Research Explainers 10 min read Free

Agents Are Reasoning Loops, Not Smart Prompts

A broad survey frames agentic AI as reasoning through action: planning, tool use, search, memory, feedback, and coordination across time. The framework clarifies why runtime design matters as much as model intelligence.
Research Explainers 10 min read Free

Agent Skills Need a Trust Layer

A survey argues that agent skills are becoming the packaging layer for procedural AI work, making governance, permissions, and verification unavoidable. It maps the controls needed before reusable instructions can be trusted across teams and organizations.
Research Explainers 9 min read Free

The Agent Is the Whole System

A survey argues that agent quality is a system property spanning models, memory, tools, planners, verifiers, permissions, traces, and evaluation. It offers a practical architecture for diagnosing failures without blaming the base model by default.
Research Explainers 8 min read Free

Multi-Agent Systems Fail Like Organizations

A NeurIPS dataset paper finds that multi-agent LLM systems fail through role confusion, broken handoffs, and weak verification, not only weak models. Its taxonomy turns coordination breakdowns into observable failure modes teams can test and repair.
Research Explainers 9 min read Free

Skill Bloat Is the New Context Tax

A paper argues that agent skills need a build-time optimization pass because many reusable instruction files waste context and make agents worse. Its proposed compiler trims redundancy while preserving the instructions that actually improve task performance.
Profile 7 min read Free

Lessons from Adrian Cockcroft

Lessons from Adrian Cockcroft Adrian Cockcroft shaped modern cloud infrastructure at Sun Microsystems, Netflix, and AWS by proving microservices and chaos...
Profile 7 min read Free

Lessons from Christina Wodtke

Lessons from Christina Wodtke Christina Wodtke is a Stanford professor and former tech executive who helped rescue Objectives and Key Results (OKRs) from...
Profile 7 min read Free

Lessons from Brendan Gregg

Lessons from Brendan Gregg Brendan Gregg is the performance engineer behind Flame Graphs and the USE method. At Joyent, Netflix, and Intel, he built...

Choose your reading rhythm.

Start with a weekly briefing, add daily notes, or hear only when a durable essay or library update is ready.
You've successfully subscribed to Antoine Buteau
Great! Next, complete checkout to get full access to all premium content.
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.
Press ESC to close.