Kicks off Code w/ Claude 2026 with hands‑on workshops, live demos of new capabilities, and conversations with the teams behind Claude. Sets the day's three‑track agenda: Research, Claude Platform, Claude Code.
Kicks off Code w/ Claude 2026 with hands‑on workshops, live demos of new capabilities, and conversations with the teams behind Claude. Sets the day's three‑track agenda: Research, Claude Platform, Claude Code.
~20‑minute overview of recent Claude Code updates: what shipped, why, and how to get started. Positioned as the entry point before the day's deeper Claude Code workshops.
At Spotify the bottleneck has moved from writing code to orchestrating it — 96% of engineers use AI and PR frequency is up 60%. Covers Honk, a background coding agent built on the Agent SDK, integrated with the Fleetshift migration platform and the Backstage software catalog.
Argues that "the same standardization that makes teams effective makes agents effective too," and explores structured guardrails as accelerators rather than limits.
Claude's Managed Agents platform now handles infrastructure, state management, and permissioning automatically — the layer that used to require significant development effort. Covers the fundamentals of building and deploying a production‑grade agent at scale, plus industry perspectives on the future of agentic infrastructure.
Software built on Lovable currently serves 600M+ monthly sessions. Walks through three systems they built:
Theme: the distinction between rapidly prototyping with AI versus maintaining production systems at consumer scale.
Three European companies, three distinct integrations:
Discusses implementations, challenges, and strategies for keeping pace as Claude evolves.
"Frontier models are getting more capable, fast. Where the curve is going, and what it means for developers building on Claude."
Three architectural patterns shaped Legora's legal‑AI agent: "what they could reuse from coding agents, what they had to translate, and what they had to invent." Shows how document editing, linting, and bulk review were rebuilt for legal work, with a live demo of the agent.
How to "cut cost, manage context, boost intelligence." Live demos covering:
Design considerations for memory architectures in Claude Managed Agents, and how dreaming verifies and enriches memory between sessions — so agents retain and improve learned information across interactions instead of starting fresh each time.
Inside Claude Design, a tool that converts natural‑language descriptions into production‑ready, on‑brand outputs. "Learn how a small team built a design tool that ships in your brand, from prompt to production."
Base44's path from one engineer to hypergrowth (including acquisition by Wix). How Claude Code helped with three challenges: "ramping new engineers, compressing the experiment‑and‑validate cycle, and keeping the lights on as the surface area grew."
Plus an elegant simplicity principle that kept the architecture deliberately uncomplicated as the team scaled.
"Adaptive thinking and effort controls give developers a new decision: how much should Claude reason for a given task?" Covers thinking budgets, effort levels, and the cost / latency / quality tradeoffs involved.
What changes when agentic coding becomes standard practice across teams, not just an individual tool. "The tool isn't the hard part — your processes are." Anthropic's own operational shifts: bottlenecks in code review, ownership, recruiting, and process innovations developed to keep shipping velocity high while scaling AI‑native development.
Man Group has trading signals in production that were "researched, backtested, and proposed by AI." Made possible in a regulated investment environment by two mechanisms: a governed skills framework and a core data layer that let Claude learn decades of quantitative trading methodology.
Scaled across ~750 developers and quants with 100+ skills. Focuses on the governance model that earned compliance approval for AI on critical workflows.
A live build from zero to deployed in thirty minutes — a feedback app spanning five roles and the full software lifecycle, using Claude and Google Cloud alongside subagents, MCP servers, and custom skills. Attendees test the finished app at the end of the session.
"How to apply core prompting principles to agentic systems that plan, act, and adapt."
"Hands‑on techniques for testing and comparing models against your use case, so you can make a confident call each time a new release ships."
"The mechanics that separate basic Claude Code use from real leverage: CLAUDE.md done well, wiring tools in with MCP, packaging team knowledge as skills, and using auto mode safely."
Routines turn Claude Code into a proactive teammate that reads your repo and opens a PR before you've opened your laptop. Covers triggers, context, and steering decisions, and ends "one /schedule command away from your first routine."
45‑minute hands‑on. "Stand up Claude Code in Amazon Bedrock, teach it your team's conventions with CLAUDE.md, and turn your everyday workflows into reusable agent skills." Leave with a working, team‑tuned agentic dev environment on Bedrock.
"A hands‑on build session for Claude Managed Agents. You'll deploy a production‑ready agent from scratch, then debug and monitor it live in the developer console."
"Provision Claude in Microsoft Foundry, connect it to a real MCP server with Claude Code, and build a working agent. You'll leave with running code and a cupcake to prove it."
End‑to‑end routine construction: trigger, context, steering. Practical implementation via the /schedule command, aimed at developers ready to deploy proactive agent workflows with Claude Code.