Loading
Integrating OAuth 2.0 into Enterprise Multi-Agent RAG Architectures
Learn how to secure a FastAPI multi-agent RAG application with OAuth 2.0 and OIDC, using token roles to control document retrieval and preserve user-specific sessions.
Learn it from developers who built it.
Tutorials, how-tos and deep dives on AI, .NET, C#, cloud and developer tools, written by the community.
Learn how to secure a FastAPI multi-agent RAG application with OAuth 2.0 and OIDC, using token roles to control document retrieval and preserve user-specific sessions.
Build a multi-agent LangGraph framework to evaluate RAG systems using context precision, recall, faithfulness, answer relevancy, and correctness metrics.
Build a multi-agent LangGraph system that combines RAGAS diagnostic metrics and G-Eval LLM-as-a-judge scoring to evaluate RAG quality in production.
Learn how to build a LangGraph multi-agent RAG system that profiles long documents and selects retrieval, summarization, or cross-section strategies based on each query.
Build a LangGraph RAG workflow that reduces LLM hallucinations through grounded retrieval, self-consistency checks, NLI fact-checking, citation verification, and corrective regeneration.
Learn how to build enterprise-ready AI agents in .NET with Microsoft Agent Framework, including tools, state, MCP integration, workflows, safety controls, and observability.
Learn how OpenAI Codex cloud environments support remote, multi-device coding workflows, reproducible setups, dependency management, and test validation.
Build a LangGraph multi-agent advisor that evaluates data freshness, citations, latency, budget, and risk to recommend RAG, fine-tuning, or a hybrid LLM architecture.
Learn how to isolate AI agent sessions in Microsoft Foundry using session IDs, tenant boundaries, authorization, cache isolation, RAG filters, and secure tools.
Learn how to control AI agent network access in Microsoft Foundry using identity, egress controls, private networking, tool authorization, and least privilege.
Build a LangGraph-based hybrid RAG search system that combines BM25 and vector retrieval, adaptive result fusion, and cross-encoder reranking for better retrieval quality.
OpenAI Dots are persistent AI agents that continue work between chats. Learn about their capabilities, availability, permissions, safety controls, and enterprise governance.
Build a LangGraph-based hybrid search system that combines BM25 sparse retrieval and dense vector search, then uses Reciprocal Rank Fusion and reranking to improve results.
Build a LangGraph multi-agent system that evaluates embedding models by retrieval quality, domain fit, cost, latency, language support, and deployment constraints.
Build a LangGraph multi-agent advisor that evaluates document characteristics and recommends RAG chunking strategies, including semantic, structure-aware, parent-child, and late chunking.
Build a multi-agent LangGraph workflow that audits RAG retrieval, classifies failure modes, identifies root causes, and recommends targeted fixes using persistent failure memory.
Build a multi-agent LangGraph system that grounds LLM answers in retrieved sources, verifies citations, and scores confidence for transparent, traceable AI responses.
Build a LangGraph multi-agent RAG system that analyzes training and validation curves to diagnose underfitting, overfitting, and double descent, then recommends model improvements.
Google Cloud API Gateway can now expose your existing REST APIs directly as MCP tools for AI agents - no separate server, no duplicated security logic. Here's a simple, no-jargon walkthrough of how it works and why it matters.
Learn where security belongs in an AI agent stack, from models and harnesses to runtime controls, credentials, tool access, audit logs, and recovery.
Build an enterprise RAG workflow with LangGraph that monitors latency, quality, and safety signals, then automatically rolls back model and prompt versions when thresholds are breached.
Build a LangGraph-based multi-agent RAG workflow that retrieves evidence, verifies generated claims, detects hallucinations, and rewrites unsupported answers.
Graceful degradation transforms fragile AI systems into resilient enterprise solutions. By implementing circuit breakers, fallback strategies, caching, and clear user communication, your multi-agent RAG system maintains value delivery even during service disruptions. The key is designing multiple degradation levels that progressively simplify functionality while preserving core utility. Monitor your circuit breakers, test failure scenarios regularly, and always prioritize user experience over perfect accuracy when systems are under stress. This approach ensures your manufacturing AI assistant remains a reliable tool, not a single point of failure.
Optimizing Graph RAG for fintech requires a shift from simple retrieval to intelligent, parallelized reasoning. By leveraging the structural power of Neo4j, the orchestration capabilities of LangGraph, and the speed of async FastAPI, we can build systems that provide deep, accurate insights in real-time. As financial markets become increasingly complex, the ability to quickly traverse and understand these connections will be a definitive competitive advantage.
Understand the difference between APIs and MCP, including how MCP enables AI agents to discover and use tools while APIs provide structured application-to-application communication.
Unifying transactional and NLP-derived signals within a feature store transforms raw data into actionable intelligence. By integrating this store with a Multi-Agent LangGraph RAG system, enterprises can move beyond static rules to dynamic, context-aware decision-making. This POC illustrates how hybrid features enable more nuanced outcomes, such as empathetic support routing.
Building exactly-once or effectively-once semantics in multi-agent LangGraph RAG systems requires a combination of idempotency patterns, distributed state management, and transactional databases. By leveraging unique identifiers, conditional writes, and checkpointing, enterprises can ensure data consistency even in the face of failures.
Learn how AI coding agents can work without sending source code to the cloud using local models, private repositories, network controls, sandboxing, and secure C# workflows.
Learn how to build interactive AI agents in C# with conversation state, tool calling, follow-up questions, human approval, and multi-step workflows.
Learn when running AI coding agents locally makes sense, including hardware needs, code privacy, offline development, security, model limits, and C# workflows.
Everything on AI Agents, not only its articles: the AI Agents page →
Mahesh Chand9 videos · 24 news posts+5.5Kpoints2
Aarav Patel21 articles · 1 reaction received+2.1Kpoints3
Ananya Desai21 articles · 1 reaction received+2.1Kpoints4
Riya Patel20 articles · 1 reaction received+2Kpoints5
Bhavya Singh20 articles+2KpointsFull leaderboard →
DevSocialUpcoming · 3rd editionAI Agents ConferenceNov 23–27, 2026Live onlineMembers only17days leftRegisterMembers onlyWrite an article and earn +1,000 SHARP when it is approved.
Write an article
