2025 Schedule
Preliminary Schedule. The schedule is subject to change.
Tuesday, December 16th, 2025
Badge Pick-Up - Light Continental Breakfast Located on the 1st & 2nd Flr
Conference Introduction and Keynote:
The Next Generation of AI Products
Break - Snacks and Coffee Available on the 1st & 2nd Flr
Beyond Prompting: Context Engineering and Memory Management for AI Systems at Scale
As AI agents evolve from stateless prompt-response tools into stateful, long-running systems, context - not just compute - becomes the true bottleneck. Yet most architectures today treat context retrieval as an afterthought, bolting vector stores onto LLMs and hoping for the best.
Graph RAG: Building Smarter Retrieval Workflows with Knowledge Graphs
Retrieval-Augmented Generation (RAG) has unlocked new capabilities for large language models (LLMs) by providing them with external context.
Getting Rid of LeetCode Interviews in the World of AI
AI-fueled innovation is accelerating all around us, but one thing that is not changing are FAANG "leetcode" interviews. Experienced developers continue to be subjected to humiliating puzzles that can be memorized, sinking their time and talent into mindless learning of basic algorithms.
Reference Architecture for Agentic AI
The agentic AI landscape is facing an architectural crisis due to framework fragmentation, bottlenecking the creation of truly reliable autonomous systems.
Break
Moving Mountains: Migrating Legacy Code in Weeks instead of Years
Recently we've been working on migrating our enterprise reporting application to a modern open-source metrics store. Historically, large-scale legacy migrations have been some of the most challenging projects in software.
Fine Tuning the Enterprise: Reinforcement Learning in Practice
In this talk, we’ll discuss the Reinforcement Fine Tuning (RFT) platform, allowing you to train OpenAI models to reason better on your specific tasks to arrive at better answers.
The AI Gateway: Scaling Centralized Inference Across Decentralized Teams
As enterprises adopt AI, one tension has become clear: inference needs to be centralized for efficiency, governance, and reliability, while use cases and model development are necessarily decentralized across teams.
The Agent Execution Gap: Why Most Agent Systems Don't Go Beyond POC (And How Yours Can)
Agents shine in POCs but fail in production. This session shows how reliable, observable orchestration bridges the gap by embedding agentic behavior into business workflows, and how MCP gateways turn internal services into MCP tools so your APIs are agent ready without glue code.
Choosing Your AI Copilot: Maximizing Developer Productivity
The AI coding agent landscape evolves weekly. This talk compares today’s frontrunners, shows where each shines, and shares prompts, policies, and “rules templates” that turn code suggestions into production-quality output.
The Multi-Agent Approach: Building Reliable and Controllable Software Development Automation
AI-driven development is shifting from autocomplete to continuous, controllable automation across the SDLC. This talk presents a multi-agent architecture where specialized agents collaborate asynchronously — from planning and analysis to testing and code review.
Taming Agentic AI: Lessons from Streaming Architecture for Scalable, Safe Systems
Agentic AI is everywhere—but deploying it safely and reliably inside production systems is another story. The move from clever demos to autonomous agents that operate within enterprise infrastructure introduces new risks and architectural challenges.
The Modern Application Stack: Orchestrating Workflows, Agents, and Governance for Adaptive Systems
Modern applications behave less like codebases and more like distributed, adaptive systems.
Break
Panel: Scaling AI in Engineering - Driving Alignment, Adoption and Impact
AI is already reshaping software development—but most companies are stuck in pilot mode, unsure how to move from experiments to meaningful transformation. This panel will share practical experiences in adopting and scaling AI across the software development lifecycle.
From Hype to Strong Foundations: What the Rise, Fall and Resurgence of Agents Can Teach Us About Outlasting the Cycle
2025 has been declared "the year of agents", but so were 1994, 1998, and 2016. In fact, the history of agents is a story of recurring peaks and valleys.
Chaos Engineering GPU Clusters
We are used to the concepts of fault injection and chaos engineering in normal clusters and web api services. Techniques like node shutdowns, cpu exhaustion, memory leaks, etc. are all easy things to automate in Kubernetes with open source or proprietary tools.
Building Self-Healing, Hallucination-Aware AI Systems with Runtime Configuration
Building Self-Healing, Hallucination-Aware AI Systems with Runtime Configuration
Break - Snacks and Coffee Available on the 1st & 2nd Flr
Building Evals for AI Adoption: From Principles to Practice
As organizations adopt AI at scale, evaluation becomes the backbone of trust, safety, and product readiness. Yet building effective evals is deceptively hard: there is no single metric or benchmark that captures the complexity of user-facing AI systems.
From Copy-Paste to Composition: Building Agents Like Real Software
We're building AI agents like it's 1978. Our "programs" are monolithic prompts. Our "shared libraries" are MCP tools that get copy-pasted into context windows. Our "architecture" is hoping the LLM figures it out.
Building MCP Servers That Make Agents More Effective
Agents often rely on external tools to help them accomplish their tasks, and external MCP servers are convenient for getting those tools with minimal code.
SovrenOS: Building a Truth-Native Operating System for AI
AI systems continue to struggle with hallucination because they have no consistent way to distinguish truth from plausible fabrication. Most solutions attempt to patch this problem at the model layer or through external guardrails.
Break
Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery
Modern AI platforms don’t have to choose between deterministic precision and probabilistic exploration—they need both.
AI-First Software Delivery: Balancing Innovation with Proven Practices
As AI reshapes the work of software teams and brings both opportunities and uncertainties, ensuring high-quality delivery becomes even more essential.
Live Demo – Develop and Deploy a Trustworthy Multi-Agent System
Agents are inherently unreliable. While simple to prototype, agentic systems with their many (distributed) moving parts are complex, have degrading trust, and are expensive due to inefficient model usage and ineffective scaling.
Unconference Session: Brainstorming with Peers
What is Unconference?Unconference sessions are a simple way to run productive meetings for 5 to 2000 or more people, and a powerful way to lead any kind of organization in everyday practice and extraordinary change.
Room 21, 2nd Flr
Reception - Dry Snacks & Drinks - 2nd and 3rd Flr - Sponsored by Kurrent
Wednesday, December 17th, 2025
Badge Pick-Up - Light Continental Breakfast Located on the 1st & 2nd Flr
Workshop: Supercharged Scripting for Integration Testing
Conference Introduction and Keynote:
Deepfakes, Disinformation, and AI Content Are Taking Over the Internet
Break - Snacks and Coffee Available on the 1st & 2nd Flr
Platform Teams Enabling AI - MCP/Multi-Agentic Tools Across Linkedin
Discover how LinkedIn is operationalizing AI tools at scale to drive measurable productivity gains across its engineering organization.
Leadership in AI-Assisted Engineering
To realize meaningful returns on AI investments, leadership must take accountability and ownership of establishing best practices, enabling engineers, measuring impact, and ensuring proper guardrails are in place.
Autonomous Data Products for the Autonomous Era: Rethinking Data Architecture for GenAI
As enterprises scale their deployment of Generative AI (Gen AI), a central constraint has come into focus: while large language models and the infrastructure to support them are the focus of intensive investment fueling a remarkable stream of innovation, data management approaches and infrastruct
Vibes Won't Cut It: Agentic Engineering in Production
If you think AI agents code like junior engineers that's because you set it up to code like a junior engineer. AI is a tool, not a magic wand, and like any tool you need to take time to learn and sharpen it.
Break
AI Native Engineering
Meta is making a big, public bet on AI - and not just in our products. Teams across the company are building new tools to leverage best-in-class models to enhance productivity, quality and understanding.
Infusing AI into the DNA of Engineering Organizations
Every engineering leader today is under pressure to “do something with AI.” The challenge is figuring out how to infuse AI into the day-to-day work of teams without falling into hype or overwhelming them with complexity.
Postgres for Production Agents: Your Relational Foundation for Enterprise AI
Retrieval Augmented Generation (RAG) is now a fundamental pillar of enterprise AI, moving beyond initial adoption to production-grade applications.
Using GenAI Where It Truly Shines: Building a Strengths-Optimized App
GenAI can generate working interfaces, flows, and logic in minutes—but knowing what to let it handle is just as important as knowing what to take back into human hands.
Using AI as a Thinking Partner for Large-Scale Engineering Systems
Google Cloud’s SDK and client library ecosystem spans nine programming languages, hundreds of repositories, and multiple generations of specifications and tooling.
From OTEL to SLMs: Distilling Frontier Model Behaviour from Production Telemetry
Your production agents already generate rich training data: every interaction is captured in your OTEL traces. This talk shows how to distill that telemetry into datasets to fine-tune Small Language Models (SLMs) and turn the process into a repeatable platform capability.
Building AI Agents for 127 Million Customers: Practical Lessons from Nubank
Scaling autonomous AI agents to serve over 127 million customers introduces significant challenges. This technical talk details the system design patterns and engineering principles employed at Nubank to build and operate production-grade, customer-facing AI agents.
Agentic Inception - Use Agents to Build Agentic Systems
Everyone is using AI coding assistants these days. Regardless of how we feel about this, assisted coding isn’t going away anytime soon, so what can we do to embrace and leverage it?
Break
AI Works, Pull Requests Don’t: How AI Is Breaking the SDLC and What To Do About It
This talk will use CircleCI’s adoption of AI agents as a lens for both individual and organizational changes that AI brings. We will first discuss the realities of using AI as an individual engineer, where things work well today, and where tools are lacking.
Rules for Understanding Language Models
After millions of years of evolution, humans understand each other pretty well. But now, confronted with machines that talk, we cannot assume they will act like humans, or act for the same reasons as humans.
Scaling Code Maintenance with AI agents: Resolve CVEs 10x Faster
One of the hardest truths about contemporary software is that it rots: dependencies go out of support, vulnerabilities are announced, and APIs break. Keeping up is a huge burden for software teams, and mostly involves rote work and toil, rather than creativity or deep thought.
People, Process & Probability: Scaling AI learning through Collaboration
Most AI projects impress in demos but fail in production. While 60% of CIOs expect GenAI workloads by 2025, only a few deliver meaningful results.
What I Learned Building Multi-Agent Systems From Scratch
A multi-agent orchestration system emerged from a hack days frustration—manually copying code between two Claude Code windows. What started as a simple experiment became a tool that reduced a 22-hour task to 7 minutes and saw significant adoption across Shopify.
AI Agents to Make Sense of Data at OpenAI
OpenAI's internal data platform spans tens of thousands of tables and hundreds of petabytes of data. It’s powerful, but navigating it without deep institutional knowledge is hard.
Evolution of the Modern Vector Database Architecture
Great systems often begin as simple modules solving a specific problem, then grow into complex architectures to meet needs at scale. Many of today's databases and infrastructure tools followed this path—and Milvus vector database was no different.
Unconference Session: Brainstorming with Peers
What is Unconference?Unconference sessions are a simple way to run productive meetings for 5 to 2000 or more people, and a powerful way to lead any kind of organization in everyday practice and extraordinary change.
Room 21, 2nd Flr
QCon AI Closing Reception - Dry Snacks & Drinks - 2nd and 3rd Flr.
