---
id: video/mBU2Iu0urw8
type: video
title: "Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive"
summary: "Agentic AL development in Visual Studio Code and via the ALMCP server: agent modes, skills, tools, debugging, LSP for AL, the BCbench evaluation framework, and a BC fix workflow using a RAL loop and sub-agents. Includes demos with GitHub Copilot CLI."
tier: community
language: en
tags:
  - agentic development
  - agent modes
  - skills
  - tools
  - mcp server
  - almcp
  - visual studio code
  - debugging
  - al development
  - language model tools api
  - agentic workflows
  - language server protocol
system: development
review:
  state: reviewed
  by: opus
  at: "2026-10-07T23:16:50.281Z"
  flags: []
generated:
  at: "2026-10-09T00:29:02.995Z"
  pipeline: 0.2.0
  prompts:
    extract-video: 1
    summarize-video: 2
  input_hash: 85388178d5308e4ee587eda92a85df7b9a2dfbc68e0eafa9c16894d9a874764c
evidence:
  - kind: video
    url: https://www.youtube.com/watch?v=mBU2Iu0urw8&t=66s
    title: "Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive"
    date: "2026-10-01T05:38:52.000Z"
    commit: null
    t: 66
    quote: with the agent mode, you can have this multi-step operation where you can take it from a small simple operation ...
  - kind: video
    url: https://www.youtube.com/watch?v=mBU2Iu0urw8&t=112s
    title: "Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive"
    date: "2026-10-01T05:38:52.000Z"
    commit: null
    t: 112
    quote: we can also make our own custom agents. The the beauty of this is that it's all just a markdown file
  - kind: video
    url: https://www.youtube.com/watch?v=mBU2Iu0urw8&t=163s
    title: "Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive"
    date: "2026-10-01T05:38:52.000Z"
    commit: null
    t: 163
    quote: it doesn't take space in your context window. All it is from uh for loading it for the agent to begin with is a
  - kind: video
    url: https://www.youtube.com/watch?v=mBU2Iu0urw8&t=210s
    title: "Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive"
    date: "2026-10-01T05:38:52.000Z"
    commit: null
    t: 210
    quote: what has been truly a gamecher with agents in comparison to the chat modes that we've seen in the past is their ability to
  - kind: video
    url: https://www.youtube.com/watch?v=mBU2Iu0urw8&t=230s
    title: "Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive"
    date: "2026-10-01T05:38:52.000Z"
    commit: null
    t: 230
    quote: it will discover them and as soon as you give them a task it will reason over that task what it has to do
links:
  learn: []
  objects: []
  features:
    - feature/573338
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
video_id: mBU2Iu0urw8
channel: yt-mibuso
source_name: mibuso.com / BC TechDays
url: https://www.youtube.com/watch?v=mBU2Iu0urw8
published_at: "2026-10-01T05:38:52.000Z"
duration_s: 2700
captions: derived
audience:
  - developer
  - partner
  - functional consultant
chapters:
  - t: 0
    title: Introduction and Agenda
  - t: 53
    title: Agent Modes - Agent, Ask, and Plan
  - t: 143
    title: Custom Agents and Skills
  - t: 210
    title: Tools and the Agentic Loop
  - t: 304
    title: Tool Categories and Discovery
  - t: 401
    title: Demo Setup and Agent Invocation
  - t: 627
    title: Code Generation and Building
  - t: 691
    title: Debugging and Troubleshooting with Agents
  - t: 854
    title: ALMCP Server and Editor Support
  - t: 967
    title: ALMCP with GitHub Copilot CLI Demo
  - t: 1155
    title: Tooling across Surfaces and LSP Introduction
  - t: 1213
    title: Language Server Protocol Benefits and Comparison
  - t: 1332
    title: LSP Configuration, Endpoints and Evaluation Framework
  - t: 1552
    title: Agent Evaluation Methodology and Agentic Workflows
  - t: 1747
    title: BC Fix Workflow Architecture and RAL Loop Technique
  - t: 1949
    title: Live Demo Setup and BC Fix Baseline Test Creation
  - t: 2171
    title: "Demo Phase 4: Bug Fix Implementation and Test Verification"
  - t: 2280
    title: Takeaways, Q&A and Agent Failure Handling
  - t: 2475
    title: Performance Management and Pull Request Review Workflow
  - t: 2680
    title: Closing Remarks
features:
  - name: Agent Mode
    status: unclear
    t: 53
    verified: false
    status_source: video
  - name: Ask Mode
    status: unclear
    t: 85
    verified: false
    status_source: video
  - name: Plan Mode
    status: unclear
    t: 95
    verified: false
    status_source: video
  - name: Custom Agents
    status: unclear
    t: 112
    verified: false
    status_source: video
  - name: Skills
    status: unclear
    t: 143
    verified: false
    status_source: video
  - name: BC Quality Repository Skills
    status: unclear
    t: 180
    verified: false
    status_source: video
  - name: Agent Tools
    status: unclear
    t: 210
    verified: false
    status_source: video
  - name: Language Model Tools API
    status: unclear
    t: 272
    verified: false
    status_source: video
  - name: MCP Servers for AL Development
    status: unclear
    t: 292
    verified: false
    status_source: video
  - name: Build Tool
    status: unclear
    t: 315
    verified: false
    status_source: video
  - name: Symbol and Relationship Tools
    status: unclear
    t: 325
    verified: false
    status_source: video
  - name: Publishing and Debugging Tools
    status: unclear
    t: 335
    verified: false
    status_source: video
  - name: Test Tools
    status: unclear
    t: 345
    verified: false
    status_source: video
  - name: Troubleshooting Tools
    status: unclear
    t: 355
    verified: false
    status_source: video
  - name: Tool Discovery and Invocation
    status: unclear
    t: 381
    verified: false
    status_source: video
  - name: Approval Workflow
    status: unclear
    t: 515
    verified: false
    status_source: video
  - name: Context Size Configuration
    status: unclear
    t: 498
    verified: false
    status_source: video
  - name: Reasoning Model Selection
    status: unclear
    t: 487
    verified: false
    status_source: video
  - name: ALMCP Server
    status: unclear
    t: 875
    verified: false
    status_source: video
  - name: AL CLI Tool
    status: unclear
    t: 917
    verified: false
    status_source: video
  - name: Agent database statistics access
    status: unclear
    t: 788
    verified: false
    status_source: video
  - name: Agent stack trace analysis
    status: unclear
    t: 824
    verified: false
    status_source: video
  - name: ALMCP GitHub Copilot integration
    status: unclear
    t: 994
    verified: false
    status_source: video
  - name: Language Server Protocol (LSP) for AL
    status: ga
    t: 1187
    verified: false
    status_source: roadmap
    roadmap_ids:
      - "573338"
  - name: LSP folding range endpoint
    status: unclear
    t: 1395
    verified: false
    status_source: video
  - name: BCbench evaluation framework
    status: unclear
    t: 1491
    verified: false
    status_source: video
  - name: Hidden test verification method
    status: unclear
    t: 1520
    verified: false
    status_source: video
  - name: Agentic workflow framework
    status: unclear
    t: 1657
    verified: false
    status_source: video
  - name: RAL loop technique
    status: unclear
    t: 1899
    verified: false
    status_source: video
  - name: BC fix skill
    status: unclear
    t: 1784
    verified: false
    status_source: video
  - name: BC fix baseline skill
    status: unclear
    t: 1909
    verified: false
    status_source: video
  - name: BC fix implement skill
    status: unclear
    t: 2191
    verified: false
    status_source: video
  - name: BC test implement agent
    status: unclear
    t: 1857
    verified: false
    status_source: video
  - name: AL developer session skill (BCLdev session)
    status: unclear
    t: 1784
    verified: false
    status_source: video
  - name: MCP tools integration
    status: unclear
    t: 1800
    verified: false
    status_source: video
  - name: Agent evaluation methodology
    status: unclear
    t: 1589
    verified: false
    status_source: video
  - name: Sub-agent context isolation
    status: unclear
    t: 2036
    verified: false
    status_source: video
  - name: Session retrospective skill
    status: unclear
    t: 2432
    verified: false
    status_source: video
  - name: Business Central performance profile tool
    status: unclear
    t: 2539
    verified: false
    status_source: video
  - name: Agent-assisted telemetry analysis
    status: unclear
    t: 2568
    verified: false
    status_source: video
  - name: Agent pull request commenting
    status: unclear
    t: 2637
    verified: false
    status_source: video
  - name: Custom AL code analyzers with MCP server
    status: unclear
    t: 2370
    verified: false
    status_source: video
objects_mentioned:
  - page page (shown in demo for JSON parsing)
  - codeunit process from JSON method
  - other process entry method
  - other trim method
  - other lookup method
  - table customer table
  - other AL command
  - other ALC
  - other BCLdev session
  - other BC fix baseline
  - other BC fix implement
  - other BC fix supplement
  - other BC test implement
quotes:
  - t: 66
    text: with the agent mode, you can have this multi-step operation where you can take it from a small simple operation ...
    check: exact
  - t: 112
    text: we can also make our own custom agents. The the beauty of this is that it's all just a markdown file
    check: exact
  - t: 163
    text: it doesn't take space in your context window. All it is from uh for loading it for the agent to begin with is a
    check: exact
  - t: 210
    text: what has been truly a gamecher with agents in comparison to the chat modes that we've seen in the past is their ability to
    check: exact
  - t: 230
    text: it will discover them and as soon as you give them a task it will reason over that task what it has to do
    check: exact
---

# Microsoft presents: Agentic development with AL developer tools and ALMCP deep dive

> Agentic AL development in Visual Studio Code and via the ALMCP server: agent modes, skills, tools, debugging, LSP for AL, the BCbench evaluation framework, and a BC fix workflow using a RAL loop and sub-agents. Includes demos with GitHub Copilot CLI.

[Watch on YouTube](https://www.youtube.com/watch?v=mBU2Iu0urw8) · mibuso.com / BC TechDays · 2026-10-01 · 45:00 · tier community · reviewed (checked by Opus)

## Overview

The session covers how coding agents work with AL tools. It explains Agent, Ask and Plan modes, custom agents defined in markdown files, skills loaded on demand, and the agentic loop where an agent picks tools, reads results and continues. Demos show building, publishing, debugging and troubleshooting, including access to stack frames, variables and database statistics during a debug session.

The second half covers the ALMCP server and AL CLI tool (.NET tools installable via NuGet), registering ALMCP in GitHub Copilot CLI, and the Language Server Protocol for AL. It then covers BCbench, which uses hidden tests from real commits, and a BC fix workflow built from sub-skills with a RAL loop, sub-agent context isolation, a session retrospective skill, and notes on performance profiling and pull request comments.

## Key points

- Custom agents are markdown files with front matter (name, description, tools, skills, knowledge, system prompt). Skills load on demand and do not use context window space up front.
- Troubleshooting tools come from a dedicated MCP server and are only available during a debugging session. They expose source, stack frames, variables, and SQL statements and database statistics.
- ALMCP server and AL CLI are .NET tools installed via NuGet, with a pre-release flag for the latest features. In GitHub Copilot the agent may call ALC directly, so instructions may be needed to redirect it to ALMCP.
- LSP gives agents semantic endpoints such as go to definition, find references and rename. In the demo, grep missed about 80% of references to a number field on the Customer table. LSP needs a package cache path configured.
- BCbench is based on SWE bench and real commits that contain both a fix and a test. It runs the hidden tests against agent fixes and averages five runs because of LLM nondeterminism. Baseline was 67%, and adding tools raised it to 71%.
- The BC fix workflow uses a RAL loop with success criteria and a maximum number of attempts. The baseline skill creates a failing test, and the implement skill runs as a sub-agent on Claude Sonnet 4.6 to limit context rot and cost.
- Pull request comments by an agent still need human approval. Profiler reading by agents is not yet in the workflows, and a loop for pipeline gate failures would need to be added.

## Chapters

- [0:00](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=0s) Introduction and Agenda
- [0:53](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=53s) Agent Modes - Agent, Ask, and Plan
- [2:23](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=143s) Custom Agents and Skills
- [3:30](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=210s) Tools and the Agentic Loop
- [5:04](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=304s) Tool Categories and Discovery
- [6:41](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=401s) Demo Setup and Agent Invocation
- [10:27](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=627s) Code Generation and Building
- [11:31](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=691s) Debugging and Troubleshooting with Agents
- [14:14](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=854s) ALMCP Server and Editor Support
- [16:07](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=967s) ALMCP with GitHub Copilot CLI Demo
- [19:15](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1155s) Tooling across Surfaces and LSP Introduction
- [20:13](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1213s) Language Server Protocol Benefits and Comparison
- [22:12](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1332s) LSP Configuration, Endpoints and Evaluation Framework
- [25:52](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1552s) Agent Evaluation Methodology and Agentic Workflows
- [29:07](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1747s) BC Fix Workflow Architecture and RAL Loop Technique
- [32:29](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1949s) Live Demo Setup and BC Fix Baseline Test Creation
- [36:11](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2171s) Demo Phase 4: Bug Fix Implementation and Test Verification
- [38:00](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2280s) Takeaways, Q&A and Agent Failure Handling
- [41:15](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2475s) Performance Management and Pull Request Review Workflow
- [44:40](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2680s) Closing Remarks

## Features

| Feature | Status | At |
|---|---|---|
| Agent Mode | status not stated, demoed | [0:53](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=53s) |
| Ask Mode | status not stated | [1:25](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=85s) |
| Plan Mode | status not stated | [1:35](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=95s) |
| Custom Agents | status not stated | [1:52](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=112s) |
| Skills | status not stated | [2:23](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=143s) |
| BC Quality Repository Skills | status not stated | [3:00](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=180s) |
| Agent Tools | status not stated, demoed | [3:30](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=210s) |
| Language Model Tools API | status not stated | [4:32](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=272s) |
| MCP Servers for AL Development | status not stated, demoed | [4:52](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=292s) |
| Build Tool | status not stated, demoed | [5:15](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=315s) |
| Symbol and Relationship Tools | status not stated | [5:25](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=325s) |
| Publishing and Debugging Tools | status not stated, demoed | [5:35](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=335s) |
| Test Tools | status not stated | [5:45](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=345s) |
| Troubleshooting Tools | status not stated, demoed | [5:55](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=355s) |
| Tool Discovery and Invocation | status not stated, demoed | [6:21](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=381s) |
| Approval Workflow | status not stated, demoed | [8:35](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=515s) |
| Context Size Configuration | status not stated, demoed | [8:18](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=498s) |
| Reasoning Model Selection | status not stated, demoed | [8:07](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=487s) |
| ALMCP Server | status not stated, demoed | [14:35](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=875s) |
| AL CLI Tool | status not stated, demoed | [15:17](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=917s) |
| Agent database statistics access | status not stated, demoed | [13:08](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=788s) |
| Agent stack trace analysis | status not stated, demoed | [13:44](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=824s) |
| ALMCP GitHub Copilot integration | status not stated, demoed | [16:34](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=994s) |
| Language Server Protocol (LSP) for AL | generally available (roadmap [Use AL language intelligence from AI agents and other editors](../features/573338.md)), demoed | [19:47](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1187s) |
| LSP folding range endpoint | status not stated | [23:15](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1395s) |
| BCbench evaluation framework | status not stated | [24:51](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1491s) |
| Hidden test verification method | status not stated | [25:20](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1520s) |
| Agentic workflow framework | status not stated, demoed | [27:37](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1657s) |
| RAL loop technique | status not stated, demoed | [31:39](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1899s) |
| BC fix skill | status not stated, demoed | [29:44](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1784s) |
| BC fix baseline skill | status not stated, demoed | [31:49](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1909s) |
| BC fix implement skill | status not stated, demoed | [36:31](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2191s) |
| BC test implement agent | status not stated, demoed | [30:57](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1857s) |
| AL developer session skill (BCLdev session) | status not stated, demoed | [29:44](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1784s) |
| MCP tools integration | status not stated, demoed | [30:00](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1800s) |
| Agent evaluation methodology | status not stated | [26:29](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1589s) |
| Sub-agent context isolation | status not stated, demoed | [33:56](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2036s) |
| Session retrospective skill | status not stated | [40:32](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2432s) |
| Business Central performance profile tool | status not stated | [42:19](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2539s) |
| Agent-assisted telemetry analysis | status not stated, demoed | [42:48](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2568s) |
| Agent pull request commenting | status not stated | [43:57](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2637s) |
| Custom AL code analyzers with MCP server | status not stated | [39:30](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2370s) |

A status with a roadmap link comes from the Microsoft 365 roadmap feature this part of the video covers (matched by Haiku; links Opus dropped are not used); other statuses need a status word in the video itself.

## AL objects mentioned

As heard in the captions. A name that matches one object page by exact type and name links to it; the others stay as named.

- page "page (shown in demo for JSON parsing)" at [7:12](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=432s)
- codeunit "process from JSON method" at [7:23](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=443s)
- other "process entry method" at [7:23](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=443s)
- other "trim method" at [13:56](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=836s)
- other "lookup method" at [10:27](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=627s)
- table "customer table" at [21:26](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1286s)
- other "AL command" at [22:12](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1332s)
- other "ALC" at [15:46](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=946s)
- other "BCLdev session" at [29:44](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1784s)
- other "BC fix baseline" at [31:27](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1887s)
- other "BC fix implement" at [30:57](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1857s)
- other "BC fix supplement" at [31:27](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1887s)
- other "BC test implement" at [30:57](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1857s)

Not found in BC28-30: page "page (shown in demo for JSON parsing)", codeunit "process from JSON method", table "customer table".

## Quotes

- [1:06](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=66s) "with the agent mode, you can have this multi-step operation where you can take it from a small simple operation ..."
- [1:52](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=112s) "we can also make our own custom agents. The the beauty of this is that it's all just a markdown file"
- [2:43](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=163s) "it doesn't take space in your context window. All it is from uh for loading it for the agent to begin with is a"
- [3:30](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=210s) "what has been truly a gamecher with agents in comparison to the chat modes that we've seen in the past is their ability to"
- [3:50](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=230s) "it will discover them and as soon as you give them a task it will reason over that task what it has to do"

## Disclaimers in the video

- [15:17](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=917s) preview: you can also specify the pre-release flag so that you get access to the latest uh bits that we're shipping
- [32:29](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=1949s) preview: I'm going to skip the planning mode completely. It was shown in the keynote very fast.
- [34:30](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2070s) other: It's probably going to run on the hik model as well. I haven't tested this one. That's exactly why we need BCbench for this.
- [38:00](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2280s) other: the part that I will um I'm going to skip I think for the pull request I have the small ...
- [42:48](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2568s) not-in-this-release: We are not doing this right away. We don't have a workflow for this one but we have it in mind
- [44:39](https://www.youtube.com/watch?v=mBU2Iu0urw8&t=2679s) coming-later: we need probably to add like another loop to make sure that agent can help with the failures in the gates

Presenters (as heard): Thomas, Quinton, Arthur.