Синтетическая эмпатия: как RAG, системные промпты и TTS инженерят привязанность к LLM-агентам
ELIZA в 1966-м заставляла секретарш просить не заглядывать в распечатки диалогов. Шестьдесят лет спустя компаньон-агенты на LLM делают то же самое,…
Architecture
⚑ Сообщить о проблемеПоследние новости Architecture от Tech News
Все темы
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
news
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
How to Build Retrieval Architecture for a Multi-Tenant SaaS Help Center (with Pagination)
Short answer: for retrieval architecture in a multi-tenant SaaS help center, use staged retrieval with explicit collections, bounded queries, and so…
Finding the Bugs I Built an AI Agent to Prevent: Building Deterministic Guardrails with LangGraph & Python
`` A real debugging log: fabrication bugs, deployment gaps, and false test passes found and closed across 6 rounds of adversarial testing. System pr…
Counting OpenAI Tokens per Request in FastAPI — Without Touching My Use Cases
I'm rebuilding evorag , a Python retrieval service: it chunks documents, embeds them with OpenAI's text-embedding-3-small , stores vectors in Postgr…
Why Agents Need a Knowledge Base: The Gaps an LLM Can't Fill by Itself
When a team starts building an agent, the first version is very often only a model, a system prompt and a few tools, and for a demo that is usually…
Travel Planner Retrieval Design with Bounded Access Rules and Source Citations
Short answer: a travel itinerary planner needs a staged retrieval architecture with bounded access rules and source context attached to every answer…
Claims Evidence Retrieval: Immutable Revisions for Insurance Intake Pipelines
Short answer: keep every uploaded claim document immutable, assign a monotonically increasing revision, and let retrieval filter by an explicit as-o…
Recruiting Candidate Search Source Deduplication — A 3-Stage Node.js Retrieval Design
Short answer: use a staged retrieval design with explicit collections, bounded queries, and traceable source context for recruiting candidate search…
Postgres Retrieval Architecture: Multi-Tenant SaaS Help Center Schema Design
Short answer: use a staged retrieval design with explicit collections, bounded queries, and traceable source context, then make index cost a schema…
Building RAG from Scratch: No Frameworks Needed
Building RAG from Scratch: No Frameworks Needed Understand Retrieval-Augmented Generation by building it yourself — pure Python, zero dependencies.…
Ragas vs Truvec for RAG Retrieval Evaluation
I have built and debugged many RAG systems, and the most common failure I saw was not because of bad prompts or weak LLM models. Most failures were…
Insurance Claims Retrieval Architecture with Node.js: Five Access-Rule Checks
Short answer: use a staged retrieval design with explicit collections, bounded queries, and traceable source context; make access rules part of retr…
Candidate Search Architecture: Tenant-Bounded Retrieval and Source Traceability
Recruiting search has an awkward constraint: a highly relevant profile is still a security incident if it came from the wrong customer. Short answer…
Building Better RAG
Most RAG systems that disappoint in production fail at retrieval, not generation: the model answers well from the wrong context, or from none at all…
The Atomic Answer Rule: Engineering Content for RAG Chunking and AI Search
The Atomic Answer Rule states that every H2 section of a document must answer its query as an independent, self-contained micro-document, without re…
One Interface, Seven Formats: How Solon AI Turns Files, Web Pages, and Even Database Schemas into RAG Documents
Every RAG pipeline starts the same way: you have stuff, and the model needs Document s. The interesting question is how far that idea stretches. Sol…
Python Retrieval Architecture for Course Tutors: Chunk Boundaries (and Why)
Short answer: use a staged retrieval design with explicit collections, bounded queries, and source context that survives all the way to the tutor's…
Production RAG Is an Evidence Pipeline, Not a Vector-Database Demo
A production RAG system is not “put documents in a vector database and ask an LLM.” It is an evidence pipeline with two versioned paths: an offline…
LLM-разработка в 2026: навыки, кейсы, требования
Привет, Хабр! Я старший инженер-программист в Финаме и автор курса «LLM-разработчик» в Хекслете. Разговор пойдёт о практике LLM-разработки и о бытов…
How to Build Financial Dashboard Pagination with Traceable Retrieval Contracts
Short answer: use staged retrieval with an explicit collection, bounded queries, and a cursor that carries source context forward. For a financial r…
How to Shape Insurance Claims Retrieval Architecture: 5 Access Rules for Auditable Intake
Short answer: use a staged retrieval design with explicit collections, bounded queries, and source context that survives every handoff. For an insur…
Real-Estate Discovery Retrieval: Hosted vs Self-Managed Privacy Controls (Choose Hosted)
Short answer: use a staged retrieval design with explicit collections, bounded queries, and traceable source context; choose a hosted API when your…
Chunking — Why How You Split Documents Decides Retrieval Quality
The previous article explained how embeddings convert text into vectors so similar meanings land close together in vector space. Before you can embe…
I Tested Amazon S3 Vectors' New Pre-Filtering Against Exact Ground Truth
A filtered vector query that asks for 10 results can come back with 2, and nothing errors. AWS's own launch post shows exactly that on a CLASSIC ind…
Hybrid Search and Reranking: What Each One Actually Buys You
Enterprise RAG Engineering — Part 2 of 3 Where Part 1 Left Off Part 1 argued that most enterprise RAG systems fail at the ingestion layer, before a…
Power Up Your Agents: Execution Hooks and Smart Memory in Agent Kernel
By Yaala Labs Ever wished you could intercept your AI agent's thoughts before they speak? Or give them a photographic memory that lasts exactly as l…
🤯 I Thought I Found an LLM Vulnerability. I Was Wrong. Then I Found a Real One.
————————————————————————————————————————————————————————————————————— A retraction, cross-user RAG chains, and a jailbreak that transfers between mo…
How Combining Fine-Tuned LLMs with RAG Systems Is Transforming Enterprise AI Accuracy
For years, enterprises watched their AI investments deliver only half the promise. Basic large language models sounded confident but frequently hall…
Building an Autonomous AI Memory Engine in n8n: Zero-Maintenance RAG Sync for Notion & Airtable
Building an Autonomous AI Memory Engine in n8n: Zero-Maintenance RAG Sync for Notion & Airtable AI agents are only as reliable as their context…
RAG evaluation: how to know if your retrieval is actually good
You built a RAG app, asked it five questions in the demo, and every answer sounded right. That is not evaluation, that is vibes. The moment a real u…