Categories

Most of my articles are about the Astrophotos that I take during my free time. I also write about software architecture and modern application development
Agent Engineering
39
Architecture
39
Artificial Intelligence
47
Astrophotography
16
Building Composable Systems
8
Claude Code
5
Composable UI
39
Galaxy
2
Narrowband
13
Nebula
11
Next.js
1
Node.js
1
Orchestration
9
React
4
Supernova Remnant
3
Tailwind CSS
3
The Composable Frontend Architecture
13

Stay Tuned

Want to become a Next.js pro?
The best articles, links and news related to web development delivered once a week to your inbox.

Latest Articles

A few handcrafted articles about my thoughts and experiments.

A mechanical hand uses one small brass token to unlock a narrow door while larger vaults remain sealed
Artificial Intelligenceagent-securityAgent EngineeringArchitecture
Capability Tokens for AI Agents
A practical model for granting AI agents narrow, temporary, auditable authority to use tools, touch data, and perform consequential actions.
Published on
A mechanical governor meters crowded cargo capsules into a single tunnel inside a steam-filled switching hall
Artificial IntelligenceAgent EngineeringOrchestrationreliability
Agent Queues Need Backpressure
How AI work queues should control intake, priority, concurrency, retries, and human review so autonomous systems do not turn demand into uncontrolled motion.
Published on
An operator uses a weathered runbook built into an industrial control desk while autonomous machinery works outside in a storm
Artificial IntelligenceAgent EngineeringArchitecturereliability
AI Runbooks Are Product Interfaces
Why agent systems need operational runbooks that encode intent, evidence, authority, escalation, and recovery instead of leaving procedure trapped in prompts.
Published on
A compact clockwork greenhouse tends one thriving plant while an enormous unfinished autonomous factory stands idle in the distance
Artificial IntelligenceAgent EngineeringArchitectureOrchestration
Build the Smallest Autonomous Loop That Can Work
A practical way to scope AI autonomy around one observable goal, one bounded action surface, and one trustworthy feedback loop before expanding further.
Published on
A calm night operations team rehearses containment around a physical system model while the real autonomous machine remains visible through an observation window
Artificial Intelligenceagent-securityobservabilityreliability
AI Incident Response Starts Before the Incident
How to prepare containment, evidence, ownership, communication, and recovery for AI failures before a fast-moving agent system makes them necessary.
Published on
A bridge section built by one industrial rig is subjected to independent alignment and load tests by a separate inspection system
Artificial IntelligenceevaluationAgent Engineeringreliability
Verification Must Be Independent
Why agents should not be the sole judges of their own work, and how separate evidence, evaluators, and invariants create trustworthy completion.
Published on
A powerful experimental machine operates inside a transparent containment chamber with only a few permitted tool channels crossing concentric safety walls
Artificial Intelligenceagent-securityAgent EngineeringArchitecture
Sandboxes Are Capability Containers
Why effective AI sandboxing is about constraining authority, data, tools, networks, and persistence—not merely isolating a process.
Published on
A curator admits a small ordered set of records from a chaotic archive conveyor into a bright, quiet reading chamber
Artificial Intelligencecontext-engineeringretrievalArchitecture
Retrieval Needs Admission Control
Why reliable AI context depends on source authority, freshness, conflict handling, and deliberate exclusion—not merely finding semantically similar documents.
Published on
Turbulent blue material passes through a precision industrial mold and emerges as exact illuminated forms ready for a downstream machine
Artificial IntelligenceAgent EngineeringArchitecturereliability
Structured Outputs Are Protocol Boundaries
Why schemas, validation, repair, and semantic checks are the boundary that turns probabilistic model output into dependable system behavior.
Published on
123456789101112
Page 2 of 12
HomeAboutArticlesProjectsChat