Search
Glossary2
Open the full glossary- RAG (Retrieval-Augmented Generation)Look material up first, hand the retrieved passages to the model along with the question, and have it answer from them.
- Regex (regular expression)A notation for describing what a piece of text looks like, used to find or validate matching fragments inside larger text.
Found 17 articles
DeepSeek's Open-Source Super-Agent Prototype: A Source-Level Breakdown
A source-level breakdown of DeepSeek's open-source dsh-superagent-prototype: the three-plugin architecture, the event-driven core, 11 injected host services — and which designs are worth borrowing, and which are not.
Build Your First AI Agent in Seven Steps: from environment to a minimal production pass
Adapted from the MIT-licensed awesome-agentic-ai-zh integrated tutorial: one 'paper assistant' project wires up environment setup, your first LLM call, the four-part prompt, tool use, the agent loop with reflection, RAG memory, evals with observability, and the smallest interface. Every step ships minimal runnable code and safety rails; the local Ollama path costs 0 in API fees.
Internal-Document Knowledge-Base Q&A System
Can't find company policies or process docs, and keep asking colleagues instead? This article shows how to build an intelligent Q&A system with AI + RAG, so employees ask questions right in their instant-messaging tool and get accurate answers with the source document attached. The focus is on designing for retrieval accuracy and a miss-tracking mechanism.
Performance Review Data Aggregation and Visualization: From Fragmented Feedback to Structured Insights
The most expensive thing about performance reviews is not the time — it is the bias. This article uses Lattice, 15Five, and AI together to build automatic aggregation of multi-source feedback, theme extraction, and trend visualization, so managers decide based on data instead of impressions.
DCF Assumptions and Sensitivity Analysis: Make the Valuation Challengeable
The value of a DCF is not in computing one number but in whether the assumptions behind it can be examined, challenged, and recomputed. Using a hypothetical model for teaching, this article demonstrates the assumptions register, the three-stage cash-flow structure, the composition facets and trade-offs of WACC, the risks of the two terminal-value methods, the design of single-factor and two-factor sensitivity matrices, and how to present a valuation as a defensible range rather than a fragile single point.
Building Your Own Investment-Research System: The Complete Design from Skill Library to Verification Gates
Gathers the methods of all the previous articles into one complete blueprint: the five-layer architecture of data, skills, orchestration, verification, and output; the input/output contract design of the skill library; five gates from format validation to low-confidence abstention; why coverage and accuracy must be counted separately; the seven-step method for building an evaluation set; post-launch operations mechanisms; and the four-stage evolution path from a solo tool to a team system.
What Is Vibe Coding: Fast, but Fragile
Vibe coding turns plain-language prompts into a working prototype in minutes. So why does it collapse in production? Three failure modes and five guardrails, so you can move fast without breaking things.
A Reality Check on Decision Models: Why They Seem Miraculous Online but We Measured Only 54%: A Full Comparison of JEV / LAYA / KEV / CLM-8B and a Deployment Formula
In September 2026, System One decision models formed a new category within two weeks: the closed-source JEV API, then LAYA, KEV, and CLM-8B open-sourced one after another. This article does more than summarize the differences among the four; it uses six everyday scenarios to explain how they are actually used, and places the official marketing side by side with our same-question measurements: on the same set of questions, full-coverage accuracy was only 54%, but with confidence gating it reached 91.7%.
Complete LangChain Tutorial 2026: Building Enterprise-Grade LLM Applications from Scratch
The most detailed LangChain 2026 tutorial: covering LCEL, RAG, Agent, LangGraph, LangSmith. From installation to production deployment, with complete code examples.
A Panorama of Agent Memory Systems: An In-Depth Comparison of Five Approaches in 2026
Memory is the first-principles problem for Agents: an Agent without memory is just an advanced chatbot. This article compares five approaches (agentmemory / PlugMem / Infini-Memory / verifiable-memory / Qdrant+MemoryHub) and provides a scenario selection matrix.
Headroom: An LLM Context Compression Engine, Saving 60-95% of Tokens
GitHub Trending #2 · 38K ⭐ · Compresses everything an AI Agent reads (tool output/logs/documents/RAG), keeping the answer unchanged while reducing tokens by 60-95%. Supports four deployment modes: Library/Proxy/MCP/Agent Wrap
Vector Memory Deep Dive: A Production-Grade Memory System That Ensures AI Agents Never Lose Memory Again
State amnesia is the #1 killer in production Agent environments. We built a four-layer vector memory system based on Qdrant + BGE-m3, with 9 retrieval modes, validated with 6,675 memories in real-world use, raising Chinese search accuracy from 0% to >78%. One line curl | bash, 100% local deployment, and data sovereignty stays in your hands.
Triple Strike: OMP Error #15, PEP 668, and Python Dependency Hell
The MemoryHub daemon crashed and restarted repeatedly over three hours: ModuleNotFoundError → OMP Error #15 → silent crash loop. An in-depth analysis of the faiss + torch dual libomp conflict, the Homebrew PEP 668 block, and the structural fragility of the Python scientific computing ecosystem. Includes a complete prevention plan.
MemoryHub v2.0 System Architecture In-Depth Analysis: From Capture Daemon to MCP Real-Time Memory Capture
A complete breakdown of MemoryHub v2.0's dual-mode capture engine, Qdrant vector storage, MCP four-platform integration, Dashboard real-time monitoring, three-layer deduplication, and ten-year lifecycle design.
Complete Comparison of Top 10 Vector and Full-Text Databases: MemoryHub Backend Storage Selection Guide
An in-depth review of ten databases, including Qdrant, Chroma, LanceDB, SQLite-vec, FAISS, Redis, PostgreSQL (pgvector), Elasticsearch, MongoDB Atlas, and Neo4j, in AI memory system scenarios, covering performance, deployment difficulty, resource consumption, and use cases.
RAG In-Depth Principles and Practice: A Complete Guide from Chunking to Rerank
The complete tech stack for Retrieval-Augmented Generation (RAG): Embedding selection, Chunking strategies, vector database comparison, Rerank optimization, with practical code examples.
LangChain vs LlamaIndex: A Selection Guide and Hands-On Primer
A deep comparison of two major LLM application frameworks: LangChain's generality vs LlamaIndex's data indexing expertise, with starter code and scenario recommendations.