They tried to make me do a reorg, but I said no, no, no

Inspired by a comment from Anders Bruvik, I asked ChatGPT 4o to write some song lyrics about the dreaded “re-org” and include some Team Topologies ideas:

Please write song lyrics that are similar to the lyrics of the song “Rehab” by Amy Winehouse but are instead focused on avoiding a “reorg”. Include some concepts from Team Topologies. The first line of the song should be “They tried to make me do a reorg, but I said no, no, no”

Here is the result – it’s not bad!

UPDATE: Stephen Kurzeja did a GenAI version of the song via Suno using the lyrics from ChatGPT 🤩 – https://suno.com/song/c4a1e33b-577d-49b1-a438-d3ed0d8d341c


Verse 1:

They tried to make me do a reorg, but I said no, no, no
I like my team just the way it is, can’t you see it’s a flow, flow, flow
I know the silos are hard, but trust the Stream-Aligned
We’ll deliver value fast, on time, on time

Chorus:

I don’t need no new boundaries, or Conway’s Law fix
With clear communication, our team really clicks
You say DevOps, I say fine, just give me a task to grow
But reorgs break our rhythm, and the answer is no, no, no

Verse 2:

They’re talking about Complicated Subsystems, and let’s dismantle the mess
But we need our Enabling Teams, to help and not to impress
Coordination’s key, with our Platform and Stream
Reorgs just shuffle pieces, and disrupt the dream

Chorus:

I don’t need no new boundaries, or Conway’s Law fix
With clear communication, our team really clicks
You say DevOps, I say fine, just give me a task to grow
But reorgs break our rhythm, and the answer is no, no, no

Bridge:

We got Team Topologies, and we know our roles
Collaborating fluidly, achieving all our goals
You think the org chart changes everything, but I say it’s a show
We got our ways of working, and that’s why the answer’s no

Chorus:

I don’t need no new boundaries, or Conway’s Law fix
With clear communication, our team really clicks
You say DevOps, I say fine, just give me a task to grow
But reorgs break our rhythm, and the answer is no, no, no

Outro:

Don’t need no reorg, don’t need no shake-up plan
With our team topology, we’re doing all we can
Alignment and flow, that’s how we like to go
Reorgs just bring chaos, so the answer is no, no, no


And for completeness, here is the original video of “Rehab” by the superb Amy Winehouse 💖

Designing organisations for responsiveness

Key points:

  1. Set up the organisation to ‘sense’ its environment
  2. Treat internal teams (almost) as external providers
  3. Conway’s Law should shape our organisation design
  4. Promise Theory is a useful approach to organisational agility

IMG_20171002_125459

I have been doing quite a bit of work recently with various organisations to help them develop new capabilities for building and evolving software-rich services. Part of this work involves thinking about the responsibilities of different teams and how these evolve. This blog post captures some thoughts and links on how the more successful organisations arrange themselves for agility and responsiveness.

Continue reading Designing organisations for responsiveness

Slides from Team and Monoliths talk at Velocity Conf EU, Amsterdam, 7 Nov

I gave a talk at Velocity Conference Europe 2016 called How to break apart a monolithic system safely without destroying your team based on work we have done at Skelton Thatcher Consulting over the past few years with various organisations.

Slides:

The slides are on Slideshare at http://www.slideshare.net/SkeltonThatcher/teams-and-monoliths-matthew-skelton-velocity-eu-2016 and the video of the talk will be online soon.

The main take-aways from the talk are:

  • Recognise that by starting with the needs of the team, we can avoid cognitive overload, thereby making future development more sustainable
  • Understand the type of monolith you are dealing with (there are many kinds of monolith)
  • Consider using Code Forensics (see Your Code as a Crime Scene)
  • Find the natural ‘fracture planes’ in your code and work with these
  • Instrument the monolith before splitting it up
  • Understand data flows and fault responses
  • Split off one segment of code at a time, considering the cognitive load for the team

There is quite a bit more in the talk itself, including the effect of Conway’s Law, the benefits of monoliths, and real-world examples from client engagements.

teams-and-monoliths-summary

A big thanks from me to the organisers of VelocityConf for their hard work, to the audience in my talk for some excellent questions, and to the speaker selection panel for choosing my talk (!).

New eBook on Continuous Delivery with Windows and .NET

Back in 2010 when Jez Humble and Dave Farley wrote their ground-breaking book Continuous Delivery, the Windows and .NET platforms lagged behind the Linux/Mac world in terms of automation capability. That is no longer the case – every core feature in Windows and .NET now has a PowerShell API and all the core tooling needed for Continuous Delivery – package management, artifact repositories, build servers, deployment pipelines tools, infrastructure automation, monitoring,and logging – are all now available natively on Windows/.NET.

Chris O’Dell (@ChrisAnnODell) and I decided we should explain how to make Continuous Delivery work with Windows and .NET, and thanks to the great editorial team at O’Reilly, we’ve published a short eBook:

CD with Windows - cover

The dedicated book website is at CDwithWindows.net and O’Reilly have published the first chapter of the book online as an article: Introduction to Continuous Delivery with Windows. We’d love your feedback: book@cdwithwindows.net

UPDATE: we’ll be at both PIPELINE Conference (March 23 2016) and WinOps Conference (May 24 2016) with printed copies of the book.

Note: we began writing the book in August 2015, and it’s astonishing (and exciting!) how much has changed in the 8 months since then, with Windows Nano, Azure and Windows support for Docker and containers, .NET Core, SQL Server on Linux, and even SSH for Windows. These and more recent developments do not feature in the book – perhaps we’ll do an updated version soon. 

Continuous Delivery for databases: microservices, team structures, and Conway’s Law

The way we think about data and databases must adapt to fit with dynamic cloud infrastructure and Continuous Delivery. The need for rapid deployments and feedback from software changes combined with an increase in complexity of modern distributed systems and powerful new tooling are together driving significant changes to the way we design, build, and operate software systems. These changes require new ways of writing code, new team structures, and new ownership models for software systems, all of which in turn have implications for data and databases.

Read the full article on Simple Talk: Continuous Delivery for Databases: Microservices, Team Structures, and Conway’s Law.

(These slides were presented in a talk I gave at develop:BBC 2014 conference on 13th November in London)