# QCon Software Development Conference Published articles for QCon Software Development Conference. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## QCon AI New York 2026 Program Committee Picks: Agent Identity, Context Costs, and Open-Source Infere DevFeed: [QCon AI New York 2026 Program Committee Picks: Agent Identity, Context Costs, and Open-Source Infere]() Original publisher: [Read original article]() Author: Artenisa Chatziou Published: 2026-10-29T11:00:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [AI Context Management](), [Agent Harness](), [Open Source]() Tags: [2026](), [actions](), [agent](), [agent-identity](), [agents](), [ai](), [ai-ml-data-engineering](), [anthropic](), [api](), [architectures](), [audio](), [authorization](), [context](), [costs](), [identity](), [inference](), [ml-data-engineering](), [new-york](), [news](), [open-source](), [qcon-ai-new-york-2026](), [qcon-ai-newyork-2026-pc-picks](), [qcon-software-development-conference](), [questions](), [standards](), [teams]() ### AI overview The QCon AI New York 2026 committee's six picks focus on production challenges in agentic systems and AI engineering. Sessions cover delegated authority, credential handling, and agent security; LLM context compression, caching, and retrieval, including failure modes in tool use; how coding agents may reshape engineering teams and junior roles; and open-source inference with Agentic API, vLLM, and llm-d, where cost per completed task is emphasized over token price alone. The remaining picks examine agent standards including MCP, A2A, and OAuth, distinguishing shipped capabilities from open work, and audio AI trade-offs such as end-to-end versus cascaded architectures and latency versus quality. The source presents these as conference session topics and committee selections, not as settled conclusions. ### Source excerpt Who authorizes an agent's actions, and how should teams manage growing context costs? The QCon AI New York 2026 program committee shares six session picks that tackle these questions, alongside open-source inference, agent standards, and audio AI. By Artenisa Chatziou ## QCon London 2027 Announces 15 Tracks on Production AI, Architecture, and Engineering at Scale DevFeed: [QCon London 2027 Announces 15 Tracks on Production AI, Architecture, and Engineering at Scale]() Original publisher: [Read original article]() Author: Artenisa Chatziou Published: 2026-10-06T10:00:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [Software Engineering](), [Chaos Engineering](), [software-architecture](), [AI Engineering](), [engineering-leadership](), [CI/CD](), [Platform Engineering](), [site-reliability-engineering]() Tags: [ai](), [ai-architecture](), [ai-ml-data-engineering](), [architecture](), [architecture-design](), [artificial-intelligence](), [development](), [distributed](), [engineering](), [leadership](), [ml-data-engineering](), [news](), [performance-engineering](), [production-ai](), [qcon-london-2027](), [qcon-software-development-conference](), [qconlondon-2027-track](), [software-engineering]() ### AI overview InfoQ previews the 15-track QCon London 2027 program, which covers agent evaluation and guardrails, AI-era architecture and software delivery, distributed systems, data platforms, performance, and technical leadership. The article emphasizes assessing production trade-offs and applying practices in the context of each team's systems and organization. ### Source excerpt A preview of the 15-track QCon London 2027 program, covering agent evaluation and guardrails, AI-era architecture, distributed-system debugging, modern data platforms, high-performance engineering, and Staff+ leadership. By Artenisa Chatziou ## Engineering Production Systems for an Agentic Era: QCon San Francisco 2026 DevFeed: [Engineering Production Systems for an Agentic Era: QCon San Francisco 2026]() Original publisher: [Read original article]() Author: Artenisa Chatziou Published: 2026-10-02T10:00:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [QCon San Francisco 2025](), [AI Engineering](), [Software Engineering](), [Platform Engineering](), [Production Engineering](), [engineering-leadership]() Tags: [agentic](), [agents](), [ai](), [ai-agents](), [ai-ml-data-engineering](), [airbnb](), [architecture-design](), [artificial-intelligence](), [coding-agents](), [developer-productivity](), [development](), [engineering](), [ml-data-engineering](), [netflix](), [news](), [openai](), [production](), [qcon-san-francisco-2026](), [qcon-software-development-conference](), [qconsf-2026-sessions](), [systems]() ### AI overview QCon San Francisco 2026 will feature sessions on deploying AI agents in customer-facing systems, setting boundaries for coding agents, managing distributed-system trade-offs, and making production systems understandable to agents. The program emphasizes safeguards, verification, observability, and engineering judgment as agents enter production workflows. ### Source excerpt 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 ## From Staff Platform Engineer to Startup Founder: Lessons on Product-Market Fit and Leadership DevFeed: [From Staff Platform Engineer to Startup Founder: Lessons on Product-Market Fit and Leadership]() Original publisher: [Read original article]() Author: Gonzalo Maldonado Published: 2026-09-29T09:14:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Platform Engineering]() Tags: [best-practices](), [co-founder](), [culture-methods](), [engineering](), [infoq](), [presentation](), [product-market-fit](), [qcon-san-francisco-2025](), [qcon-software-development-conference](), [staff-founder-lessons](), [staff-plus](), [transcripts]() ### AI overview Gonzalo Maldonado shares lessons for technical leaders moving from engineering into startup work. He discusses finding product-market fit, structuring pitches like technical documentation, avoiding co-founder conflict, and considering internal platforms as commercial ventures in a post-ZIRP environment. ### Source excerpt Gonzalo Maldonado explains how technical leaders can translate engineering skills into startup success using his "VC Abstraction Layer Knowledge" (VALK). He shares 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 ## From Agent Authorization to AI Production Evaluation: QCon AI New York 2026 DevFeed: [From Agent Authorization to AI Production Evaluation: QCon AI New York 2026]() Original publisher: [Read original article]() Author: Artenisa Chatziou Published: 2026-09-25T11:00:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [Artificial Intelligence](), [AI Engineering](), [Authorization](), [sessions](), [Platform Engineering](), [model-serving](), [observability](), [Kubernetes]() Tags: [2026](), [ai](), [ai-architecture](), [ai-engineering](), [ai-ml-data-engineering](), [ai-systems](), [architecture](), [architecture-design](), [artificial-intelligence](), [authorization](), [ml-data-engineering](), [model-serving](), [news](), [observability](), [policy-enforcement](), [qcon-ai-new-york-2026](), [qcon-ai-newyork-2026-sessions](), [qcon-software-development-conference]() ### AI overview QCon AI New York 2026 has announced 23 of more than 30 sessions focused on production AI systems. Topics include authorization for autonomous agents, operational guardrails for Kubernetes infrastructure, shared model-serving platforms, and post-deployment evaluation of AI decision systems. ### Source excerpt QCon AI New York has confirmed 23 sessions covering agent authorization, production guardrails, shared inference infrastructure, and the evaluation of AI systems after deployment. By Artenisa Chatziou ## Presentation: Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP DevFeed: [Presentation: Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP]() Original publisher: [Read original article]() Author: Ajay Prakash Published: 2026-09-19T11:00:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Model Context Protocol](), [Artificial Intelligence](), [context](), [code search](), [Programming](), [AI Agent](), [reliability-engineering]() Tags: [agents](), [ai](), [ai-architecture](), [ai-ml-data-engineering](), [architecture](), [architecture-design](), [code-search](), [coding-agents](), [context-engineering](), [development](), [engineering](), [infoq](), [linkedin](), [linkedin-context-engineering](), [ml-data-engineering](), [model-context-protocol](), [model-context-protocol-mcp](), [presentation](), [productivity](), [qcon-ai-boston-2026](), [qcon-software-development-conference](), [reliability](), [transcripts]() ### AI overview Ajay Prakash presents LinkedIn's Contextual Agent Playbooks and Tools, which use MCP to provide procedural memory, code search, and runbooks to coding agents working in large codebases. The presentation covers the architecture and operational guardrails behind the system and reports a 20% productivity boost without loss of reliability. ### Source excerpt Ajay Prakash discusses how LinkedIn overcomes AI agent limitations in large codebases. He explains Contextual Agent Playbooks and Tools - built on Model Context Protocol (MCP) - which serves procedural memory, code search, and runbooks directly to coding agents. Prakash shares architectural details and operational guardrails that deliver a 20% productivity boost with zero loss in reliability. By Ajay Prakash ## Presentation: Teaching Engineers, Trusting AI: How Education Enabled Autonomous Code Review DevFeed: [Presentation: Teaching Engineers, Trusting AI: How Education Enabled Autonomous Code Review]() Original publisher: [Read original article]() Author: Sarah Deitke Published: 2026-09-16T11:00:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Artificial Intelligence](), [Code review](), [Pull Request](), [Developer Tools](), [engineering-culture](), [observability]() Tags: [adoption](), [agile](), [ai](), [ai-ml-data-engineering](), [architecture-design](), [artificial-intelligence](), [automated](), [automation](), [autonomous](), [case-study](), [code-review](), [code-reviews](), [culture](), [culture-methods](), [developer](), [developer-experience](), [development](), [duolingo-ai-literacy-code-review](), [infoq](), [metrics](), [ml-data-engineering](), [observability](), [pairing](), [presentation](), [qcon-london-2026](), [qcon-software-development-conference](), [transcripts]() ### AI overview Sarah Deitke presents Duolingo's approach to cultural AI adoption through internal AI literacy workshops, observability dashboards, and safe AI guardrails. The presentation includes a case study on redesigning code review with an automated PR risk-assessment bot and reports faster delivery without increased defect rates. ### Source excerpt Sarah Deitke discusses how Duolingo drives cultural AI adoption beyond tooling access. She explains their internal AI literacy workshops and observability dashboards, then shares a case study on redesigning code review using an automated PR risk-assessment bot. Deitke demonstrates how pairing targeted developer education with safe AI guardrails speeds up delivery without increasing defect rates. By Sarah Deitke ## Presentation: Accelerating Performance by Incrementally Integrating Rust Into Existing Codebase DevFeed: [Presentation: Accelerating Performance by Incrementally Integrating Rust Into Existing Codebase]() Original publisher: [Read original article]() Author: Lily Mara Published: 2026-09-10T09:34:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [Rust](), [Refactoring](), [Integration testing]() Tags: [architecture](), [cost](), [culture-methods](), [design](), [development](), [engineering](), [infoq](), [infrastructure](), [performance](), [presentation](), [python](), [qcon-san-francisco-2025](), [qcon-software-development-conference](), [refactoring](), [rust](), [rust-refactoring](), [system-programming](), [testing](), [transcripts]() ### AI overview A presentation on incrementally refactoring Python bottlenecks into Rust with PyO3 to improve function-level performance, retain integration testing, and reduce infrastructure costs. ### Source excerpt Lily Mara explains how to avoid high-risk software rewrites through incremental FFI refactoring. She shares how engineering teams can replace Python bottlenecks with Rust via PyO3, demonstrating how to achieve dramatic function-level speedups, seamless integration testing, and meaningful infrastructure cost savings without microservice overhead. By Lily Mara