» Tag
system-design
32 postsThe Future of Software Engineering: From Coding to Systems Management
As AI makes code generation cheap, real engineering value shifts to architectural judgment, systemic clarity and production accountability. Here's what changes.
Why AI Orchestration Beats Bigger Context Windows
Massive context windows didn't fix AI. With models scoring under 1% on ARC-AGI-3, winning teams now engineer the system around the model, not just the model.
Environments Are Not Features: A Real Sandbox Architecture
One frontend, many environments: how proxy-based routing, identity copying and hard reloads build a real sandbox architecture that holds up.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comHow to Build Incident AI That Engineers Actually Trust
An incident-detection AI lost engineer trust by reasoning before context. Adding deploy tracking and a context graph raised hypothesis accuracy from 35% to 70%.
Deployment Status Is Actually a Distributed Systems Problem
Drawing on Guara Cloud's build experience, this piece explains why 'pending' labels fail and how deployment status must be modeled as evidence-based distributed state.
LLM agents are breaking 20-year-old web architecture
Stateful LLM agents are exposing cracks in the stateless-server-plus-database web architecture. The missing piece: a routing primitive that can address running processes directly.
Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems
Mind viruses are self-propagating ideas in multi-agent systems. This study explores their risks and implications for AI agent design.
How to Make an AI Agent's History Truly Unforgeable
An AI agent's unforgeable-history claim failed audit: dual writers, race conditions, corrupted records. Fix: single writer, signed anchor, fail-closed design.
Edge Gateway Architecture: Diskless Design and the Rust DashMap Trap
A deep dive into Cloudflare-style edge gateway architecture: data/control plane separation, in-memory TLS, WASM sandboxing, and the Rust DashMap deadlock pitfall.
When Fine-Tuning Stalls: The Architecture That Took Recall to 92%
A healthcare claims AI stuck at 45% recall on CPT/ICD coding reached 92% by adding a deterministic NCCI validation layer instead of more fine-tuning.