AI is changing both how we build software and who we're building it for.
For October's Practically AI, we have two talks exploring those changes from very different perspectives. First, we'll follow the evolution of AI-assisted software engineering from prompts and context through to autonomous loops and graphs and the engineering practices required to make them reliable.
Then we'll look at a different kind of engineering challenge: the hidden Inclusion Debt we create when the assumptions built into our software and AI systems don't hold true for everyone.
Two talks, one common theme: as AI becomes a bigger part of software engineering, good engineering matters more, not less.
-----------------------------
Phil Whittaker - Prompt > Context > Harness > Loop > Graph: The Evolution of Agentic Software Engineering
Loop and graph engineering are the phrases of the moment, but getting started can feel like learning to run before you can walk.
Phil will work through the stages engineering teams experience as they move from simple prompting to managing context, building effective agent harnesses and eventually creating reliable autonomous development loops and graphs.
Rather than jumping straight to autonomy, we'll look at what each stage adds, the problems it solves and the new engineering challenges it introduces.
Along the way, we'll examine something equally important: the traditional software engineering practices that make all of this actually work.
You'll learn:
- How AI-assisted development evolves from prompting to context engineering
- Why the agent harness is becoming an important part of the engineering stack
- How autonomous development loops work and what makes them reliable
- Where graph-based workflows fit as systems become more complex
- Why testing, architecture, observability, feedback and engineering discipline become more important as autonomy increases
The tools are changing. Feedback loops are getting faster. Automation is increasing. But designing, validating and operating reliable systems still requires engineering discipline.
This is not the end of software engineering. This is software engineering.
-----------------------------
Heather Perriam : Inclusion Debt
We talk about technical debt all the time. We can see it, estimate it and eventually pay it back.
Inclusion Debt is different.
It's the hidden cost that accumulates every time we design software, AI systems or workplace processes around assumptions that don't hold true for everyone.
An interface that overloads working memory. An AI prompt that assumes perfect written English. A chatbot that only understands one communication style. A workflow that quietly excludes someone without anybody noticing.
Unlike technical debt, Inclusion Debt rarely appears on a backlog. It doesn't break the build. Instead, users disengage, employees create workarounds and AI systems can produce increasingly unreliable outcomes.
Heather will explore why AI has the potential to amplify Inclusion Debt faster than previous technologies, and what engineers can do about it.
You'll learn:
- What Inclusion Debt is and how to recognise it in the systems you build
- How seemingly small technical and design decisions can exclude users
- Why AI systems can amplify existing assumptions and biases
- How inclusion affects the quality and reliability of AI-powered products
- Practical techniques for evaluating software against the needs of real people, rather than an imagined "average" user
As developers, architects and technical leaders, we're increasingly responsible for systems that don't just work — they need to work for real people.
Who Should Attend:
Software engineers, AI engineers, architects, tech leads and engineering leaders building with AI or responsible for the systems around it.
Whether you're experimenting with coding agents, building autonomous engineering workflows, designing AI-powered products or thinking about how those products work for the people using them, both sessions offer practical ideas you can take back to your team.
Why It's Worth Attending:
Practically AI is about the engineering reality of AI — real implementations, practical techniques and honest conversations about what's working and what isn't.
October gives us two complementary perspectives. We'll look at how increasingly autonomous AI changes the way we engineer software, while also considering the responsibility we have for the systems that result.
You'll leave with ideas you can apply to your engineering workflows immediately, a different way of thinking about software quality, and plenty of opportunity to discuss it all with Manchester's growing community of engineers working with AI.
## Agenda:
18:30 – Doors, pizza & mingling
18:50 – Introductions
19:00 – Talk: Prompt > Context > Harness > Loop > Graph – Phil Whittaker
19:40 – Talk: Inclusion Debt – Heather Perriam
20:10 – Open social & refreshments
21:00 – Close
## Entry:
Upon arrival at AZoNetwork, Manchester, please check in at reception and you'll be directed to the meetup.
Pizza and soft drinks provided.
