---
id: video/Ty6ZvzJYAvI
type: video
title: "Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having"
summary: "Podcast discussion on leading large Business Central developer teams through fast AI change: conference content gaps, standards and governance, and managing AI tool costs. Speakers describe multi-model use, GitHub Copilot's move to credit-based billing, and assigning models by developer experience."
tier: community
language: en
tags:
  - conference strategy
  - team governance
  - change management
  - developer adoption
  - technical education
  - leadership conversations
  - standards enforcement
  - pace of change
  - ai adoption
  - developer team management
  - training and education
  - development standards
system: development
review:
  state: reviewed
  by: opus
  at: "2026-10-07T23:20:08.556Z"
  flags: []
generated:
  at: "2026-10-07T23:20:08.642Z"
  pipeline: 0.2.0
  prompts:
    extract-video: 1
    summarize-video: 2
  input_hash: c0f8e55f0b4963220d719df2153085c338928d4b629acda0767ffdd2c78fe310
evidence:
  - kind: video
    url: https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=200s
    title: "Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having"
    date: "2026-06-19T13:00:06.000Z"
    commit: null
    t: 200
    quote: there's so much coming out that it feels like it's changing by the minute because I can't keep up with the volume.
  - kind: video
    url: https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=276s
    title: "Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having"
    date: "2026-06-19T13:00:06.000Z"
    commit: null
    t: 276
    quote: It is a challenge coming up with sessions so far in advance because you want to talk about things that are relevant at the
  - kind: video
    url: https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=518s
    title: "Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having"
    date: "2026-06-19T13:00:06.000Z"
    commit: null
    t: 518
    quote: Over the years, I've noticed that the ones that don't quite fit development and don't quite fit leadership get rejected more often than than
  - kind: video
    url: https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=710s
    title: "Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having"
    date: "2026-06-19T13:00:06.000Z"
    commit: null
    t: 710
    quote: we have like about 50 developers. We allow our customers to, you know, write their own code and contribute to their apps alongside of
  - kind: video
    url: https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=762s
    title: "Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having"
    date: "2026-06-19T13:00:06.000Z"
    commit: null
    t: 762
    quote: it's very grounded in that content and it's like definitive like you can say this
links:
  learn: []
  objects: []
  features: []
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
video_id: Ty6ZvzJYAvI
channel: yt-dynamicscorner
source_name: Dynamics Corner podcast
url: https://www.youtube.com/watch?v=Ty6ZvzJYAvI
published_at: "2026-06-19T13:00:06.000Z"
duration_s: 3541
captions: derived
audience:
  - decision maker
  - developer
  - administrator
chapters:
  - t: 0
    title: Introduction and seasonal reflections
  - t: 110
    title: Pace of technological change and conference timing challenges
  - t: 261
    title: Building sessions that stand the test of time
  - t: 386
    title: "Guest introductions: Matt Traxinger and Tanya Brockmann"
  - t: 463
    title: Leadership and development session gap at conferences
  - t: 618
    title: Team governance and managing change with multiple developers
  - t: 738
    title: Conference types, audience segmentation, and content strategy
  - t: 889
    title: Balancing partner vs end-user developer focus at conferences
  - t: 1027
    title: Rethinking conference track categories and AI blending into administration
  - t: 1158
    title: From academic to functional conference content and AI as dominant topic
  - t: 1270
    title: AI adoption strategy and shifting from technical deep-dives to real-world application
  - t: 1408
    title: Panel sessions and open forums as preferred conference format
  - t: 1547
    title: Managing large teams during rapid AI feature adoption and framework for AI adoption and GitHub billing changes
  - t: 1776
    title: Improving existing solutions versus chasing new projects
  - t: 1903
    title: Using AI for testing and edge cases instead of speed
  - t: 2031
    title: Measuring quality and delivering documentation with AI
  - t: 2152
    title: AI usage patterns beyond development coding
  - t: 2332
    title: Multi-model approach, team adoption strategies, and tokenization costs
  - t: 2555
    title: GitHub Copilot pricing model and business considerations
  - t: 2700
    title: Managing AI credit costs and team education
  - t: 2819
    title: Responsible AI usage and credit allocation strategy
  - t: 2951
    title: Best practices for selective AI tool deployment
  - t: 3028
    title: Model selection strategy for cost optimization
  - t: 3124
    title: AI model differences, training data concerns, and LLM experimentation
  - t: 3340
    title: Learning from base code and AI-generated content
  - t: 3404
    title: Closing remarks, contact information, and episode credits
features:
  - name: AI agents for administration
    status: unclear
    t: 1137
    verified: false
    status_source: video
  - name: Sales order agent
    status: unclear
    t: 1212
    verified: false
    status_source: video
  - name: Telemetry component in administration
    status: unclear
    t: 1061
    verified: false
    status_source: video
  - name: Custom agents for Business Central
    status: unclear
    t: 1698
    verified: false
    status_source: video
  - name: AI-assisted code unit optimization
    status: unclear
    t: 1723
    verified: false
    status_source: video
  - name: AI for Business Central performance testing
    status: unclear
    t: 1931
    verified: false
    status_source: video
  - name: AI-generated documentation
    status: unclear
    t: 2055
    verified: false
    status_source: video
  - name: AI for solution design and architecture
    status: unclear
    t: 2181
    verified: false
    status_source: video
  - name: Multi-model AI approach for design review
    status: unclear
    t: 2332
    verified: false
    status_source: video
  - name: Copilot for code generation
    status: unclear
    t: 2399
    verified: false
    status_source: video
  - name: GitHub Copilot credit-based pricing model
    status: unclear
    t: 2545
    verified: false
    status_source: video
  - name: Responsible AI model usage by developer experience level
    status: unclear
    t: 2842
    verified: false
    status_source: video
  - name: Code review agent
    status: unclear
    t: 2930
    verified: false
    status_source: video
  - name: Cheaper AI model usage for documentation and code reviews
    status: unclear
    t: 3069
    verified: false
    status_source: video
objects_mentioned:
  - other GitHub Copilot
  - other Visual Studio Code
  - codeunit event subscribers codeunit
  - other Business Central Performance Toolkit
quotes:
  - t: 200
    text: there's so much coming out that it feels like it's changing by the minute because I can't keep up with the volume.
    check: exact
  - t: 276
    text: It is a challenge coming up with sessions so far in advance because you want to talk about things that are relevant at the
    check: exact
  - t: 518
    text: Over the years, I've noticed that the ones that don't quite fit development and don't quite fit leadership get rejected more often than than
    check: exact
  - t: 710
    text: we have like about 50 developers. We allow our customers to, you know, write their own code and contribute to their apps alongside of
    check: exact
  - t: 762
    text: it's very grounded in that content and it's like definitive like you can say this
    check: fuzzy
---

# Episode 521: 50 Developers, Zero Playbook: The Leadership Conversation Nobody's Having

> Podcast discussion on leading large Business Central developer teams through fast AI change: conference content gaps, standards and governance, and managing AI tool costs. Speakers describe multi-model use, GitHub Copilot's move to credit-based billing, and assigning models by developer experience.

[Watch on YouTube](https://www.youtube.com/watch?v=Ty6ZvzJYAvI) · Dynamics Corner podcast · 2026-06-19 · 59:01 · tier community · reviewed (checked by Opus)

## Overview

Episode 521 of the Dynamics Corner podcast covers two connected themes. The first is conference content: the guests say sessions that sit between leadership and pure development, such as team adoption, standards enforcement and change management, tend to be rejected, and they favor panels and open forums over lectures. They also discuss how AI is blending administration and development, and how the pace of change makes it hard to plan sessions months ahead.

The second theme is running a team of about 50 developers while AI features arrive quickly. Speakers describe using AI more for design, testing and documentation than for raw coding speed, combining several models for design and review, and the cost pressure from GitHub's switch to paid credits. They discuss giving costly models to experienced developers and cheaper ones to others, and raise concerns about AI models training on AI-generated content.

## Key points

- A speaker's team has about 50 developers and lets customers write code alongside them. Getting internal and client developers to follow the same standards is hard, especially as AI features ship quickly.
- Sessions that fit neither development nor leadership, such as team adoption, standards and change management, are said to be rejected more often at conferences.
- Speakers prefer panels, open forums and Q&A over lecture-style sessions, and want conference content to be more functional and less academic.
- Matt says he uses AI for everything and for development the least. He spends more time on solution design, and coding ends up as about 20% of total time.
- One speaker does initial design with Claude, uses ChatGPT as design reviewer and then Gemini for a further review, so the layers converge on a solution.
- Copilot or Claude Code is described as getting about 80% of the way there. The developer still fixes Business Central-specific details such as wrongly named fields and posting setup references.
- GitHub Copilot moved from a monthly plan with a fixed allowance to actual credit use, which makes cost harder to estimate. Tanya notes that splitting a large codeunit into smaller ones uses fewer tokens.

## Chapters

- [0:00](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=0s) Introduction and seasonal reflections
- [1:50](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=110s) Pace of technological change and conference timing challenges
- [4:21](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=261s) Building sessions that stand the test of time
- [6:26](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=386s) Guest introductions: Matt Traxinger and Tanya Brockmann
- [7:43](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=463s) Leadership and development session gap at conferences
- [10:18](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=618s) Team governance and managing change with multiple developers
- [12:18](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=738s) Conference types, audience segmentation, and content strategy
- [14:49](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=889s) Balancing partner vs end-user developer focus at conferences
- [17:07](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1027s) Rethinking conference track categories and AI blending into administration
- [19:18](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1158s) From academic to functional conference content and AI as dominant topic
- [21:10](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1270s) AI adoption strategy and shifting from technical deep-dives to real-world application
- [23:28](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1408s) Panel sessions and open forums as preferred conference format
- [25:47](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1547s) Managing large teams during rapid AI feature adoption and framework for AI adoption and GitHub billing changes
- [29:36](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1776s) Improving existing solutions versus chasing new projects
- [31:43](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1903s) Using AI for testing and edge cases instead of speed
- [33:51](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2031s) Measuring quality and delivering documentation with AI
- [35:52](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2152s) AI usage patterns beyond development coding
- [38:52](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2332s) Multi-model approach, team adoption strategies, and tokenization costs
- [42:35](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2555s) GitHub Copilot pricing model and business considerations
- [45:00](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2700s) Managing AI credit costs and team education
- [46:59](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2819s) Responsible AI usage and credit allocation strategy
- [49:11](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2951s) Best practices for selective AI tool deployment
- [50:28](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=3028s) Model selection strategy for cost optimization
- [52:04](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=3124s) AI model differences, training data concerns, and LLM experimentation
- [55:40](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=3340s) Learning from base code and AI-generated content
- [56:44](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=3404s) Closing remarks, contact information, and episode credits

## Features

| Feature | Status | At |
|---|---|---|
| AI agents for administration | status not stated | [18:57](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1137s) |
| Sales order agent | status not stated, demoed | [20:12](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1212s) |
| Telemetry component in administration | status not stated | [17:41](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1061s) |
| Custom agents for Business Central | status not stated | [28:18](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1698s) |
| AI-assisted code unit optimization | status not stated | [28:43](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1723s) |
| AI for Business Central performance testing | status not stated | [32:11](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1931s) |
| AI-generated documentation | status not stated | [34:15](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2055s) |
| AI for solution design and architecture | status not stated | [36:21](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2181s) |
| Multi-model AI approach for design review | status not stated | [38:52](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2332s) |
| Copilot for code generation | status not stated | [39:59](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2399s) |
| GitHub Copilot credit-based pricing model | status not stated | [42:25](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2545s) |
| Responsible AI model usage by developer experience level | status not stated | [47:22](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2842s) |
| Code review agent | status not stated | [48:50](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=2930s) |
| Cheaper AI model usage for documentation and code reviews | status not stated | [51:09](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=3069s) |

## 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.

- other "GitHub Copilot" at [3:31](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=211s)
- other "Visual Studio Code" at [3:31](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=211s)
- codeunit "event subscribers codeunit" at [28:43](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1723s)
- other "Business Central Performance Toolkit" at [32:27](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1947s)

Not found in BC28-30: codeunit "event subscribers codeunit".

## Quotes

- [3:20](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=200s) "there's so much coming out that it feels like it's changing by the minute because I can't keep up with the volume."
- [4:36](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=276s) "It is a challenge coming up with sessions so far in advance because you want to talk about things that are relevant at the"
- [8:38](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=518s) "Over the years, I've noticed that the ones that don't quite fit development and don't quite fit leadership get rejected more often than than"
- [11:50](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=710s) "we have like about 50 developers. We allow our customers to, you know, write their own code and contribute to their apps alongside of"
- [12:42](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=762s) "it's very grounded in that content and it's like definitive like you can say this"

## Disclaimers in the video

- [29:36](https://www.youtube.com/watch?v=Ty6ZvzJYAvI&t=1776s) other: There's no like standard. You don't feel like you are really grounded in your standards because your standards are always ...

Presenters (as heard): Chris, Brad, Matt, Matt Traxinger, Tanya Brockmann, Tanya, Tony, Matt Traxler.