process.

ALDC gives Copilot and Claude Code a working model for AL delivery: specs, plans, tests, review gates and reusable skills. Less vibe coding. More traceable implementation.

Start with the docs Open the collection guide GitHub

Free, hands-on: Public ALDC Workshop →

4 public + 2 on-demand agents 11 skills 6 workflows BCQuality-ready Copilot + Claude Code v4.1.0 · MIT

What's new in 4.1.0¶

Lower token / AIC cost per interaction

A 31% lighter always-on entrypoint, narrow per-object instruction globs, and curated context passed to subagents. Same capabilities — fewer tokens on every request.
Cited reviews & audits with BCQuality

Optional external knowledge base (configurable, defaults to upstream microsoft/BCQuality). Agents cite findings to real files, with a graceful native fallback when it's absent. Never blocks.

Install once, from the Command Palette. Run AL Collection: Install Toolkit to Workspace and ALDC drops the agents, skills, instructions and config into your project — then start with @AL Architecture & Design Specialist or @AL Development Conductor.

Also new: on-demand @AL Triage (reactive diagnosis) and @Dredd (independent auditor) — read-only on your code.

Installing the ALDC toolkit from the VS Code Command Palette

What's ALDC¶

Most AI coding tools generate a file and hope for the best. ALDC is different.

Every feature starts with a spec contract that is functional, technical, and testable, kept in .github/plans/{req_name}/. Architecture and test plans live next to it.

A conductor agent orchestrates a TDD cycle: the Implementation Subagent writes tests first, code second, then refactors. A Review Subagent validates against the spec. You approve every phase.

Underneath it all, 11 composable skills covering API, events, performance, testing, and more load on demand so agents only know what they need for the task in front of them.

The result: AL code that passes review the first time, with traceable decisions from requirement to merge.

flowchart TD
    R([Requirement]) --> S[Spec Contract<br/><small>functional + technical</small>]
    S --> A[Architecture<br/><small>decisions + diagrams</small>]
    A --> T[Test Plan<br/><small>RED before GREEN</small>]
    T --> I[TDD Implementation<br/><small>subagent loop</small>]
    I --> V[Review<br/><small>vs spec</small>]
    V --> M([Merged])

    style R fill:#ebffb1,color:#232529,stroke:#ade900
    style M fill:#7a9e00,color:#fff,stroke:none
    style S fill:#ebffb1,color:#232529,stroke:#ade900
    style A fill:#ebffb1,color:#232529,stroke:#ade900
    style T fill:#d8723c,color:#fff,stroke:none
    style I fill:#d8723c,color:#fff,stroke:none
    style V fill:#d8723c,color:#fff,stroke:none

Why it matters¶

Spec-driven, not prompt-and-pray

No more "please re-explain the requirement for the 5^th time". Every feature has a written contract that agents consult.
TDD enforced, not suggested

The Implementation Subagent refuses to write code before tests. RED → GREEN → REFACTOR is hardcoded in the agent.
You approve every phase

Agents stop at architecture, plan, implementation, review, deploy. Nothing ships without a human saying yes.
Extension-only discipline

Never touches base app objects. Always tableextensions, pageextensions, event subscribers. Least-privilege permissions by default.
One toolkit, two runtimes

Same primitives work in GitHub Copilot and Claude Code. Pick the tool your team already uses.
Skills load on demand

11 composable skills replace 300kb of prompt soup. Agents only load what's relevant to the task.

Cited reviews & audits with BCQuality¶

BCQuality is an optional layer that turns the review/audit agents into citing reviewers — every finding points to a real Business Central knowledge file, not just an opinion.

Configurable source. Defaults to the canonical upstream microsoft/BCQuality; point it at your own fork in aldc.yaml.
Consumed externally. A sibling clone via multi-root workspace — never compiled, never pollutes your app.
Hooks in via entry.md. Agents read the meta-skill and run whatever it dispatches.
Never blocks. Absent by default → graceful native A–G fallback.

Read the BCQuality guide →

# from your AL project root — opt in when you want cited reviews
bash tools/bcquality/install.sh      # or: pwsh tools/bcquality/install.ps1
#   → clones microsoft/BCQuality to ../bcquality (configurable)

# then open aldc.code-workspace and run:
@Dredd                               # independent audit
@AL Development Conductor            # review phases cite BCQuality

Quick start¶

GitHub Copilot (VS Code) Claude Code Just exploring?

git clone https://github.com/javiarmesto/ALDC-AL-Development-Collection.git
cd ALDC-AL-Development-Collection
npm install
npx aldc init

Then in VS Code with Copilot enabled:

@workspace use al-initialize

/plugin install aldc

Then:

/aldc:al-initialize

git clone https://github.com/javiarmesto/ALDC-AL-Development-Collection.git
cd ALDC-AL-Development-Collection
npm install && npm run validate

Resources¶

Everything ALDC-related lives here. Pick your path.

Start here

Getting Started

Install, configure and ship your first feature in under 10 minutes.

→ Guide

Collection Guide

The public guide to ALDC: architecture, primitives, flow, validation and adoption.

→ Roles

Agents

Architect, Developer, Conductor, Pre-Sales — plus on-demand Triage & Dredd. What each one does and when.

→ Automation

Workflows

6 workflows from initialize to PR prepare. Invocable from chat.

→ Standards

Instructions

9 always-on AL coding standards. Style, perf, naming, errors, events.

→ Execution

Complete Development Flow

See the end-to-end path from requirement intake to validated delivery.

→ Talks

Events & Talks

Conference sessions, community talks and upcoming public appearances.

→ Example

Reproducible Example

Walk through a concrete ALDC setup with a documented starting point.

→ Contribute

Contributing

Open issues, submit improvements and propose new primitives with the repo guidelines.

→ Open source

Source code

Every agent, skill and workflow. MIT licensed. Star and fork welcome.

→ Community

Discussions

Ask questions, share patterns and propose primitives with the community.

→ History

Changelog

Track releases, fixes and the evolution of the collection over time.

→

Events & talks¶

ALDC also exists outside the repo: conference talks, Dev Days and hands-on sessions where the collection, workflow and delivery model are the topic. Here you only see confirmed upcoming talks.

See upcoming talks Start with the docs

How to collaborate¶

Four ways to make ALDC better. No contribution is too small.

01

Try it and tell me

Install, build something real, and open an issue with what broke, what felt awkward, or what you wish existed. Bug reports are gold.

Open an issue →

02

Contribute a primitive

Have a skill, workflow or agent you'd pay for? Propose it. Fork, follow the contribution guide, open a PR.

Contribution guide →

03

Shape v1.2

Priorities are discussed openly. Vote on trade-offs, challenge assumptions, and propose alternatives with the community.

Join the discussion →

04

Share the workflow

Star the repo. Mention ALDC in your BC community, internal enablement docs or session notes. Useful references beat generic hype.

Star on GitHub →