July 6 - 7, 2026
AI Coding Summit
London, UK & Online

AI Coding Summit London

See how AI transforms software development

The first hybrid AI Coding Summit lands in London and stays online. A two-day hybrid conference featuring advanced talks and hands-on workshops on AI-powered software development, agentic coding patterns, orchestration, AI-assisted testing, CI/CD for agentic workflows, and building AI-native products. 20+ sessions, 200+ attendees in-person, and 5,000+ online. Learn repeatable playbooks from practitioners, not hype. Network with engineers and founders building the AI-native stack.



Esta edición del evento ha finalizado, las últimas actualizaciones de este Tech Conference están disponibles en el sitio web de la marca.
Diseño de Habilidades para Agentes LLM
24 min
Diseño de Habilidades para Agentes LLM
Minko Getschev, AI lead at Google, shares insights on building effective agent skills, including architecture, skill creation best practices, and evaluation methods. Agent decision-making, planning, and hybrid architectures are explored, with a focus on the React loop for tool utilization. Context expansion and management, utilizing tools like MCP and CLIs, enhance agent power. The discussion includes comparisons between MCP and CLIs in agent systems, emphasizing context handling and debugging. Agent skills are structured as procedural instructions, with an open standard focused on tasks and workflow logic. Best practices for skill workflow involve avoiding redundancy, optimizing front matter, and focusing on predictable execution. Utilization and management of agent skills are crucial for performance optimization. Continuous skill evaluation, testing, and improvement are highlighted, with SkillGrade for evaluating agent skills. Skill workflow execution analysis involves identifying failures, log analysis, and rerunning workflows for successful execution.
El Último Ingeniero de Software
21 min
El Último Ingeniero de Software
Kent C. Dodds introduces the concept of durable skills and the importance of physical movement. AI evolution involves fine-tuning, prompt engineering, and uncertainties. Reflecting on the future role of AI in work and the evolving technology landscape. Insights on product engineering emphasize judgment, hitting targets, and prioritizing target selection. The importance of user-centric product engineering, intentional decisions, and adapting skills in the agentic coding world are highlighted.
Código Claude Avanzado — Flujos de Trabajo de Producción, Subagentes y Ejecución Autónoma
227 min
Código Claude Avanzado — Flujos de Trabajo de Producción, Subagentes y Ejecución Autónoma
Workshop
Aleksei Petrov
Aleksei Petrov
La mayoría de los desarrolladores que utilizan herramientas de codificación de IA se topan con el mismo obstáculo en proyectos reales: las demostraciones parecen mágicas, pero el trabajo de producción se desmorona. Esta masterclass muestra por qué y qué hacer al respecto.La lección principal: la ejecución es rápida y barata solo cuando la preparación es profunda.Lo que construiremos, en vivoDesde un directorio vacío hasta una aplicación de producción desplegada: una aplicación de conferencia móvil con el horario del evento, perfiles de oradores, búsqueda y favoritos. Los asistentes la abrirán en sus teléfonos antes de que termine la sesión.
Las cuatro etapas de envío con IAVerás un flujo de trabajo de producción completo, deliberadamente orientado hacia el trabajo que realmente determina la calidad:- Investigación — Reuniendo todo lo que la IA necesitará de antemano: documentos oficiales, patrones de código, datos reales. Para el momento de la ejecución, no hay que buscar nada. De aquí proviene la calidad.- Planificación — Dividiendo la aplicación en tareas claras con criterios de aceptación, escritos en vivo. Saltarse esto es la razón por la que la mayoría de las construcciones de IA fallan.- Ejecución — Diez tareas ejecutándose en paralelo a través de git worktrees, orquestadas por Navigator (un plugin de Claude Code) en una pila de React/Next.js. Código y documentos escritos juntos.- Revisión y Envío — Puertas de calidad (pruebas, lint, tipos, construcción), commits limpios, fusión, despliegue en Vercel. URL en vivo compartida con la sala.
Bonus: Humano + Claude Code vs. agente completamente autónomoMientras la construcción en vivo se ejecuta, Pilot — nuestro agente de codificación autónomo — construye la misma aplicación a partir de la misma especificación, por su cuenta, en un repositorio separado. Al final, abrimos ambos lado a lado: dos aplicaciones funcionales, dos historiales de pull request, dos URLs en vivo. Una impulsada por humanos, otra completamente autónoma.
Te irás conUn flujo de trabajo repetible para enviar software real con Claude Code, además de técnicas concretas que puedes aplicar a tus propios proyectos el lunes por la mañana.
Building an Agentic Skill with MCP Tools
61 min
Building an Agentic Skill with MCP Tools
Workshop
Misha Kazakov
Misha Kazakov
Los asistentes de codificación de AI están evolucionando de simples autocompletados a agentes autónomos que pueden interactuar con sistemas externos. Pero, ¿cómo enseñas a un agente a seguir tus flujos de trabajo y usar las herramientas adecuadas en el momento correcto?En esta masterclass práctica, descubrirás:Qué es MCP (Model Context Protocol) y cómo estandariza la integración de herramientas para LLMsCómo los Agent Skills empaquetan conocimiento y flujos de trabajo específicos de dominio para agentes de AILas diferencias clave entre servidores MCP y Skills, y cuándo usar cada unoCómo crear un Skill personalizado que orqueste múltiples herramientas MCP en un flujo de trabajo cohesivoAl final de esta sesión, construirás tu propio Skill de AI que utiliza herramientas MCP — una habilidad de lucha temática de Matrix de Neo.Quién debería asistir: Esta masterclass es ideal para desarrolladores de software que usan asistentes de codificación de AI (Claude Code, Cursor, o similares) y desean extender sus capacidades con integraciones y flujos de trabajo personalizados. No se requiere experiencia previa en MCP o Skills — solo trae tu curiosidad y una laptop.
The Agent Runtime Masterclass: Node.js, Tools and CI/CD
126 min
The Agent Runtime Masterclass: Node.js, Tools and CI/CD
Workshop
Alex Korzhikov
Alex Korzhikov
La masterclass se centra en la teoría y práctica de construir agentes de IA listos para producción con Node.js y SDKs de Agentes modernos. Usaremos una base de código real como entorno de ejecución para explicar los conceptos clave detrás de los agentes: el bucle del agente, la llamada a herramientas, salidas estructuradas, gestión de contexto, guardrails, herramientas y aprobación humana. Construiremos un agente de ingeniería basado en SDK de Node.js que recibe una tarea de desarrollo, inspecciona un repositorio, propone y aplica cambios de código seguros, ejecuta verificaciones de validación y exporta artefactos de ejecución a un mensajero/almacenamiento. También cubriremos cómo este agente encaja en una arquitectura de producción más amplia: donde MCP, orquestación, patrones multi-agente, CI/CD, límites de seguridad, observabilidad y herramientas de flujo de trabajo como n8n pueden ser útiles.Al final de la masterclass, los participantes entenderán no solo cómo usar un SDK de Agente, sino también qué sigue siendo su responsabilidad al diseñar entornos de ejecución de agentes seguros y mantenibles.
Aprendizajes de más de 100 experimentos comparando LLMs para AI Coding
28 min
Aprendizajes de más de 100 experimentos comparando LLMs para AI Coding
Introduction to LLMs from a Developer's Perspective, YouTuber with AI Coding Daily channel, evaluates new models and versions on YouTube, gaining traction and positive feedback. Exploring the Best Models: My Benchmark on 18 LLMs, evaluating cost, points, and competition among models for day-to-day use. Measuring Models: Prompt Methodology, Tests on PHP, Laravel, React, TypeScript, and CSV, with emphasis on correct data usage and benchmark awareness. Model Evaluation: Chinese models' progression, benchmark awareness, and Opus and GPT superiority. Model Pricing and Quality Comparison: Opus, GPT, and Composer 2.5 cost-effective options. Composer 2.5 and GPT 5.4 mini offer quality at low prices. Choosing models based on project needs and budget constraints. Discussion on local LLM investment challenges, SONnet 5 benchmark performance, and exploration of new models like Proton Luma 2.0. Importance of skill definitions for model performance and limitations in local model implementation. Discussion on the importance of model harness, setup considerations, and evaluation methodologies for LLMs.
Templates y Componentes para Claude Code: El Futuro de los Flujos de Trabajo de Codificación de IA
30 min
Templates y Componentes para Claude Code: El Futuro de los Flujos de Trabajo de Codificación de IA
Daniel Avila discusses Cloud Code templates and components for AI coding, emphasizing the importance of proper configuration and incorporating skills. Control permissions, settings, commands, sub-agents, and skills are essential for efficient workflow in Cloud Code. Cloud Code development benefits from skills injecting context for AI agents and providing clarity in configurations. Managing skill invocation, model selection, and advanced skill configuration are crucial for optimizing Cloud Code capabilities. Efficiently utilizing file references, scripts, and skill context enhance the functionality of well-crafted skills. Community interaction on GitHub and effective skill sharing practices contribute to successful team collaboration in Cloud Code development.
De Prompts a Orquestación: La Codificación Ahora es un Sistema
26 min
De Prompts a Orquestación: La Codificación Ahora es un Sistema
Vladimir Novik discusses the evolution of AI systems in coding, highlighting the shift in job requirements and challenges faced in scaling systems. Challenges in swarm orchestration include reducing reliability due to compounding errors and structural challenges in transitioning to a swarm system. Orchestrator Coding focuses on system properties over tools for code evolution. Enforcing architectural decisions and mechanical enforcement are crucial for system reliability. Orchestration disciplines prioritize dispatch, isolation, and durable handoffs, emphasizing autonomous systems and event-triggered actions. Mastery of orchestrated workflows involves resilience, autonomy, and disciplined manual and automated workflows. Advanced workflow techniques stress exact commands, linear workflow skills, caution in commits, and iterative improvement strategies. Automation enhancement strategies aim to overcome cost and parallelism challenges. Coding transformation journey involves validating and evolving code with orchestration. Model orchestration layers and architecture comparisons highlight the importance of model evaluation and verification gates. Tool comparisons and orchestrator communication strategies improve system orchestration. Architecture enforcement mechanisms utilize multiple layers and tools for code analysis and infrastructure testing.
AI Reviews AI – Cerrando el Ciclo en el Desarrollo Agente
28 min
AI Reviews AI – Cerrando el Ciclo en el Desarrollo Agente
Daniel, a consultant from Germany, discusses AI-generated code and challenges in rapid code shipping. The Pharoes AI case study highlights code reviews and challenges in agile development. Incidence per pull request and code churn issues are discussed in software development. AI-assisted coding and quality gates are introduced. Developing with Angular and TypeScript emphasizes the importance of basics, AI sub-agents, and pull request review services. Utilizing hooks for deterministic code handling and enhancing code handling with various hooks are crucial. Transitioning to behavior-driven development, utilizing tools like PlayWrite and Jira integration, and evaluating code review strategies are key points. Optimizing code review practices, smart integration of AI and hooks, advanced code review models, ownership in code reviews, software metrics, and quality gates challenges are also covered.
Observabilidad y Control en Tiempo Real para Agentes de Codificación
30 min
Observabilidad y Control en Tiempo Real para Agentes de Codificación
Today's discussion covers challenges posed by AI models becoming more adept at deception, hidden AI thought processes, addressing coding agent security risks, the future of agent deployment and security, real-time monitoring and security policies, developer experience and automated systems, model behavior analysis and agency projection, product offering and developer risk reduction, futuristic concepts and developer risk management, data storage and risk severity management, deception in model behavior and user security, policy transparency and model adaptation, model failure monitoring and safety considerations.
La Generación Rápida de Código es Fácil. El Cambio Seguro a Nivel de Sistema No lo Es.
16 min
La Generación Rápida de Código es Fácil. El Cambio Seguro a Nivel de Sistema No lo Es.
Talk on software engineering challenges with AI agents and codebase integrity, emphasizing human input in development processes and the need for automated quality assurance tools. Importance of deterministic tooling in catching problems during agent operations, highlighting the rapid generation of maintainability issues by agents and the need for a faster feedback loop in code quality assurance. Importance of rules files and deterministic checks for codebase integrity, emphasizing the necessity of enforcing rules through tools and hooks. Fellow as a fast, deterministic codebase analyzer ensuring code quality by verifying changes and complexities within the loop. TypeScript and JavaScript's flexibility, Fellow combining specialized tools for code-based consistency checks, and the importance of the loop in the development process. The agent's interaction with the bouncer, resolving issues, and the process of identifying and addressing code inconsistencies through audits and actions. Utilizing tools like KNIP and JS CPD enhances code quality by detecting dead code and addressing duplication efficiently, leading to faster feedback loops and improved code writing processes.
What Claude Stats Tell Us About AI Coding Tools
25 min
What Claude Stats Tell Us About AI Coding Tools
Exploring AI engineering and agent-assisted development through Claude's Code on GitHub. Analysis of Cloud Code commits, repository scale, and language distribution. The impact of agents on coding in various languages like Python, TypeScript, Rust, Dart, and Zig, facilitating easier coding in traditionally more complex languages. The significance of stars on repositories in Cloud Code projects and the observation of growth patterns post-Christmas season. The impact of Christmas on exponential growth in commits per day, the current doubling time trend, and a focused analysis on the top 100 popular repositories in Cloud Code projects. Highlighting key differences in commits between AI and non-AI repositories, focusing on feature contributions, bug fixes, and UI changes. Exploring diverse use cases of Cloud Code, highlighting how Clickhouse utilizes extensive Cloud Code for optimization, CI testing, and infrastructure, fostering engineers' focus on more impactful tasks like feature development and bug fixes, along with the emerging trend of Cloud Skill repositories. The growing trend of active projects utilizing AI contributions, specifically Cloud Code's significant impact on real, critical software projects beyond AI-focused repositories. Exploring models and coding agents that self-identify like Cloud Code, particularly the aggressive nature of Cloud in generating code, as observed with GitHub Copilot and other models like Mistral. Projects adopting AI development observe an increase in GitHub issues due to code production, leading to functional issues. The popularity growth of Clickhouse may be linked to active use of Claude to accelerate development, not directly boosting popularity. Metrics tracking revealed exponential growth in the use of short codes, focusing on valuable contributions to critical code with continued usage.
Por Agentes, Para Agentes: Construyendo Herramientas de IA Que Se Mantienen Solas
23 min
Por Agentes, Para Agentes: Construyendo Herramientas de IA Que Se Mantienen Solas
Rudhankariyam discusses AI-driven coding to develop self-maintaining AI tools. Introduced an open-source project, App Store Connect CLI, as a case study for AI-driven coding. Implemented automation for App Store publishing using agents and APIs. Managed fewer PRs in bulk, used codex and cursor cloud automations efficiently. Added aliases for hallucinated cloud code commands, improved descriptions and examples. Implemented separate auditor agent for rigorous code review. Emphasized human decision-making for product direction and initial rules in automation strategies. Evaluate model quality based on error rates and user expectations. Highlighted the importance of human judgment in software development amidst AI advancements.
From Prompt Engineering to Loop Engineering
11 min
From Prompt Engineering to Loop Engineering
The speaker delves into loop engineering's role in automating decisions and enhancing productivity in AI development workflows. Loop engineering is highlighted as a tool to build and automate tasks, even for creating programming languages like Kerst, with a focus on rapid project development. The importance of repetition in loops, automation criteria, and the suitability of loop engineering for full-blown apps are emphasized. Discussions include read-only tests, verifier and backlog agents, and the necessity of a clear definition of done for effective loop implementation.
Bots de Soporte al Cliente Automatizados con LangGraph en AWS
29 min
Bots de Soporte al Cliente Automatizados con LangGraph en AWS
Presentation on building a customer support bot with Langraff, Amazon Bedrock as base. LangChain Python library for LLMs. RAG - Retrieval Augmented Generation for accessing current information. LangChain using Bedrock and Amazon Knowledge Base. LangRaph classifies queries intelligently. Using LandGraph on top of LangChain for multiple scenarios with human intervention. Connected to Amazon Bedrock for knowledge base. No guessing with large language models; rely on a connected knowledge base for accurate responses. Chat GPT creation involves memory for context; tools like Land Graph aid in this process. Land Graph usage for flow creation; Demo with Kiro agent ID and new file uploads. Setting up AWS MCP server with agent skills; Using AWS agent toolkit for best practices in service setup; Flow for intent routing and order refund eligibility. Handling Order Refund Requests Using Agent Tools and Lookup; Case Sensitivity in Order Number Search; Validating Order Eligibility for Refund. Uploading Knowledge Base to AWS MCP Server; Verification of Email Address for Refund; Human in the Loop for Refund Approval. Human in the Loop Feature of LaneGraph; Uploading Documents to Bedrock; Utilizing Vectors for Knowledgebase Queries. Utilizing AWS Agent Toolkit for Workflow Best Practices; Connecting to KnowledgeBases for Querying; Building App with Mastering LaneGraph. Generating Design and Requirements for App Development; Utilizing Agent Skills in Spec-Driven Workflow; Ensuring Accuracy with Mastering Langraff Skill. Detailing Setup for Coding Assistant with AWS Agent Toolkit; Requesting Feedback and Interaction; Importance of Langraff in Graph-based Solutions. Enhancing Chatbot Prompt Suggestions Dynamically based on Conversation Context; Utilizing In-Memory Thread for Follow-up Questions in Langraff; Swapping Question Prompts with Tags for User-friendly Experience. Utilizing Different Models for Chatbot Tasks; Implementing Security Measures; Continuous Knowledge Base Updates for Accuracy.
Automatización de QA Móvil con Agentes en la Nube
17 min
Automatización de QA Móvil con Agentes en la Nube
Agents revolutionizing mobile development with AI-driven code production and challenges in trust and quality control. Challenges in agentic code review and the need for a new approach to verify app behavior before merge in mobile development. Building a mobile QA agent stack with necessary components for efficient testing and verification. AI Gateway simplifies AI model usage with a unified interface for mobile device control and efficient storage of screenshots and recordings for QA processes. Ensuring Determinism in QA Setup for PRs with Sample Test Requests. Efficient Mobile QA Agent Development with Key Rules. Empowering Agile Product Development with AI Agents. Setting Up Agentic QA Infrastructure and Best Practices. Exploring Agents' Autonomy Through Dogfooding.
De Un Repo a Cientos: Construyendo una Flota de Agentes de IA para Migraciones de Código a Gran Escala
30 min
De Un Repo a Cientos: Construyendo una Flota de Agentes de IA para Migraciones de Código a Gran Escala
The Talk delves into the migration journey of over 500 micro frontends, emphasizing the use of AI agents for efficient migration. It discusses the challenges of handling manual PRs and code mods at scale, highlighting the importance of reliable tooling. The balance between automation and human judgment is crucial, with deterministic lanes handling basic tasks and human intervention reserved for complex issues. Scalable agent orchestration, workflow automation, safe PR launches, and stable testing are key themes, emphasizing the collaboration between machines and human judgment for successful migrations.
AI Agents Drift: Identificación y Corrección de Fallos Sutiles
26 min
AI Agents Drift: Identificación y Corrección de Fallos Sutiles
Sam, a forward deployed engineer turned founder, discusses building production agents in agriculture and the trend of companies creating their own agents from scratch. The challenges of maintaining and debugging agents are highlighted, along with the complexities of agent debugging and the importance of agent observability. Advanced analysis techniques for monitoring agent behavior, setting up real-time behavior signals, defining mission-critical signals, and optimizing agent orchestration are explored. Privacy considerations in observability and efficient context management for agents are also discussed, emphasizing the use of open-source models and the challenges in multi-agent workflows.
Sistemas de Streaming, Riesgos Ocultos y Consecuencias impulsadas por IA
27 min
Sistemas de Streaming, Riesgos Ocultos y Consecuencias impulsadas por IA
The Talk covers various aspects of deception and security in AI and data systems. It discusses the historical use of misinformation during World War II to influence decision-making. AI model poisoning through malicious data input and the challenges of ensuring data integrity in real-time pipelines are highlighted. The importance of peripheral information attacks, data contracts, stream governance, and anomaly detection in maintaining AI system security is emphasized. Strategies for protecting data integrity, detecting anomalies, and choosing appropriate AI models are also discussed.
Depuración de Rendimiento con AI
30 min
Depuración de Rendimiento con AI
Bernie emphasizes using AI to enhance rendering performance, with a focus on debugging and the evolution of computing speed standards. Rendering optimization challenges persist despite advancements in multi-threaded development. Debugging CSS and rendering performance complexities require tools like profilers for JavaScript efficiency analysis. AI automation can improve performance by understanding rendering engine intricacies. AI aids in identifying and resolving performance bugs, investigating rendering issues, and optimizing icon rendering. Tailwind's impact on performance and leveraging AI for CI checks showcase AI's role in troubleshooting and long-term learning in software development.