Agile Artificial Intelligence: An Introduction to AIOps

You've decided Artificial Intelligence (AI) can help your customers? Excellent! AI is increasingly accessible today. However, deploying AI solutions into production in a way that is repeatable, maintainable, and scalable presents its own set of challenges. AIOps, which integrates DevOps and Agile methodologies, addresses these challenges and enhances outcomes by fostering cross-functional collaboration, enabling fast iterative development, and prioritizing end-to-end automation.

This talk will introduce AIOps, explaining what it is, how it compares to other *Ops practices, and how AIOps principles can be applied through three case studies during the session.

How to Avoid Meetings That Could Have Been An Email

Meetings can be so hazardous to the productivity of an organization that the CIA’s precursor, the OSS, included them in their sabotage field manual. While we may not be called upon to thwart direct enemy action, as meeting facilitators we should run the kinds of meetings we would want to attend. There are many reasons meetings are ineffective, most of which can only be mitigated before the meeting happens. This talk will give you things to consider and do to prepare for a meeting.

Attendees will leave with some techniques they can use today to make the most of their precious time. This is primarily aimed at anyone running a meeting. Facilitators, scrum masters, team leads, and managers most often do this, but anyone attending a meeting could benefit. To misquote Arleen Lorrance, “be the meeting you want to see happen.”

Avoiding False Starts With Artificial Intelligence

Artificial Intelligence (AI) is no longer science fiction; it’s here today, and it’s here to stay. It is in the products you use every day: home automation, digital assistants, or credit card fraud detection, just to name a few.

All businesses will be affected by AI in the coming years, and the impact will be significant. The only remaining question is, how will you influence its effect on your company?

Getting started with AI is a daunting task, but necessary for businesses who want to stay competitive. During this session, we’ll discuss:

* How to determine if, where, and how to use AI effectively within your organization
* When and how to build an AI team
* Common early mistakes and pitfalls when getting started with AI
* Typical misconceptions around AI and its application
* What to look for in an AI partner or potential hire

When is a Regular Expression Better Than Artificial Intelligence?

When we need to scale a product, automation is almost always the right answer, and it’s easy to reach for Artificial Intelligence (AI) because it’s so broadly applicable. However, a general-purpose tool like AI often underperforms when compared to more specialized tools. This talk is a case study about a product team that was scaling their product (scoring assignments against a rubric) with AI (using GenAI, NLP, and ML) and not seeing the results they expected. In this talk we will discuss why and the special-purpose techniques we used in place of AI.

By the end of the talk, the audience will have been introduced to two models for AI-based natural language and code understanding. We will establish some heuristics for deciding when AI is necessary or when a more specialized technique is likely be more desirable. These discussions don’t require a fluency in AI itself, GenAI, ML, NLP, or any of the other technologies we used. The important part is a desire to find the right technology for a given problem.

Can We Learn to Manage Uncertainty? Probably!

When we’re asked when something will be done, it’s tempting to answer the question. “It’ll be done on March 32nd” or “it’ll take 182.5 days” or “we need 15 sprints”. It doesn’t matter if that answer is the best-case, average, or worst-case scenario.

The answer is fundamentally wrong because using a single value hides the fact that what we really meant was a distribution of possible dates, durations, or outcomes. The exact value is uncertain. Development may be faster or slower than we thought. What if the tech lead wins the lottery and retires? What if a global pandemic forces us to change the way we work?

While we can’t control any of those factors, we can be mindful of their existence and communicate more clearly. In this talk we will introduce “bet” language, which makes uncertainty and luck an explicit part of the conversation. This mindset helps us accurately assess risks, pick the right risks to embrace, and avoid analysis paralysis. It also helps us learn in an uncertain world, where even if we make good decisions, we may experience bad outcomes (and vice versa!).

What Does Security Look Like When Building AI?

Anyone who is working with AI or considering doing so should care about security. When considering building an AI-powered system or product, the traditional attack surfaces and mitigations still apply. However, new attack surfaces can be present depending on the specific AI approaches used. In addition, due to the typically higher level of automation in AI systems, they can do more harm if they are compromised.

In this talk, we’ll discuss how AI has the same attack vectors as traditional software, and what those attacks look like. We’ll also discuss new attacks that are specific to generative AI (e.g. LLMs like ChatGPT), machine learning & computer vision systems, and optimization techniques. For each type of attack, we’ll point out how they can be thwarted, or at least mitigated.

Previous experience with AI and security are not required to benefit from the session. Attendees will see techniques to help write more secure AI-enabled software. They will walk away with a better understanding of AI-specific attack vectors and their mitigations. They will be equipped to find security education resources in the future.

Previous experience with AI and security are not required to benefit from the session. The goal is not to teach attendees the intricacies of the techniques, but rather to give them the lay of the land and the key terms to google when they leave.

Creating Generative AI & LLM-Powered Applications

Many companies are exploring what can be done with LLMs, and LLM skills are in high demand. However, large language models are a huge field of study that is growing daily. Knowing where to start isn’t easy, and best practices are changing rapidly.

While there are a billion LLM tutorials, they often show how to build a toy demo without explaining the underlying foundational principles. These are key to understanding the behaviors of LLMs and deploying robust LLM-powered applications.

This workshop seeks to address this gap. Each 1-hour session is self-contained, i.e. fresh code is provided at the start of each session, so attendees can drop in and drop out without missing anything.

Session 1: How does an LLM work?
* Overview of the training process
* Overview of the generation (output) process
* What is "truth" to an LLM?
* The difference between creativity and hallucination

Session 2: Build a chatbot
* What happens when an LLM doesn’t know the answer?
* The difference between an LLM and an LLM-powered product application
* How can we introduce new knowledge to the LLM?
* How do we test & evaluate the LLM’s output?
* LLM caching to save on cost

Session 3: Build a knowledge base question-answering tool
* Explore model fine-tuning vs Retrieval-Augmented Generation (RAG)
* Overview of RAG & an implementation
* Data provenance concerns & approaches
* IP concerns & approaches

Session 4: Prompt engineering
* Techniques & approaches
* Chain of Thought
* Few- and many-shot learning
* Prompt injection

Notes to organizer/selection committee: each 1-hour session is self-contained, i.e. fresh code is provided at the start of each session, so attendees can drop in and drop out without missing anything.

Stay Awhile and Listen

Deckard Cain had it right: telling an engaging story is a powerful tool. While we may not be fighting the forces of darkness, the stories and words we use can influence the future of our features, products, and even our company. Storytelling is a powerful tool that can bridge gaps between teams, clarify complex concepts, and keep user needs at the forefront of the development process. Stories and narratives increase engagement and retention. They make it easier to explore "what ifs" through analogies and metaphors.

In this talk, we’ll explore the role of storytelling in software development, such as how narratives can increase empathy with users, drive design decisions (and user-centric design), and align cross-functional teams toward a shared vision. We’ll look at real-world examples of how storytelling has shaped successful projects across multiple industries, and maybe a few failure cases, too. Whether you're a developer, designer, or product manager, you'll leave with actionable insights on how to harness the power of storytelling to build better, more impactful software.

Lessons From My Many Careers in Software Development

In a fast-paced and ever-changing tech industry, experience with multiple roles is a great asset. Embracing diverse experiences will enhance your career. That said, it’s not easy to step into a new role, deal with uncertainty & imposter syndrome, come up to speed in new knowledge areas, and learn to work with new groups, departments, verticals, and companies.

In this talk, we’ll discuss how to approach a new role, apply prior skills to new roles, and acquire new skills. I will share insights and anecdotes from my career journey through various positions in the software development field. From developer to tech lead to team lead to product owner to AI Lead, each role has presented unique challenges and opportunities for growth. This session will explore the key skills that have been essential in successfully transitioning between roles, strategies for continuous learning, and offer actionable advice on how to navigate your kind of career in software development.

What Are AI Agents, Anyway?

Terms like 'AutoGPT,' 'agent-based systems,' and 'agentic AI' are trending, building on the momentum of Generative AI. This approach promises systems capable of autonomously executing complex tasks while adapting to changes with minimal human intervention.

It’s one thing to promise, and another entirely to deliver. As the hype around “AI agents” grows, so does the confusion: What exactly are they? How do they differ from traditional AI models? Why do so many implementations fall short of their promises?

In this talk, we’ll go over what AI agents really are: how they work, where they succeed, and where they fail. We’ll look at some agentic AI design patterns and how they are analogous to traditional software tools, databases, networks, and peer-to-peer systems.

Learning objectives:
* What is an AI Agent?
* How do they differ from traditional AI? From generative AI (e.g. LLMs)?
* When to use / when not to use
* Design patterns
* Multi-agent