#AI Engineering

PostHog's Joshua Snyder on Self-Driving Products

Joshua Snyder from PostHog explains how to build a "self-driving product" pipeline that translates product signals into automated pull requests.

AI Agents Get Dumber With More Context, Expert Warns

Nupur Sharma of Qodo explains how too much context can hinder AI agents, leading to the 'lost in the middle' problem, and discusses solutions like context engines and hybrid orchestration.

Dat Ngo on Arize: LLM Observability Platform

Dat Ngo from Arize AI explains their LLM observability, evaluation, and experimentation platform, crucial for building robust GenAI applications.

AI Evals: Broken But Essential, Use Them Anyway

Ara Khan and Cline argue that AI evaluations, though flawed, are crucial. They outline common pitfalls and a process for iterative improvement, emphasizing honesty and nuanced assessment.

Michael Hablich on Agent Interfaces and Chrome DevTools

Michael Hablich from Google discusses building AI agent interfaces, drawing lessons from Chrome DevTools and highlighting key concerns like token efficiency, error recovery, and trust.

AI Decisions: BDD, ADR, PRD, and Harnessing AI

Michal Cichra discusses how BDD, ADR, and PRD frameworks help capture decisions for humans and AI, emphasizing the need for enforcement loops and skills to guide AI agents.

AI Engineer Melbourne 2026 Keynote Livestream

Livestream of AI Engineer Melbourne 2026, Day 1, featuring keynotes and discussions with support from major tech sponsors.

Task Fidelity Scaling Laws: Kobie Crawford on AI Data Quality

Kobie Crawford of Snorkel discusses 'Task Fidelity Scaling Laws,' emphasizing how data quality impacts AI model performance and outlining Snorkel's approach to creating verifiable datasets.

Steven Willmott on Spec-Driven Testing for AI Agents

Steven Willmott of SafeIntelligence discusses spec-driven testing for AI agents, emphasizing the need for clear specifications beyond traditional datasets to ensure robustness and safety.

Nick Nisi on Building Better AI Agents

Nick Nisi of WorkOS discusses how to build better AI agents by focusing on measurement, enforcement, and learning from failures.

Agent vs. Traditional Observability: Braintrust's Phil Hetzel Explains

Phil Hetzel of Braintrust discusses the fundamental differences between traditional observability and the specialized needs of AI agent evaluation.

LinkedIn's Generative Recommender Speed-Up

LinkedIn engineers drastically improved Generative Recommender training efficiency, cutting GPU hours by up to 65% through system-level optimizations.

Hugging Face's Ben Burtenshaw on AI System Engineering

Ben Burtenshaw from Hugging Face discusses how AI coding agents can be used for AI system engineering, kernel optimization, and building multi-agent autoresearch labs.

Does GenAI Belong to Data Scientists?

Phil Hetzel of Braintrust discusses the evolving role of data scientists in Generative AI agent development, arguing for a collaborative, multidisciplinary approach.

Lou Bichard on Agent Swarms and the Missing Primitive

Lou Bichard of Ona discusses the challenges of agent swarms, the missing coordination primitive, and the future of software factories powered by AI agents.

Sally Ann O'Malley on OpenClaw in Containers

Sally Ann O'Malley from Red Hat discusses how OpenClaw agents can be containerized for reproducible, secure, and portable AI development from local machines to Kubernetes.

Marc Klingen on AI Agents & Langfuse

Marc Klingen of Langfuse shares lessons on upskilling AI coding agents, discussing the importance of observability, documentation, and iterative improvement.

AI Sovereignty: What Breaks When You Build AI

Bilge Yücel from deepset GmbH explains the engineering challenges and solutions for building sovereign AI systems, focusing on data, model, infrastructure, and operational control.

IBM's Tejas Kumar on 'AI Harnesses'

IBM's Tejas Kumar explains the concept of AI harnesses, detailing their types (Eval and Agent) and key components like tools, models, context management, and guardrails.

Neo4j's Stephen Chin on Context Graphs for AI

Stephen Chin from Neo4j discusses how context graphs, built on knowledge graph technology, are essential for creating explainable and context-aware AI agents.

Supabase's Pedro Rodrigues on AI Agents and Context

Pedro Rodrigues from Supabase discusses how 'Skills' and the MCP framework improve AI agent context and performance. Learn key principles for building effective product skills.

Agentic AI Fails: Loops, Planning & Unsafe Tool Use

An IBM Advisory AI Engineer breaks down why agentic AI systems fail, focusing on infinite loops, planning errors, and unsafe tool use, and offers mitigation strategies.

AutoScout24 Turbocharges Engineering with AI

AutoScout24 Group dramatically scaled its engineering capabilities by integrating OpenAI's ChatGPT and Codex, slashing development times and boosting innovation.

Embedding OpenClaw Coding Agent in Your Product

Matthias Luebken from Tavon.ai discusses embedding the OpenClaw coding agent, Pi, into products, highlighting its utility for developers and the future of AI in software systems.

Matt Pocock: Engineering Fundamentals Still Crucial in AI

Matt Pocock, author of 'AI Hero', emphasizes that engineering fundamentals are more crucial than ever for building robust AI systems.

Samuel Colvin on Optimizing AI Agents in Production

Samuel Colvin, Pydantic CEO, discusses optimizing AI agents in production using GEPA and Logfire's managed variables at AI Engineer Europe.

Missions: AI Agents That Ship for Days

Luke Alvoeiro from Factory discusses how multi-agent systems, like their 'Missions' platform, can overcome human attention bottlenecks in software engineering.

Build Dumb AI Loops That Ship with Chris Parsons

Chris Parsons of Cherrypick discusses how to build effective AI loops and products by focusing on simplicity and iteration.

AI Engineers: Context is the New Code

Patrick Debois outlines the 'Context Development Lifecycle' for AI agents, emphasizing that 'context is the new code' and detailing the process from generation to observation.

Building Better AI Agents: The Eval Platform Challenge

Phil Hetzel of Braintrust discusses the challenges and best practices for building effective evaluation platforms for AI agents, emphasizing a systems-level approach.

Matt Pocock on LLM Planning: "Don't Bite Off More Than You Can Chew"

Matt Pocock, AI expert, shares insights on effective LLM planning, highlighting the 'smart zone' vs. 'dumb zone' and the power of multi-phase plans with the 'grill-me' skill.

Anthropic, NEC Team on AI Workforce

Anthropic and NEC are joining forces to build Japan's largest AI engineering workforce, deploying Claude AI across 30,000 employees and developing specialized AI products.

AI Needs Fundamentals: Matt Pocock on Code Quality

Matt Pocock emphasizes that AI in coding requires solid software fundamentals, clear design concepts, and a shared language to avoid common pitfalls and produce quality code.

AI Agents: The Next Application Layer?

Vercel CTO Malte Ubl discusses the rise of AI agents as the next application layer, exploring their impact on software development, infrastructure, and the future of AI innovation.

7 Skills for Effective Agent Engineering

IBM AI Engineer Bri Kopecki outlines 7 key skills for building effective AI agents, emphasizing system design, tool integration, and reliability beyond basic prompt engineering.

Simon Podhajsky on "Cognitive Exhaust Fumes"

Simon Podhajsky discusses 'Cognitive Exhaust Fumes,' advocating for read-only AI observers to analyze personal data and reveal cognitive patterns, contrasting this with riskier AI agents.

IBM AI Engineer on AgentOps: The Future of AI?

IBM AI Engineer Bri Kopecki discusses the emerging field of AgentOps, crucial for managing AI agents, highlighting key metrics for observability, evaluation, and optimization.

Allen Park & Swyx on AI, Noodles, and Scaling

Allen Park of Humanloop and Swyx discuss AI development and cooking, sharing insights on building reliable AI and tackling the Dandan Noodles challenge.

IBM Experts Unpack AI Agent Interoperability

IBM's Anna Gutowska and Martin Keen discuss the Agent-to-Agent Protocol (A2A) and Model Context Protocol (MCP) for enabling AI agent collaboration.

Context Engineering: The Graph-Powered Evolution of AI Context

Anthropic's Opus 4.5: Redefining AI Capabilities and Efficiency

The Unseen Architect: How AI Can Engineer a Future of Zero Bugs

Tenex: The 10x Shift in AI Engineering Compensation

The Quest for AI Engineering's Standard Model

The State of AI Engineering: Insights from Amplify's 2025 Report with Barr Yaron

The State of AI Engineering: Insights from Amplify\'s 2025 Report with Barr Yaron

\"Evaluation/evals\" stands as the single most painful aspect of AI Engineering today, a stark revelation from Amplify Partners\' recent 2025 AI Engineering...