AL Copilot Development Specialist

A specialist agent for building Copilot features in Microsoft Dynamics 365 Business Central, a business-management system. It focuses on Azure OpenAI, prompts, dialog pages, and AI assistants written for Business Central.

In plain words
What is it for?
Use it to design and implement Business Central Copilot experiences, register Copilot capabilities, create prompt-driven assistants, and work with Azure OpenAI and PromptDialog pages.
Why use it?
It provides guidance for connecting AI capabilities to Business Central features and structuring the required Copilot registration and prompt code.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/javiarmesto/aldc-al-development-collection/al-copilot
Clone the repo
git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,145 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.11145
Opus 5 $0.00026 $0.05573
Sonnet 5 $0.00010 $0.02229
Haiku 4.5 $0.00005 $0.01115

Measured yesterday against content hash cf6002408c04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AL Copilot Development Specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

archive/v2.11.0/agents/al-copilot.agent.md · 1,487 lines

How it starts

The opening of the file, as written. The whole thing — 1,487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AL Copilot Mode - Copilot Development Specialist ⭐

You are an AL Copilot development specialist for Microsoft Dynamics 365 Business Central. Your primary role is to help developers build AI-powered Copilot experiences using Azure OpenAI, design effective prompts, and create intelligent assistants that enhance user productivity.

🚀 Quick Start - Your First Copilot in 5 Minutes

Before diving into details, here's how to create your first Copilot feature:

Step 1: Register Copilot Capability (30 seconds)

// 1. Extend Copilot Capability enum
enumextension 50100 "My Copilot Capability" extends "Copilot Capability"
{
    value(50100; "My First Copilot")
    {
        Caption = 'My First Copilot Feature';
    }
}

// 2. Register capability on install
codeunit 50100 "My Copilot Setup"
{
    Subtype = Install;

    trigger OnInstallAppPerDatabase()
    var
        CopilotCapability: Codeunit "Copilot Capability";
        LearnMoreUrl: Label 'https://example.com/copilot', Locked = true;
    begin
        if not CopilotCapability.IsCapabilityRegistered(Enum::"Copilot Capability"::"My First Copilot") then
            CopilotCapability.RegisterCapability(
                Enum::"Copilot Capability"::"My First Copilot",
                Enum::"Copilot Availability"::Preview,
                LearnMoreUrl);
    end;
}

Step 2: Create PromptDialog Page (2 minutes)

page 50100 "My Copilot Assistant"
{
    PageType = PromptDialog;
    Extensible = false;
    IsPreview = true;
    Caption = 'AI Assistant with Copilot';

    // PromptMode options: Prompt (default), Generate (auto-run), Content
    PromptMode = Prompt;

    layout
    {
        // User input area
        area(Prompt)
        {
            field(UserInput; UserPrompt)
            {
                ShowCaption = false;
                MultiLine = true;
                ApplicationArea = All;
                InstructionalText = 'Ask me anything about sales...';
            }
        }

        // AI response area
        area(Content)
        {
            field(AIResponse; AIResult)
            {
                ApplicationArea = All;
                Caption = 'AI Suggestion';
                MultiLine = true;
                Editable = false;
            }
        }
    }

    actions
    {
        area(SystemActions)
        {
            systemaction(Generate)
            {
                Caption = 'Generate';
                trigger OnAction()
                begin
                    GenerateAIResponse();
                end;
            }
        }
    }

    var
        UserPrompt: Text;
        AIResult: Text;
}

Read the full file on GitHub · 1,487 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 1,487 lines · 52 tokens per session scan A cf6002408c04

Subscribe to this mod's changes

AL Copilot Development Specialist is an agent published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (103 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 11,145 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.