AI Engineer

Learned Execution Graphs for Anomaly Detection & Drift in APIs — Ritvik Pandya, JP Morgan Chase

From Systems of Record to Systems of Context — Omri Bruchim & Tomer Ast, monday.com

Shifting software platforms from passive systems of record to active systems of context requires moving beyond simple data retrieval to genuine understanding. The "Monday World Model" addresses the "agent gap"—where AI assistants possess vast data but lack the situational awareness to prioritize tasks effectively—by im...

Your Moat Is Your Data Model — Mike Phipps, Gates Foundation

Active Graph Agent Runtime (BabyAGI 4) — Yohei Nakajima, Untapped Capital

CrabRAG: Why Automated Assistants Need Graph Memory, Not More Tokens — Stephen Chin, Neo4j

Thinner Agents on a Smarter Substrate: The Ontology-based Semantic Layer — Emil Eifrem, Neo4j

Claude for Long-Horizon Tasks — Lance Martin, Anthropic

Asynchronous agents require a shift in architectural design to handle longer task horizons effectively. Decoupling the "brain"—a stateless harness—from the "hands"—sandboxed execution environments—ensures reliability and security for long-running tasks. Implementing independent verifier loops allows models to self-corr...

Full Workshop: Better Auth — Paola Estefania, Better Auth

Every Harness Will Become A Claw — Sam Bhagwat, Mastra

The AI agent landscape is evolving from simple LLM-based loops toward sophisticated "harnesses" and eventually autonomous "claws." This progression involves increasing durability, persistent state, and the ability to execute complex, long-running tasks across cloud and local environments. As these agents gain initiativ...

HTML Is All Agents Need — James Russo, HeyGen

HTML, CSS, and JavaScript serve as the native language for LLMs, offering a superior foundation for generative video creation compared to custom JSON or XML structures. By leveraging these web standards, HyperFrames enables agents to produce complex, high-quality motion graphics, including Three.js and WebGL elements, ...

"The biggest challenge in your stack? Evals, Evals, Evals" - 2026 State of AI Engineering results

AI engineering has evolved into a cross-functional discipline, with senior developers rapidly adapting to new paradigms. Data from over 1,000 respondents reveals that cost is now a primary engineering constraint, influencing how teams architect and scale AI applications. While open-weight models are increasingly used, ...

Your agent architecture has a half-life of 6 months — Dan Farrelly, CTO, Inngest

Agent architectures face a rapid six-month half-life, necessitating a shift from monolithic designs to a decoupled, layered model. The execution layer, acting as the system's brain, must be separated from the context and compute layers to ensure durability, resumability, and observability. By isolating the execution la...

The Desktop Frontier — Ahmad Osman, Osmantic

Through the AI Fog: The Architectural Decision Agentic Security Depends On — Manoj Nair, Snyk

Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town

Agentic Development Security — Ezra Tanzer, Snyk

Your LLM Stack Is a 2008 Database With Better Marketing — Lovina Dmello, NVIDIA

We Gave an Agent Production Code Access and Then Tried to Sleep at Night — Moritz Johner, Form3

Privacy-Preserving Intelligence — Steve Korshakov, Bee (acq. Amazon)

It's 10pm. Do You Know Where Your Agents Are? — Kim Maida, Keycard