InfoQ - QCon Software Development Conference

Presentation: Building Reusable Evaluation Frameworks for Agentic AI Products

Susan Chang — Mon, 05 Oct 2026 11:19:00 GMT

Susan Chang explains how Elastic transitioned from siloed, ad-hoc AI agent evaluations to a unified, production-grade framework. She discusses balancing LLM-as-a-judge with deterministic rules, bridging Python data science evals with TypeScript production code, and implementing deep tracing to catch regressions across complex RAG and cybersecurity workloads while preserving domain context.

By Susan Chang

Presentation: Building GenAI Platform at DoorDash

Siddharth Kodwani, Swaroop Chitlur — Sat, 03 Oct 2026 11:00:00 GMT

Swaroop Chitlur and Sidd Kodwani share DoorDash’s journey building an internal GenAI platform. They discuss core architectural bets, transitioning from vendor-first setups to open-weights models, navigating LLM and agent gateways, and balancing accuracy, latency, and cost for over 5,000 internal users.

By Siddharth Kodwani, Swaroop Chitlur

Presentation: Managing Asynchronous APIs at Scale

Ian Cooper — Fri, 02 Oct 2026 11:00:00 GMT

Ian Cooper discusses managing asynchronous APIs in event-driven architectures at scale. He explains the "ABCs" of messaging (Address, Binding, Contract) and shares how to tackle discovery, governance, and provisioning using AsyncAPI, CloudEvents, schema registries, and automated CI/CD infrastructure pipelines based on real-world engineering practices at Just Eat Takeaway.

By Ian Cooper

Engineering Production Systems for an Agentic Era: QCon San Francisco 2026

Artenisa Chatziou — Fri, 02 Oct 2026 10:00:00 GMT

QCon San Francisco 2026 will bring together practitioners from Airbnb, OpenAI, Netflix, Honeycomb, and other engineering organizations to share how they are building, operating, and evolving production systems as AI agents take on a larger role.

By Artenisa Chatziou

Presentation: Keeping the Mainline Green across Diverse Language Monorepos

Dhruva Juloori — Thu, 01 Oct 2026 09:33:00 GMT

Dhruva Juloori discusses how Uber maintains green mainlines across massive monorepos handling 65,000+ monthly changes. He explains how SubmitQueue uses binary speculation trees, conflict analysis, and machine learning models to predict build success and execution times. Juloori shares how bypassing large diffs slashed CI resource usage by 53% while accelerating PR landing times by 37%.

By Dhruva Juloori

Presentation: Context is the New Code

Patrick Debois — Wed, 30 Sep 2026 11:00:00 GMT

Patrick Debois discusses how to manage, evaluate, distribute, and observe context using proven software engineering practices. He shares how treating context like code - complete with testing, CI/CD, package managers, and security scanning - enables engineering leaders to reliably scale AI coding agents, maintain control over non-deterministic outputs, and build long-term organizational knowledge.

By Patrick Debois

Presentation: From Staff Platform Engineer to a16z Founder: What I Wish I'd Known

Gonzalo Maldonado — Tue, 29 Sep 2026 09:14:00 GMT

Gonzalo Maldonado explains how technical leaders can translate engineering skills into startup success using their "VC Abstraction Layer Knowledge" (VALK). They share hard-won lessons on finding product-market fit, structuring pitches like technical docs, avoiding co-founder drama, and evaluating internal platforms as commercial ventures in a post-ZIRP environment.

By Gonzalo Maldonado

Presentation: From Consumers to Builders: Turning 200 of our Team into Agent Creators in Two Weeks

Ben Maraney — Mon, 28 Sep 2026 11:00:00 GMT

Ben Maraney shares how Forter demystified AI agent creation for technical and non-technical staff. He discusses leveraging custom MCP servers, combining no-code and code-based platforms, sidestepping complex RAG setups, and aligning security and legal teams to accelerate internal agent adoption across R&D.

By Ben Maraney

Presentation: Adaptive Recommenders in the Real World: Inference, Evals, and System Design

Mallika Rao — Sat, 26 Sep 2026 11:00:00 GMT

Mallika Rao explains that the true complexity of adaptive recommendation systems lies outside model architecture. She discusses how real-time feedback loops, retrieval freshness, multi-stage orchestration, and end-to-end latency budgeting enable systems to continuously learn and evolve in production under real-world operational constraints like latency, cost, and observability.

By Mallika Rao