AI Engineer

Give Your Chat Agent a Voice — Luke Harries, Head of Growth, ElevenLabs

How Transformers Finally Ate Vision – Isaac Robinson, Roboflow

FLUX, Open Research, and the Future of Visual AI — Stephen Batifol, Black Forest Labs

Agentic Search for Context Engineering — Leonie Monigatti, Elastic

Agent Optimization with Pydantic AI: GEPA, Evals, Feedback Loops — Samuel Colvin, Pydantic

Optimizing AI agent performance requires a combination of structured evaluation, genetic algorithms, and dynamic configuration. The GEPA library automates prompt engineering by evolving prompts based on performance against golden datasets, effectively navigating the Pareto frontier to balance quality and cost. Integrat...

Vibe Engineering Effect Apps — Michael Arnaldi, Effectful

Everything You Need To Know About Agent Observability — Danny Gollapalli & Zubin Koticha, Raindrop

Full Walkthrough: Writing & Using Skills — Nick Nisi and Zack Proser

The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory

Software engineering productivity is currently constrained by human attention rather than model intelligence. To overcome this, multi-agent systems like "Missions" utilize a structured architecture—comprising orchestrators, workers, and validators—to automate complex development tasks over extended periods. By implemen...

MCP UI: Extending the frontier — Liad Yosef and Ido Salomon, MCP Apps

The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked

Accelerating AI on Edge — Chintan Parikh and Weiyi Wang, Google DeepMind

Demand-Driven Context: A Methodology for Coherent Knowledge Bases Through Agent Failure

Training an LLM from Scratch, Locally — Angelos Perivolaropoulos, ElevenLabs

Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase

Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick

TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM — Cormac Brick, Google

Edge AI enables privacy-centric, low-latency, and offline machine learning by deploying models directly on consumer hardware. The current landscape shifts between system-level generative AI, which integrates larger models into operating systems, and in-app generative AI, which utilizes tiny language models (TLMs) under...

Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked

Context Is the New Code — Patrick Debois, Tessl

Context has replaced traditional code as the primary driver of AI-assisted development, necessitating a structured "Context Development Lifecycle" (CDLC) analogous to DevOps. This lifecycle involves generating, testing, distributing, and observing context to ensure reliability in AI coding agents. Rather than relying o...

Human-in-the-Loop Automation with n8n — Liam McGarrigle