Start here
Agent Architecture
Learn Agent Architecture as a connected topic across articles, concepts, simulations, and interview reasoning.
Agent ArchitectureMental ModelTradeoffsFailure ModesInterview ReasoningLLM Skills vs Tools
Begin with
LLM Skills vs Tools gives you the cleanest entry point before branching into constraints, failures, and related systems.
12
Articles
10
Concepts
Related systems
Follow the nearby ideas
Use the map as a quiet orientation layer, then move back into the articles for depth.
Guidance
Agent Architecture
Continues from what you have already explored.
System behavior
HyperLogLog Cardinality Estimation
Hash values route into registers, leading-zero runs update maxima, and the harmonic mean estimates unique cardinality with bounded error.
Step 1 / 3Normal flow
Read in sequence
1LLM Skills vs Tools: The Missing Layer in Agent DesignTLDR: A tool is a single callable capability (search, SQL, calculator). A skill is a reusable mini-workflow that coordinates multiple tool calls with policy, guardrails, retries, and output structure.16 min2LLM Skill Registries, Routing Policies, and Evaluation for Production AgentsTLDR: If tools are primitives and skills are reusable routines, then the skill registry + router + evaluator is your production control plane. This layer decides which skill runs, under what constrain14 min3Data Lineage Explained: Tracking Data Flow Across Your OrganizationTLDR: 📊 Data lineage is the complete genealogy of your data — where it comes from, how it's transformed, and where it ends up. It's critical for debugging pipelines, proving compliance, and understan12 min4Data Governance Essentials: Framework and Best PracticesTLDR: 📋 Data governance is the framework that answers "who owns this data, who can access it, and what quality standards must it meet?" Without governance, data pipelines become chaotic. Implement it9 min5OWASP Credential Stuffing Key Terms Explained with Practical ExamplesTLDR: Credential-stuffing defense works only when you treat login as a layered, risk-adaptive system: detect attack shape, add step-up authentication, combine bot and fingerprint signals, prevent user15 min6Java 21 to 25: Virtual Threads, Pattern Matching, and Structured ConcurrencyTLDR: Java 21 LTS makes virtual threads a production-ready replacement for bounded thread pools — your newFixedThreadPool(200) can become newVirtualThreadPerTaskExecutor() and handle 10× the concurren22 min7Java 14 to 17: Records, Sealed Classes, Text Blocks, and Pattern MatchingTLDR: Java 14–17 ran a deliberate four-release preview-to-stable conveyor belt. Records replaced 50-line POJOs with one line. Text blocks ended escape-sequence chaos in multi-line strings. Sealed clas25 min8Java 8 to 11: Lambdas, Streams, Modules, and the End of BoilerplateTLDR: Java 8 introduced the most impactful set of language features in Java's history — lambdas eliminated anonymous inner classes, streams replaced imperative loops, and Optional made null handling e16 min9Spark Structured Streaming: Micro-Batch vs Continuous Processing📖 The 15-Minute Gap: How a Fraud Team Discovered They Needed Real-Time Streaming
A fintech team runs payment fraud detection with a well-tuned Spark batch job. Every 15 minutes it reads a day's worth27 min10Spark Adaptive Query Execution: Dynamic Coalescing, Pruning, and Skew HandlingTLDR: Before AQE, Spark compiled your entire query into a static physical plan using size estimates that were frequently wrong — and a wrong estimate at planning time meant a skewed join, 800 small ta39 min11Pythonic Code: Idioms Every Developer Should KnowTLDR: Writing for i in range(len(arr)): works, but Python veterans will flag it in your first code review. Idiomatic Python uses enumerate, zip, comprehensions, context managers, unpacking, the walrus27 min12Python OOP: Classes, Dataclasses, and Dunder Methods📖 Why Every Java Developer Writes Un-Pythonic Classes on Day One
Imagine a developer — let's call him Daniel — who has written Java for six years. He sits down to write his first Python class and pro22 min
Related threads