Tagged articles

Agent Architecture

246 articles · Page 1 of 3

Oct 1, 2026 · Artificial Intelligence

Pi vs DeepSeek Harness: Agent Loop Design for Continuation, Closure & Recovery

This article compares Pi and DeepSeek Harness agent loop architectures across four control points—input attribution, tool scheduling, closure permissions, and persistent evidence—revealing how each handles mid-task user constraints, parallel tool execution, token truncation, and crash recovery through distinct runtime contracts and durable extensions.

Agent ArchitectureAgent LoopCrash Recovery

0 likes · 20 min read

Pi vs DeepSeek Harness: Agent Loop Design for Continuation, Closure & Recovery

PMTalk Product Manager Community

Oct 1, 2026 · Product Management

From B-End PM to AI PM: Complete Transition Roadmap

The author shares a verified transition path from traditional B-end product management to AI product management, covering technical understanding of API interactions, core frameworks like LangGraph and Dify, RAG product design, tool design, open-source product teardowns, and a five-step hands-on learning roadmap culminating in an MVP project.

AI Product ManagerAgent ArchitectureCareer Transition

0 likes · 7 min read

From B-End PM to AI PM: Complete Transition Roadmap

SpringMeng

Sep 30, 2026 · Artificial Intelligence

Jev: The Non-Generative AI Model Beating LLMs at Classification 200x Faster

Jev is a non-generative 'System One' AI model from TypeSafe that outputs structured decisions with calibrated probabilities instead of text, achieving 20-200x speedups and 40-400x cost reductions over LLMs for classification, routing, and scoring tasks, with community Java SDKs enabling type-safe integration.

Agent ArchitectureJava SDKJev

0 likes · 23 min read

Jev: The Non-Generative AI Model Beating LLMs at Classification 200x Faster

DataFunTalk

Sep 28, 2026 · Artificial Intelligence

Why Agents Are Splitting Off a Decision Layer: Jev and the System One Model

TypeSafe's Jev introduces a specialized 'System One' model for high-frequency structured decisions like routing and tool selection, enabling agents to offload bounded judgments from expensive generative LLMs into a fast, calibrated decision layer that sits between rule-based logic and complex reasoning.

Agent ArchitectureContext CompactionDecision Layer

0 likes · 23 min read

Why Agents Are Splitting Off a Decision Layer: Jev and the System One Model

Ops Development & AI Practice

Sep 27, 2026 · Artificial Intelligence

OpenAI API Evolution: Completions to Responses — Why Open Source Still Uses Chat Completions

This article traces OpenAI's API evolution across six generations from Completions to Responses API, explains why the open-source ecosystem remains anchored to Chat Completions despite official advances, compares architectural trade-offs between stateless and stateful paradigms, and provides a practical selection guide for engineers building heterogeneous model gateways or agent systems.

API EvolutionAgent ArchitectureChat Completions

0 likes · 28 min read

OpenAI API Evolution: Completions to Responses — Why Open Source Still Uses Chat Completions

IT Services Circle

Sep 26, 2026 · Artificial Intelligence

Jev: The Non-Generative AI Model That's 200x Faster for Decisions

Jev is a non-generative 'System One' AI model from TypeSafe that outputs structured decisions with calibrated probabilities in 70-500ms, 20-200x faster and 40-400x cheaper than LLMs, enabling high-frequency classification, routing, and agent supervision in Java ecosystems via community SDKs.

Agent ArchitectureDecision ModelsJava SDK

0 likes · 24 min read

Jev: The Non-Generative AI Model That's 200x Faster for Decisions

DataFunTalk

Sep 26, 2026 · Artificial Intelligence

OpenAI Demotes RAG: Context Graphs Become Primary for Enterprise Agents

OpenAI's V7 case study reveals a shift where enterprise agents query a pre-built Context Graph first, falling back to RAG only when the graph lacks information, addressing retrieval bottlenecks shown by the HERB benchmark and enabling reliable multi-step agent workflows.

Agent ArchitectureContext GraphEnterprise AI

0 likes · 15 min read

OpenAI Demotes RAG: Context Graphs Become Primary for Enterprise Agents

DataFunTalk

Sep 25, 2026 · Artificial Intelligence

Amap's Text-to-SQL Accuracy Jump: 50% to 95% via Skill Architecture

Amap's intelligent query product raised accuracy from 50% to 95% by replacing RAG with a Skill-based Agent architecture that uses on-demand knowledge retrieval and self-reflection, backed by semantic layer modeling and a three-part evaluation flywheel.

Agent ArchitectureAmapBI

0 likes · 6 min read

Amap's Text-to-SQL Accuracy Jump: 50% to 95% via Skill Architecture

Tech Architecture Stories

Sep 25, 2026 · Artificial Intelligence

Why LLMs Shouldn't Think Everything: Jev, Codex, and the Heterogeneous Agent Revolution

The article argues that AI agents waste compute by using large language models for low-entropy decisions, and introduces Jev, a lightweight decision model that handles tool routing, code search, and log triage in milliseconds, enabling a System 1/System 2 architecture where Jev filters noise before Codex performs deep reasoning, a pattern mirrored by Glean's enterprise search stack.

AI AgentsAgent ArchitectureCodex

0 likes · 16 min read

Why LLMs Shouldn't Think Everything: Jev, Codex, and the Heterogeneous Agent Revolution

Machine Learning Algorithms & Natural Language Processing

Sep 24, 2026 · Artificial Intelligence

Frozen Model Weights, Evolving Agents: ModularRSI Enables Harness Self-Improvement

ModularRSI freezes base model weights and evolves the agent's harness — system mechanisms like loop control, observation handling, tool use, context management, and task completion detection — through execution experience, achieving a 4.86-point gain on Terminal-Bench 2.0 that transfers across tasks, domains, and different base models.

Agent ArchitectureAgent Self-ImprovementFrozen Model Weights

0 likes · 18 min read

Frozen Model Weights, Evolving Agents: ModularRSI Enables Harness Self-Improvement

Architect

Sep 24, 2026 · Artificial Intelligence

Laya vs Nimble vs Kev: Choosing the Right Open-Source Jev for Agents

This article compares three open-source Jev implementations — Laya, Nimble, and Kev — analyzing their model architectures, training approaches, performance benchmarks, deployment requirements, and the four runtime components (context scoping, logging, policy code, failure loops) needed before using semantic decision models in production Agent systems.

Agent ArchitectureJevKev

0 likes · 26 min read

Laya vs Nimble vs Kev: Choosing the Right Open-Source Jev for Agents

Tech Freedom Circle

Sep 23, 2026 · Artificial Intelligence

Jev: The 'Non-Chatting' AI That's 193x Faster & 444x Cheaper Than LLMs for Agent Judgment Tasks

This article dissects Jev, a specialized judgment model from TypeSafe AI that replaces LLM-based classification with single-forward-pass inference, achieving 70-500ms latency and $0.042/M input tokens (output free). It covers Jev's three output primitives (Noul, Choice, Score), benchmarks against DeepSeek and Claude, and real-world use cases in browser automation, game AI, agent guardrails, and model routing.

AI performance optimizationAgent ArchitectureJev

0 likes · 20 min read

Jev: The 'Non-Chatting' AI That's 193x Faster & 444x Cheaper Than LLMs for Agent Judgment Tasks

Architect

Sep 22, 2026 · Artificial Intelligence

Jev: Extracting Semantic Micro-Judgments from Agent Loops into Observable Decision Layers

TypeSafe's Jev isolates semantic micro-judgments — routing, risk scoring, boolean checks — from generative LLM calls using Choice, Score, and Noul primitives that return typed probabilities, enabling policy code to branch directly on observable, auditable signals instead of parsing free-text model outputs.

Agent ArchitectureChoice Score NoulContext Compaction

0 likes · 25 min read

Jev: Extracting Semantic Micro-Judgments from Agent Loops into Observable Decision Layers

DataFunTalk

Sep 21, 2026 · Artificial Intelligence

Jev's First Week: 15 Projects Show How Agents Separate Generation from Judgment

In Jev's first six days, 239 public builds demonstrate a shift where developers offload structured judgments — yes/no, choice, scoring — to a specialized model while reserving LLMs for generation and code for execution, across browser automation, coding agents, batch classification, content scoring, and SQL integration.

Agent ArchitectureBatch ProcessingBrowser Agent

0 likes · 25 min read

Jev's First Week: 15 Projects Show How Agents Separate Generation from Judgment

DataFunSummit

Sep 20, 2026 · Artificial Intelligence

Alibaba's OpenCodeReview: Why Production Agents Are Reclaiming Control from LLMs

Alibaba's OpenCodeReview adopts a hybrid deterministic-engineering-plus-agent architecture for code review, cutting token usage by ~9x versus generic coding agents by constraining agent autonomy with hard-coded filters, token guards, and line-resolution modules, trading lower recall for higher precision and reliability.

AACR-BenchAI code reviewAgent Architecture

0 likes · 16 min read

Alibaba's OpenCodeReview: Why Production Agents Are Reclaiming Control from LLMs

Architect

Sep 16, 2026 · Artificial Intelligence

Google Agentic Skills: Survey, Engineering Practices & Lifecycle Framework

This article reviews Google's Agentic Skills survey and engineering practices, covering a formal six-tuple skill definition, three criteria for true skills, a nine-stage lifecycle, security governance, skill debt, conditional benefits, and complementary research on WikiSkill and SKILL.state, concluding with six critical questions for production skill deployment.

Agent ArchitectureAgentic SkillsGoogle

0 likes · 22 min read

Google Agentic Skills: Survey, Engineering Practices & Lifecycle Framework

Architect

Sep 13, 2026 · Artificial Intelligence

Multi-Agent Consistency: Distributed Systems Challenges Return with Autonomous Agents

The article explores four critical questions for multi-agent consistency: task decomposition rationale, structured handoffs with versioned snapshots, conflict resolution via evidence-based contracts, and verifiable completion criteria. It argues multi-agent systems reintroduce classic distributed systems challenges—identity, leases, idempotency, compensation—and require runtime proofs over model assertions.

Agent ArchitectureRuntime Verificationagent orchestration

0 likes · 21 min read

Multi-Agent Consistency: Distributed Systems Challenges Return with Autonomous Agents

Architect

Sep 12, 2026 · Artificial Intelligence

Google's Multi-Agent Research: Task Structure, Not Agent Count, Determines Architecture Value

Google's research on 260 multi-agent configurations across six benchmarks shows centralized architectures improve parallel tasks by 81% but hurt sequential planning by 39-70%. Teamwork framework adds critique-synthesis loops that retain failed branches. The key insight: agent count isn't an architecture metric—task decomposability, verifiable sub-results, and coordination costs should drive design.

AI AgentsAgent ArchitectureGoogle Research

0 likes · 18 min read

Architect

Sep 10, 2026 · Artificial Intelligence

Claude Code Memory Architecture: How CLAUDE.md, Auto Memory, and Runtime Evidence Shape Agent Context

This article dissects Claude Code's memory loading chain by examining its source code, revealing how CLAUDE.md, Auto Memory (MEMORY.md), and live workspace evidence interact — and why memory files are navigation aids, not enforceable configuration.

AI agent memoryAgent ArchitectureAuto Memory

0 likes · 19 min read

Claude Code Memory Architecture: How CLAUDE.md, Auto Memory, and Runtime Evidence Shape Agent Context

Data Bricklaying Diary

Sep 9, 2026 · Artificial Intelligence

Three Graphs, Three Jobs: Loop, Task Graph & Plugin Runtime in Agent Systems

This article argues that complex Agent systems must separate three distinct structures: Loop handles node-level convergence, Task Graph manages work dependencies and coordination, and Plugin Runtime binds capabilities like models and tools; mixing them into a monolithic Agent leads to invisible boundaries and unrecoverable failures.

Agent ArchitectureComponent GraphContext

0 likes · 17 min read

Three Graphs, Three Jobs: Loop, Task Graph & Plugin Runtime in Agent Systems

Architecture Development Notes

Sep 8, 2026 · Artificial Intelligence

Rethinking Agent Composition: Single-Loop Skills vs. Sub-Agent Handoffs

This article analyzes why default multi-agent architectures leak state in long conversations, advocating for single-loop agents with dynamically loaded skills based on usage frequency, using Anthropic's commerce-agents reference implementation to illustrate caching-aware design, handoff vs. delegation distinctions, and evaluation strategies.

Agent ArchitectureAnthropicLLM applications

0 likes · 10 min read

Rethinking Agent Composition: Single-Loop Skills vs. Sub-Agent Handoffs

AI Cyberspace

Sep 8, 2026 · Artificial Intelligence

General Agent Harness Architecture: From 4 LLM Defects to 36 Functional Modules

This article derives a universal Agent Harness architecture from four mainstream coding agents, identifying four fundamental LLM limitations — no external perception, no action capability, no memory across calls, and no guaranteed correctness — and mapping them to eight responsibility domains with 36 concrete functional modules, plus a five-dimensional framework for vertical scenario adaptation.

Action ControlAgent ArchitectureCoding Agents

0 likes · 53 min read

General Agent Harness Architecture: From 4 LLM Defects to 36 Functional Modules

LuTiao Programming

Sep 6, 2026 · Artificial Intelligence

Spring AI 2.0 Tool Search: Stop Flooding LLMs with Dozens of Tools

The author migrates a Spring AI Agent with 30+ business tools to Spring AI 2.0's Tool Search, which uses Lucene indexing to let the model search for relevant tools before calling them, reducing context overload and improving selection accuracy, while sharing best practices for tool descriptions and safe write-operation handling.

AI AgentAgent ArchitectureJava

0 likes · 15 min read

Spring AI 2.0 Tool Search: Stop Flooding LLMs with Dozens of Tools

Architect

Sep 6, 2026 · Artificial Intelligence

Vector Databases Aren't Dead: How Claude Code & Cursor Are Redefining RAG for Agents

The article debunks claims that vector databases are obsolete, analyzing how Claude Code and Cursor integrate retrieval into agent runtime loops rather than abandoning RAG, and proposes a five-layer architecture where vector indexes serve as retrieval projections alongside grep, semantic search, and authoritative sources.

AI AgentsAgent ArchitectureClaude Code

0 likes · 21 min read

Vector Databases Aren't Dead: How Claude Code & Cursor Are Redefining RAG for Agents

James' Growth Diary

Sep 6, 2026 · Artificial Intelligence

7-Layer Agent Platform Architecture: Why Misdiagnosis Happens and How to Fix It

This article defines a 7-layer architecture for self-built Agent platforms, illustrates three real-world misdiagnoses caused by layer confusion, compares four layering approaches, provides a self-check matrix for different product stages, and warns against four common architectural pitfalls.

AI platformAgent ArchitectureMCP

0 likes · 29 min read

7-Layer Agent Platform Architecture: Why Misdiagnosis Happens and How to Fix It

Architecture and Beyond

Sep 6, 2026 · Artificial Intelligence

DeepSeek Harness: Context, Memory & Knowledge Architecture Deep Dive

This article dissects DeepSeek Harness's unified Session Log architecture where context management, memory compaction, and knowledge acquisition collaborate through layered context assembly, structure-preserving compaction, and tool-mediated retrieval — all traceable and replayable.

Agent ArchitectureContext ManagementDeepSeek Harness

0 likes · 31 min read

DeepSeek Harness: Context, Memory & Knowledge Architecture Deep Dive

AI Engineering

Sep 6, 2026 · Artificial Intelligence

Grok Bot: Treating AI Agents as Colleagues, Not Software Tools

SpaceXAI's Grok Bot reimagines AI agents as persistent, specialized teammates with their own cloud computers, demonstrating a multi-bot team that handles engineering, product, design, and operations tasks autonomously while humans focus on review and strategy.

AI AgentsAI teammatesAgent Architecture

0 likes · 19 min read

Grok Bot: Treating AI Agents as Colleagues, Not Software Tools

PaperAgent

Sep 6, 2026 · Artificial Intelligence

Anthropic's Killer Multi-Agent Blueprint: One Loop, Skills, Harness & Snapshot Eval

Anthropic's production e-commerce and math-formalization agents share a unified architecture: a single-model loop with modular skills, tool calls to existing systems, code-enforced harness rules, and snapshot-based evaluation, enabling scalable, verifiable multi-agent systems.

Agent ArchitectureAnthropicFormal Verification

0 likes · 17 min read

Anthropic's Killer Multi-Agent Blueprint: One Loop, Skills, Harness & Snapshot Eval

Alibaba Cloud Native

Sep 5, 2026 · Artificial Intelligence

DeepSeek Harness: Architecting Enterprise Evolution via Post-Training Design

This article analyzes DeepSeek Harness from a post-training perspective, revealing how its architecture bakes enterprise evolution into environment shaping and trajectory sedimentation, validated by a self-evolution POC that identifies interface design, contract shape, and feedback quality as critical bottlenecks.

Agent ArchitectureDeepSeek HarnessPOC validation

0 likes · 37 min read

DeepSeek Harness: Architecting Enterprise Evolution via Post-Training Design

James' Growth Diary

Sep 5, 2026 · Artificial Intelligence

Why Build Your Own Agent: From Chat to Reliable Execution

This article argues that chat APIs alone are insufficient for AI agents; true agent systems require execution environments, tool loops, multi-tenant isolation, and layered architecture to move from demo to production-grade reliability across multiple entry points.

AI AgentsAgent ArchitectureExecution Environment

0 likes · 22 min read

Why Build Your Own Agent: From Chat to Reliable Execution

TechVision Expert Circle

Sep 4, 2026 · Artificial Intelligence

AI Bills Skyrocket Despite Cheaper Models: The Agent Cost Multiplier Effect

As model inference prices drop, AI costs surge because Agent architectures multiply model calls per user request; the article breaks down the four-layer cost structure and offers six practical governance tactics—model routing, prompt caching, call-chain slimming, token budgets, observability, and chargebacks—to build a sustainable AI FinOps practice.

AI cost managementAgent ArchitectureFinOps

0 likes · 15 min read

AI Bills Skyrocket Despite Cheaper Models: The Agent Cost Multiplier Effect

AI Large-Model Wave and Transformation Guide

Sep 3, 2026 · Artificial Intelligence

Why More Tools Make Enterprise Agents Less Trustworthy: Tool Registry vs. Governed Action Space

The article argues that simply connecting more tools to enterprise AI agents reduces operational trust because tools lack business context; instead, a governed action space that dynamically determines valid actions based on object state, rules, and permissions is essential for safe, autonomous agent operation.

AI AgentsAction SpaceAgent Architecture

0 likes · 14 min read

Why More Tools Make Enterprise Agents Less Trustworthy: Tool Registry vs. Governed Action Space

Wu Shixiong's Large Model Academy

Sep 1, 2026 · Artificial Intelligence

Why Did Task B Inherit Task A's Retry Count? LangGraph's Three Data Layers

This article explains how misplacing retry_count in LangGraph's user-level Store instead of thread-level State causes cross-task contamination, detailing the distinct lifecycles of State, Runtime Context, and Store with code examples and engineering checks.

Agent ArchitectureData LifecycleLangChain

0 likes · 13 min read

Why Did Task B Inherit Task A's Retry Count? LangGraph's Three Data Layers

The Dominant Programmer

Aug 29, 2026 · Artificial Intelligence

Harness Engineering with Spring AI Alibaba: Theory, Architecture, and Full Implementation Guide

This comprehensive guide walks through Harness Engineering concepts, the seven‑layer architecture, environment setup, full Spring Boot codebase, agent configuration, best‑practice recommendations, testing procedures, common issues, and advanced directions for building controllable AI agents with Spring AI Alibaba.

AI AgentsAgent ArchitectureHarness Engineering

0 likes · 34 min read

Harness Engineering with Spring AI Alibaba: Theory, Architecture, and Full Implementation Guide

Wu Shixiong's Large Model Academy

Aug 27, 2026 · Artificial Intelligence

Why Agents Refund When Policy Says No: The Retrieval-Enforcement Gap

An AI agent correctly retrieves a 'no refund' policy but still executes a $50 refund, exposing the critical gap between policy retrieval and runtime enforcement; the article argues authorization must be enforced at the tool gateway with bound decisions, not just in model context, and outlines regression tests for deny paths.

AI AgentsAgent ArchitectureLLM security

0 likes · 13 min read

Why Agents Refund When Policy Says No: The Retrieval-Enforcement Gap

Top Architecture Tech Stack

Aug 26, 2026 · Artificial Intelligence

Doubao Agent Demonstrates It Can Match Every Competitor’s Office Agent Capability

Doubao Work integrates tightly with Feishu to showcase an enterprise AI agent that not only handles typical office tasks like file processing, web generation, and spreadsheet manipulation, but also leverages organizational context, permissions, and native workflow integration to outperform standard chat‑based bots.

AI productivityAgent ArchitectureContextual AI

0 likes · 12 min read

Doubao Agent Demonstrates It Can Match Every Competitor’s Office Agent Capability

Architecture Development Notes

Aug 22, 2026 · Artificial Intelligence

Three-Layer Verification for AI Agents: Catching Reasoning Errors Before They Cascade

This article details a three-layer verification architecture for AI agents—step-level validators, consistency checkers, and reasoning trace verifiers—to catch intermediate reasoning errors that end-to-end checks miss, plus graded failure handling, cost-control tactics, and a phased rollout plan for production systems.

AI AgentAgent ArchitectureConsistency Checking

0 likes · 12 min read

Three-Layer Verification for AI Agents: Catching Reasoning Errors Before They Cascade

Software Engineering 3.0 Era

Aug 22, 2026 · Artificial Intelligence

Codex Harness: How OpenAI Built an Embeddable Agent OS in 135 Rust Crates

This article dissects OpenAI's Codex Harness, a 146K-line Rust workspace of 135 crates that powers ChatGPT, CLI, and IDE extensions as an embeddable agent platform, detailing its agent loop, context engineering, JSON-RPC protocol, multi-OS sandboxing, and multi-agent architecture with measurable benchmark gains on ARC-AGI-3.

Agent ArchitectureAgent LoopCodex Harness

0 likes · 33 min read

Codex Harness: How OpenAI Built an Embeddable Agent OS in 135 Rust Crates

DaTaobao Tech

Aug 21, 2026 · Artificial Intelligence

Best Practices for Developing AI Skills: A Case Study of the Baibu Detail Assistant

This article analyzes the end‑to‑end development of an AI Skill for the Baibu detail assistant, covering industry best practices, architecture with a bridge decoupling local and remote components, workflow design patterns, development efficiency tricks, and runtime optimizations that together illustrate how to build maintainable, high‑performance Skills.

AI Skill DevelopmentAgent ArchitectureControl Tuning

0 likes · 21 min read

Best Practices for Developing AI Skills: A Case Study of the Baibu Detail Assistant

Geek Labs

Aug 21, 2026 · Artificial Intelligence

How a Hippocampus‑Style Memory Layer Stops AI Coding Assistants from Forgetting

The article explains why AI coding assistants frequently lose context, breaks down the concepts of context windows, compression, and long‑term memory, and shows how the open‑source Magic Context plugin implements a capture‑consolidate‑recall memory loop to keep agents aware of project history across sessions and tools.

AI coding assistantAgent ArchitectureContext Management

0 likes · 15 min read

How a Hippocampus‑Style Memory Layer Stops AI Coding Assistants from Forgetting

Wuming AI

Aug 20, 2026 · Industry Insights

How a Lawyer Uses AI to Run a Complete Litigation Workflow

Lawyer Cheng Jiandu demonstrates an end‑to‑end AI‑assisted litigation process for an equipment sale dispute, showing how AI can organize materials, verify facts, perform multi‑model checks, and generate draft documents while the lawyer retains ultimate decision‑making and oversight.

AIAgent ArchitectureLegalTech

0 likes · 13 min read

How a Lawyer Uses AI to Run a Complete Litigation Workflow

Architect

Aug 19, 2026 · R&D Management

Pi vs OpenCode vs DSH: Where Does the Harness Put the Complexity?

A recent Agent Harness test comparing Pi, OpenCode, and DSH shows Pi completing 20 of 30 tasks at $0.028 per task versus OpenCode's 14 tasks at $0.195, while the article analyzes how each system distributes complexity, handles extensions, server boundaries, and runtime composability, highlighting trade‑offs for real‑world migrations.

Agent ArchitectureDSHExtension

0 likes · 18 min read

Pi vs OpenCode vs DSH: Where Does the Harness Put the Complexity?

Architecture Development Notes

Aug 19, 2026 · Artificial Intelligence

Orchestrator-Worker Pattern: Engineering Dynamic Task Decomposition for AI Agents

This article explains the Orchestrator-Worker pattern for AI agents, where an orchestrator dynamically decomposes complex tasks into specialized workers, enabling parallel execution and reducing context interference, with practical engineering considerations for model selection, error handling, and observability.

AI AgentsAgent ArchitectureContext Management

0 likes · 14 min read

Orchestrator-Worker Pattern: Engineering Dynamic Task Decomposition for AI Agents

Data Bricklaying Diary

Aug 18, 2026 · Artificial Intelligence

Semantic Models ≠ Live State: Why Agents Need Object Runtime

This article distinguishes semantic models (which define business object meanings) from object runtime (which provides traceable, versioned projections of specific object states for AI agents), detailing five core responsibilities, differences from data platforms and agent runtimes, a credit-adjustment case study, and guidance on when and how to implement minimal object projections.

Agent ArchitectureCDCDigital Twin

0 likes · 21 min read

Semantic Models ≠ Live State: Why Agents Need Object Runtime

Linyb Geek Road

Aug 18, 2026 · Artificial Intelligence

How Decoupling the “Brain” and “Hands” Transforms Agent Architecture and Cuts First‑Token Latency by 60%

The article analyzes the structural flaw of tightly coupling session, harness, and sandbox in a single container, proposes separating them into three independent interfaces, and demonstrates how this redesign improves fault tolerance, security, and reduces Time‑to‑First‑Token latency by about 60% while enabling flexible, scalable agent deployments.

Agent ArchitectureHarnessLLM performance

0 likes · 11 min read

How Decoupling the “Brain” and “Hands” Transforms Agent Architecture and Cuts First‑Token Latency by 60%

DataFunTalk

Aug 15, 2026 · Artificial Intelligence

Why Real-Time Agents Need More Than One Loop: Google’s AMIE Splits Talk, Think, and See

Real‑time agents face a three‑way conflict—low‑latency interaction, slow reasoning, and continuous perception—so Google’s AMIE (Video) replaces a single loop with three asynchronous agents (Talker, Planner, Perception), cutting average latency from 21.4 s to 2.6 s while preserving task performance.

AMIEAgent Architectureasynchronous orchestration

0 likes · 13 min read

Why Real-Time Agents Need More Than One Loop: Google’s AMIE Splits Talk, Think, and See

Su San Talks Tech

Aug 15, 2026 · Artificial Intelligence

Why Did DeepSeek Harness Suddenly Go Viral?

DeepSeek Harness, DeepSeek’s first Agent product, went from launch to 50,000 GitHub stars in 12 hours, thanks to its all‑plugin architecture, record‑breaking growth, and a lightning‑fast two‑step release, positioning it as an open‑source Agent operating system that rivals Claude Code and Pi.

AI AgentAgent ArchitectureCordis

0 likes · 21 min read

Why Did DeepSeek Harness Suddenly Go Viral?

Architect

Aug 9, 2026 · Artificial Intelligence

Repositioning the Three Architectural Axes of LLM Memory

This article reviews the recent “Memory for Large Language Models” survey, outlining three orthogonal design axes—representation, update dynamics, and persistence—and maps them to engineering concerns such as work‑set, compressed state, long‑term items, and raw evidence, while discussing evaluation dimensions and practical implementation guidelines for agent systems.

Agent ArchitectureAttentionLLM memory

0 likes · 20 min read

Repositioning the Three Architectural Axes of LLM Memory

AI Large-Model Wave and Transformation Guide

Aug 9, 2026 · Artificial Intelligence

Why Enterprise AI Needs All Three Legs: Data, Agent, and FDE

The article explains how a large enterprise succeeded in AI‑enabled sales by cleaning five years of data, deploying a dedicated AI agent for each of eleven sales stages, and using Front‑end Deployment Engineers to translate expert knowledge into repeatable processes, showing that missing any of these three components makes the system limp.

AI DeploymentAgent ArchitectureBusiness Process Automation

0 likes · 9 min read

Why Enterprise AI Needs All Three Legs: Data, Agent, and FDE

Data Bricklaying Diary

Aug 6, 2026 · Artificial Intelligence

From Ontology Semantics to Ontology Intelligence: Why Understanding Business ≠ Driving It

The article distinguishes ontology semantics (AI understanding business objects, states, rules) from ontology intelligence (explainable decisions, contract-constrained actions, auditable loops), outlining seven engineering capabilities needed to close the loop and emphasizing a minimal viable loop around high-value decisions.

Action ContractsAgent ArchitectureAgent Runtime

0 likes · 16 min read

From Ontology Semantics to Ontology Intelligence: Why Understanding Business ≠ Driving It

Data Bricklaying Diary

Aug 5, 2026 · Industry Insights

Ontology Intelligence: Closing the Engineering Gap for Enterprise AI Agents

This article introduces the Ontology Intelligence series, explaining why enterprise AI agents fail in production without unified business semantics, current object state, explainable decisions, controlled actions, and continuous governance—outlining a five-layer framework and scenario-based criteria for adopting ontology-driven architectures.

AI Production GapAgent ArchitectureControlled Actions

0 likes · 18 min read

Ontology Intelligence: Closing the Engineering Gap for Enterprise AI Agents

Machine Heart

Jul 24, 2026 · Artificial Intelligence

From One‑Shot Answers to Action Chains: S‑Agent Advances Spatial Intelligence

S‑Agent redefines spatial intelligence by replacing single‑shot answers with a multi‑step action chain that combines a vision‑language model for task planning, specialized depth and pose models for 3D alignment, and a spatial expert that converts geometry into usable evidence, achieving state‑of‑the‑art zero‑shot scores on MMSI‑Bench and ViewSpatial‑Bench and further improvements after distilling 29.2 k trajectories into an 8‑billion‑parameter model.

Agent ArchitectureSpatial IntelligenceVision-Language Model

0 likes · 11 min read

From One‑Shot Answers to Action Chains: S‑Agent Advances Spatial Intelligence

AI Illustrated Series

Jul 22, 2026 · Interview Experience

How to Design a Smart Customer Service Agent: Core Four‑Layer Architecture

The article outlines a four‑layer architecture for a smart customer service agent—access, understanding, processing, and output—detailing each layer's responsibilities, handoff triggers to human agents, real‑world use cases, and key evaluation metrics.

AIAgent ArchitectureCustomer Service

0 likes · 4 min read

How to Design a Smart Customer Service Agent: Core Four‑Layer Architecture

TechVision Expert Circle

Jul 21, 2026 · Artificial Intelligence

Apple’s New Siri Public Beta Redefines Mobile Assistants with LLM‑Based Agent Architecture

Apple’s July 2026 public beta of Siri replaces its legacy intent‑based pipeline with a large‑language‑model‑driven agent architecture, introducing multimodal perception, persistent memory, and a three‑tier edge‑cloud inference system that reshapes mobile assistants while emphasizing privacy through on‑device processing and differential‑privacy techniques.

Agent ArchitectureAppleEdge AI

0 likes · 13 min read

Apple’s New Siri Public Beta Redefines Mobile Assistants with LLM‑Based Agent Architecture

Alibaba Cloud Developer

Jul 21, 2026 · R&D Management

How End‑to‑End Delivery 2.0 Turns AI Coding into an Industrial‑Scale Assembly Line

The article analyzes the bottlenecks of current AI‑assisted coding, proposes a 2.0 end‑to‑end delivery framework that combines a Spec‑driven pipeline with a Harness constraint system, introduces multiple specialized agents, and outlines traceability, verification, and continuous‑improvement mechanisms to achieve industrial‑grade software production.

AI codingAgent ArchitectureEnd-to-End Delivery

0 likes · 41 min read

How End‑to‑End Delivery 2.0 Turns AI Coding into an Industrial‑Scale Assembly Line

AI Architecture Path

Jul 19, 2026 · Artificial Intelligence

DeepTutor: 27K‑Star Open‑Source AI Tutor with Agent‑Native Architecture and Auditable Memory

The article critiques common AI learning tools for providing only answers, losing context, and risking data privacy, then presents DeepTutor—a locally deployable, open‑source AI tutor that uses a unified Agent‑Native runtime, double‑loop reasoning, three‑layer auditable memory, and a full offline learning loop covering study, practice, testing, research, and note‑taking.

AI tutoringAgent ArchitectureAuditable memory

0 likes · 17 min read

DeepTutor: 27K‑Star Open‑Source AI Tutor with Agent‑Native Architecture and Auditable Memory

Linyb Geek Road

Jul 15, 2026 · Artificial Intelligence

From ReAct to Harness: Building Production‑Ready Agent Architectures

The article outlines the five‑stage evolution of AI agents—from the basic ReAct loop to self‑driving, self‑optimizing systems—and presents six engineering pillars (verification, stop, state, recovery, isolation, observability) that together form a Harness framework for deploying reliable, production‑grade agents.

AI AgentsAgent Architectureobservability

0 likes · 8 min read

From ReAct to Harness: Building Production‑Ready Agent Architectures

AI Engineering

Jul 11, 2026 · Artificial Intelligence

Why Logs Should Be the Agent Itself, Not Just a Byproduct

The article analyzes Yohei Nakajima’s "The Log is the Agent" paper, showing how ActiveGraph unifies goals, rules, tool calls, LLM responses, and artifacts into a single append‑only event log, enabling deterministic replay, cheap forking, and full provenance for LLM‑driven agents.

ActiveGraphAgent ArchitectureEvent Sourcing

0 likes · 13 min read

Why Logs Should Be the Agent Itself, Not Just a Byproduct

DataFunTalk

Jul 10, 2026 · Artificial Intelligence

How Agents Evolve Without Degrading: From Risk Control to Semantic Engineering

In a July 2 live discussion, three experts dissect practical AI‑agent engineering—covering risk, semantics, evolution, cost, architecture, evaluation metrics, responsibility, and scaling—showing how to build stable, explainable, and continuously improvable agent systems without falling into hype or degradation.

AI AgentsAgent ArchitectureCost Optimization

0 likes · 17 min read

How Agents Evolve Without Degrading: From Risk Control to Semantic Engineering

DataFunSummit

Jul 7, 2026 · Artificial Intelligence

Ant Group OpAgent: Online RL‑Powered Open‑Domain Browser Automation Agent

The article details Ant Group's OpAgent, an open‑domain browser automation agent that overcomes perception, timeliness, and implicit interaction challenges through a three‑stage pipeline of multi‑task supervised fine‑tuning, online reinforcement learning, and a four‑module Planner‑Grounder‑Reflector‑Summarizer architecture, achieving a 71.6% Pass@1 score on WebArena and releasing all code and models publicly.

Agent ArchitectureOpAgentWebArena

0 likes · 15 min read

Ant Group OpAgent: Online RL‑Powered Open‑Domain Browser Automation Agent

JavaGuide

Jul 7, 2026 · Artificial Intelligence

How Does Claude Code Detect the Skills You’ve Been Using for Months?

The article explains the technical differences between CLAUDE.md and Skill files, when to use each, their loading strategies, file structures, front‑matter fields, dynamic context, security considerations, and how Skills interact with Subagents, Plugins and Agent Teams in Claude Code.

AI SkillsAgent ArchitectureClaude Code

0 likes · 19 min read

How Does Claude Code Detect the Skills You’ve Been Using for Months?

inShocking

Jul 6, 2026 · Artificial Intelligence

AI Agent Core Technology Explained – Chapter 01: What Is a Foundational Agent?

The article breaks down how AI agents extend large language models by adding tools, memory, and looping mechanisms, explains the ReAct paradigm and its evolution, compares agents to traditional workflows, and outlines product perspectives, coding advantages, current maturity stages, and typical use‑case categories.

AI AgentAgent ArchitectureLLM

0 likes · 11 min read

AI Agent Core Technology Explained – Chapter 01: What Is a Foundational Agent?

AgentGuide

Jul 5, 2026 · Artificial Intelligence

Learning Path for Large‑Model Application Engineers: From Prompt & RAG to Agent Deployment

This guide outlines a comprehensive learning roadmap for large‑model application engineers, covering fundamentals such as Transformer architecture and scaling laws, practical API usage, prompt engineering, retrieval‑augmented generation, agent design, engineering best practices, security, observability, cost optimization, and fine‑tuning principles.

AI AgentsAgent ArchitectureRetrieval-Augmented Generation

0 likes · 14 min read

Learning Path for Large‑Model Application Engineers: From Prompt & RAG to Agent Deployment

AI Architecture Hub

Jul 3, 2026 · Artificial Intelligence

20 Loop Design Patterns Every AI Engineer Must Master

This article catalogs twenty high‑frequency loop architectures that transform single‑call AI models into autonomous, self‑optimising agents, explaining each pattern’s purpose, workflow, concrete code example, and typical commercial scenarios such as content creation, compliance review, and strategic decision making.

AI loopsAgent ArchitectureDesign Patterns

0 likes · 21 min read

20 Loop Design Patterns Every AI Engineer Must Master

AI Programming Lab

Jul 1, 2026 · Artificial Intelligence

Hands‑On Review of Claude Science: A Game‑Changer for Researchers

The article reviews Anthropic's new Claude Science app, detailing how its integrated agent architecture, reproducible workflow, reviewer agent, and seamless HPC support streamline fragmented life‑science research tasks while noting current platform limits and installation steps.

AI research assistantAgent ArchitectureAnthropic

0 likes · 8 min read

Hands‑On Review of Claude Science: A Game‑Changer for Researchers

TechVision Expert Circle

Jun 30, 2026 · Industry Insights

How AI Agents Are Redefining Enterprise Software Procurement

The article analyzes how AI agents are shifting software purchasing from license‑based models to outcome‑based and capability‑marketplace approaches, detailing architectural differences, emerging pricing models, implementation challenges, and the strategic implications for CIOs and vendors.

AI AgentsAgent ArchitectureEnterprise IT

0 likes · 11 min read

How AI Agents Are Redefining Enterprise Software Procurement

Network Intelligence Research Center (NIRC)

Jun 30, 2026 · Artificial Intelligence

From Prompt to Loop: The Evolution of AI Development Paradigms

AI applications are shifting from single‑turn Q&A to systematic intelligence through four nested engineering stages—Prompt, Context, Harness, and Loop—each addressing communication, information supply, execution safety, and autonomous closed‑loop control, while exposing distinct limitations that drive the next paradigm.

AI SystemsAgent ArchitectureHarness Engineering

0 likes · 16 min read

From Prompt to Loop: The Evolution of AI Development Paradigms

AI Architecture Hub

Jun 27, 2026 · Artificial Intelligence

From One‑Shot Prompts to Autonomous Loops: What Architects Must Focus on in 2026

In 2026 the AI industry shifts from single‑prompt engineering to autonomous Loop systems, requiring architects to adopt a four‑pillar design—trusted feedback, persistent state, stop conditions, and human hand‑off—while mapping traditional SRE reliability practices, avoiding common pitfalls, and leveraging low‑cost, production‑grade implementations such as daily CI failure triage.

AI AgentsAgent ArchitectureHigh reliability

0 likes · 15 min read

From One‑Shot Prompts to Autonomous Loops: What Architects Must Focus on in 2026

Hacker Afternoon Tea

Jun 26, 2026 · Artificial Intelligence

Why Loop Beats Multica: The Crucial Divide Between an AI “Colleague” and an Outsourced Agent

The article compares Loop and Multica, showing how Loop’s “colleague” model—featuring a three‑layer Soul/Agent/Instance identity, explicit @‑based dispatch, rich multi‑agent orchestration, rewind capability, scheduled tasks, and precise external event routing—outperforms Multica’s simpler “outsourced task” approach despite Multica’s broader tool matrix.

AI collaborationAgent ArchitectureLoop

0 likes · 18 min read

Why Loop Beats Multica: The Crucial Divide Between an AI “Colleague” and an Outsourced Agent

DataFunSummit

Jun 26, 2026 · Artificial Intelligence

Why Memory Is the Bottleneck for AI Agents and How MemOS Boosts Performance by Over 200%

The article explains how memory has become the decisive factor for AI agents, details the MemOS framework’s five‑layer architecture and three‑layer memory coordination, compares model‑driven and application‑driven approaches, and shows how MemOS‑powered cloud services achieved 100‑200% monthly growth, 45‑72% token savings, and up to 50% reduction in overall token consumption.

AI memoryAgent ArchitectureMemOS

0 likes · 18 min read

Why Memory Is the Bottleneck for AI Agents and How MemOS Boosts Performance by Over 200%

AI Architecture Hub

Jun 26, 2026 · Artificial Intelligence

30 Core AI Agent Engineering Concepts Every Developer Must Know

This article breaks down the essential 30 concepts behind AI agents—covering their loop‑based execution, state management, common patterns, configuration files, prompt caching, context corruption, capability protocols, sandbox security, permission controls, observability, and practical entry‑level advice—so developers can understand any new framework without chasing hype.

AI AgentsAgent ArchitectureMCP

0 likes · 21 min read

30 Core AI Agent Engineering Concepts Every Developer Must Know

Code Mala Tang

Jun 25, 2026 · Artificial Intelligence

30 Core Concepts Every AI Agent Engineer Must Master

Understanding the timeless principles behind AI agents—rather than chasing the latest frameworks—requires mastering 30 core concepts, from the fundamental Think‑Act‑Observe loop and state management to configuration files, workflow caching, sandboxing, and multi‑agent orchestration, enabling predictable, cost‑effective, and secure automation.

AI AgentsAgent ArchitectureSecurity

0 likes · 21 min read

30 Core Concepts Every AI Agent Engineer Must Master

Node.js Tech Stack

Jun 25, 2026 · Artificial Intelligence

Testing Tencent Marvis Reveals Claude Code‑Style AI Agent Architecture

The author tests Tencent’s Marvis AI assistant, showing how its dual‑device agent system lets a phone remotely control a Mac, locate and transfer files, execute commands, schedule tasks, and even organize documents offline, while highlighting security controls and the similarity to Claude Code’s multi‑agent design.

AI assistantAgent ArchitectureMarvis

0 likes · 9 min read

Testing Tencent Marvis Reveals Claude Code‑Style AI Agent Architecture

James' Growth Diary

Jun 24, 2026 · Artificial Intelligence

Why Immutable Historical Context Is the Core of Hermes’ Prefix‑Caching Performance Design

The article explains how Hermes relies on prefix caching—keeping the system prompt unchanged throughout a session—to achieve 70‑80% cache‑hit rates, reduce token costs by up to 60%, and shape its architecture across agents, sub‑agents, and background review tasks.

AI AgentsAgent ArchitectureCache TTL

0 likes · 14 min read

Why Immutable Historical Context Is the Core of Hermes’ Prefix‑Caching Performance Design

DataFunSummit

Jun 24, 2026 · Artificial Intelligence

Three Forms of Large Model Memory – Parameter, Token, and Latent – Why Top Companies Are All‑In

A new paper unifies AI memory research with a three‑dimensional framework (Forms, Functions, Dynamics), classifies memory as parameter‑level, token‑level, or latent‑space, and evaluates real‑world implementations from OpenAI, Google, Amazon and dozens of open‑source frameworks, highlighting trade‑offs such as retrieval quality, catastrophic forgetting and forgetting mechanisms.

AI memoryAgent Architectureframework comparison

0 likes · 19 min read

Three Forms of Large Model Memory – Parameter, Token, and Latent – Why Top Companies Are All‑In

DaTaobao Tech

Jun 22, 2026 · Artificial Intelligence

Breaking AI Coding Bottlenecks: How Specflow Agent Separates Deep Analysis from Code Execution

The article dissects why AI‑generated code often fails to boost productivity—highlighting attention‑mechanism limits, context collapse, and mismatched developer workflows—and proposes a Specflow Agent that isolates deep requirement analysis from coding to dramatically cut manual intervention.

AI codingAgent ArchitectureContext Management

0 likes · 40 min read

Breaking AI Coding Bottlenecks: How Specflow Agent Separates Deep Analysis from Code Execution

ThinkingAgent

Jun 21, 2026 · Artificial Intelligence

The 6‑Layer Architecture of AI Agents: Perception, Planning, Tools, Memory, Execution, and Feedback

This article breaks down the complete cognition‑action system of modern AI agents into six inter‑connected layers—Perception, Planning, Tools, Memory, Execution, and Feedback—explaining their core problems, engineering designs, common pitfalls, and best‑practice metrics with concrete code examples and real‑world use cases.

AI AgentsAgent Architectureexecution

0 likes · 40 min read

The 6‑Layer Architecture of AI Agents: Perception, Planning, Tools, Memory, Execution, and Feedback

TechVision Expert Circle

Jun 19, 2026 · Artificial Intelligence

Avoid the Top 5 Pitfalls When Deploying Enterprise AI Agents (Part 1)

The article shares hard‑won lessons from three enterprise‑grade AI Agent projects, detailing five common pitfalls—over‑reliance on a single agent, insecure direct model calls, latency and cost overruns, hallucinations, and lack of observability—and provides concrete architectural and operational solutions for each.

AI AgentsAgent ArchitectureCost Management

0 likes · 10 min read

Avoid the Top 5 Pitfalls When Deploying Enterprise AI Agents (Part 1)

James' Growth Diary

Jun 18, 2026 · Artificial Intelligence

Externalizing Agent Decisions to Files: How a Three‑Layer Prompt Architecture Drives Behavior

The article examines Hermes' design that moves all agent decision rules into editable text files, explains the three‑layer stable‑context‑volatile architecture, compares it with other frameworks, and shows how this approach improves transparency, controllability, and cache efficiency for AI agents.

AI safetyAgent ArchitectureHermes

0 likes · 11 min read

Externalizing Agent Decisions to Files: How a Three‑Layer Prompt Architecture Drives Behavior

Shuge Unlimited

Jun 18, 2026 · Artificial Intelligence

What the 120k‑Character Claude Fable 5 Prompt Leak Reveals About Its True Architecture

A leaked 120 KB system prompt for Claude Fable 5 shows that the model is not merely a chat bot but a fully engineered agent system with layered responsibilities, tool contracts, hard and soft constraints, runtime patches, and an opt‑in design that prevents it from autonomously selecting commercial partners.

Agent ArchitectureClaude Fable 5LLM constraints

0 likes · 17 min read

What the 120k‑Character Claude Fable 5 Prompt Leak Reveals About Its True Architecture

Frontend AI Walk

Jun 16, 2026 · Artificial Intelligence

From Manual AI Chores to Self‑Driving Loops: Six Core Components and a Five‑Step Guide

This article introduces Loop Engineering, explains its five atomic actions and six essential components, contrasts loops with traditional workflows, outlines suitable and unsuitable scenarios, presents real‑world case studies, highlights three key risks with mitigations, and provides a concrete five‑step implementation guide for building a self‑running AI loop.

AI automationAgent ArchitectureLoop Engineering

0 likes · 23 min read

From Manual AI Chores to Self‑Driving Loops: Six Core Components and a Five‑Step Guide

Coder Trainee

Jun 12, 2026 · Artificial Intelligence

From Solo to Team: Multi‑Agent Collaboration with AutoGen, CrewAI, and LangGraph

This article explains why a single AI agent often falls short for complex tasks, outlines the benefits of multi‑agent collaboration, compares common architecture patterns, and provides hands‑on examples using AutoGen, CrewAI, and LangGraph, followed by a real‑world customer‑service team case and best‑practice guidelines.

AI AgentsAgent ArchitectureAutoGen

0 likes · 14 min read

From Solo to Team: Multi‑Agent Collaboration with AutoGen, CrewAI, and LangGraph

AntData

Jun 12, 2026 · Artificial Intelligence

Rethinking AI Memory: From Raw Ledger to Policy‑Driven Closed Loop

The article argues that AI memory is not mere storage but an external state that feeds decisions, proposes three core propositions—Memory as decision‑usable external state, a minimal closure of Raw Ledger + Views + Policy, and event sequences as the fundamental unit—and details how a System 1 + System 2 architecture, non‑parametric designs, temporal handling, and learnable policies together shape the practical limits of modern agentic memory systems.

AI memoryAgent ArchitectureRetrieval Augmentation

0 likes · 42 min read

Rethinking AI Memory: From Raw Ledger to Policy‑Driven Closed Loop

IT Services Circle

Jun 12, 2026 · Artificial Intelligence

Inside Claude Code’s Query Loop: From a Simple While Loop to an Industrial‑Grade Agent Engine

This article dissects Claude Code’s 1729‑line queryLoop, explaining its four‑layer call chain (ask → QueryEngine → query → queryLoop), the async‑generator core that streams model output, how tool calls are handled in parallel, the explicit state object, and the many error‑recovery paths that make the loop production‑ready.

Agent ArchitectureAsync GeneratorClaude Code

0 likes · 27 min read

Inside Claude Code’s Query Loop: From a Simple While Loop to an Industrial‑Grade Agent Engine

Data Party THU

Jun 11, 2026 · Artificial Intelligence

GBrain’s 14K‑Star Open‑Source System Solves AI Agent Forgetting

GBrain, the open‑source AI agent memory platform with over 14,000 GitHub stars, uses a three‑layer architecture—Markdown‑based truth source, hybrid retrieval with PGLite, and 34 skill workflows—to eliminate agent forgetting, achieve a 31.4% retrieval boost, and provide Python integration via the MCP protocol, while outlining practical deployment pitfalls.

AI memoryAgent ArchitectureGBrain

0 likes · 17 min read

GBrain’s 14K‑Star Open‑Source System Solves AI Agent Forgetting

Linyb Geek Road

Jun 11, 2026 · Artificial Intelligence

From Reactive to Self‑Evolving: The Four‑Stage Evolution of AI Agents (2023‑2026)

The article maps the 2023‑2026 evolution of AI agents across four distinct stages—reactive ReAct, workflow‑driven, autonomous, and self‑evolving—while dissecting how the six core modules (Prompt, Planning, Memory, Tools, Workflow, Environment) shift from model‑centric to engineered determinism.

AI AgentsAgent ArchitectureMemory

0 likes · 10 min read

From Reactive to Self‑Evolving: The Four‑Stage Evolution of AI Agents (2023‑2026)

AI Engineer Programming

Jun 9, 2026 · Artificial Intelligence

How Pi Works: Agent Architecture, Tools, Interactive UI, and Skills

The article breaks down Pi, a minimalist programming agent, explaining its two‑layer architecture, the iterative agent loop, a four‑tool set, extensible extensions, layered context construction, and reusable Skills, showing why a clear design, not tool count, determines an agent’s capability.

AI AgentAgent ArchitectureContext layering

0 likes · 6 min read

How Pi Works: Agent Architecture, Tools, Interactive UI, and Skills

Fun with Large Models

Jun 9, 2026 · Artificial Intelligence

Master AI Agents: 6 Essential GitHub Projects to Learn From

The article outlines a progressive learning path for AI agents, recommending six GitHub projects—from a beginner-friendly tutorial to production‑grade frameworks—detailing each project's purpose, difficulty, key takeaways, and suitable audience, helping programmers transition from users to builders.

AI AgentsAgent ArchitectureAgent Development

0 likes · 15 min read

Master AI Agents: 6 Essential GitHub Projects to Learn From

IT Services Circle

Jun 6, 2026 · Artificial Intelligence

How Claude Code’s Memory Mechanism Works: A Deep Dive into the Source Code

This article explains why LLMs are stateless, distinguishes short‑term from long‑term memory needs for agents, critiques common memory solutions, and then details Claude Code’s two‑layer architecture—static CLAUDE.md with six hierarchical files and a dynamic auto‑memory system that uses structured markdown, a lightweight selector model, and aging warnings—to provide a practical, source‑level blueprint for building robust agent memory.

Agent ArchitectureClaude CodeDynamic Memory

0 likes · 33 min read

How Claude Code’s Memory Mechanism Works: A Deep Dive into the Source Code

Data Party THU

Jun 3, 2026 · Artificial Intelligence

A Six‑Day, Million‑Token AI‑Driven Review Unpacks the L1‑L5 Agent Hierarchy

The article details how an AI‑augmented workflow completed a 46‑page research paper in six days using 108 agent calls and 648 k tokens, introduces an L1‑L5 autonomy taxonomy, compares four architectural patterns across 17 systems, and highlights six open challenges and key bottlenecks such as continual knowledge accumulation and reliable self‑assessment.

AI AgentsAgent ArchitectureBenchmark analysis

0 likes · 8 min read

A Six‑Day, Million‑Token AI‑Driven Review Unpacks the L1‑L5 Agent Hierarchy

James' Growth Diary

Jun 2, 2026 · Artificial Intelligence

Cross‑Session Retrieval with SQLite FTS5 and LLM Summaries – Hermes Agent’s Four‑Layer Architecture

This article dissects Hermes Agent’s four‑layer cross‑session retrieval system, covering persistent storage, dual‑table FTS5 indexing for CJK and English, a three‑path search strategy, intelligent truncation for LLM prompts, structured summarisation, and a holographic retrieval layer that blends FTS5, Jaccard similarity and HRR vector algebra.

Agent ArchitectureCross-Session RetrievalFTS5

0 likes · 25 min read

Architect

May 31, 2026 · Artificial Intelligence

Why Automating Low‑Quality Workflows with Hermes Agent Can Backfire

The article dissects Hermes Agent’s four‑layer architecture, warns that automating sloppy processes merely amplifies their flaws, and outlines practical governance steps—including stable input, output handling, failure logging, approval boundaries, memory budgeting, skill lifecycle, and self‑evolution evidence—to keep long‑running agents reliable and maintainable.

AI agent governanceAgent ArchitectureAutomation Risks

0 likes · 21 min read

Why Automating Low‑Quality Workflows with Hermes Agent Can Backfire

DataFunSummit

May 28, 2026 · Artificial Intelligence

How DataWorks Data Agent Advances from Augmented Assistance to Full Autonomy

The article analyzes DataWorks Data Agent’s evolution from a helper‑style tool to an autonomous data‑centric AI agent, detailing its five‑stage roadmap, dual‑engine CLI/Claw architecture, unified runtime kernel, open skill ecosystem, and CPU‑GPU joint optimization for enterprise‑grade data automation.

AIAgent ArchitectureData Agent

0 likes · 12 min read

How DataWorks Data Agent Advances from Augmented Assistance to Full Autonomy

AI Large-Model Wave and Transformation Guide

May 28, 2026 · Artificial Intelligence

Why AI Agent Architecture Mirrors 50 Years of OS Design

The article maps classic operating‑system concepts—processes, system calls, caching, file‑system mounting, and scheduling—to AI agents, showing how these analogies explain challenges like context sharing, tool permissions, token limits, knowledge‑base mounting, and orchestrated execution, and proposes a concrete multi‑layer design framework.

AI AgentsAgent ArchitectureContext Management

0 likes · 10 min read

Why AI Agent Architecture Mirrors 50 Years of OS Design

TechVision Expert Circle

May 26, 2026 · Industry Insights

Bridging the Technical Gap: From Microservices to Agent Architecture for CTOs

The article examines how the emerging Agent architecture, driven by large language models, disrupts traditional microservice control flow, observability, testing, and security, and offers a three‑phase roadmap for CTOs to transition their systems by 2026.

Agent ArchitectureCTO roadmapLLM

0 likes · 11 min read

Bridging the Technical Gap: From Microservices to Agent Architecture for CTOs

Design Hub

May 24, 2026 · Artificial Intelligence

How Claude’s New Memory System Turns AI Agents into Self‑Organizing Assistants

Claude’s latest memory and Dreaming features combine cross‑session memory, project workspaces, persistent memory files, and a background “Dreaming” organizer, shifting AI agents from forgetful bots to systems that selectively retain useful experience, reduce rework, and behave more like human assistants.

AI memoryAgent ArchitectureClaude

0 likes · 10 min read

How Claude’s New Memory System Turns AI Agents into Self‑Organizing Assistants

AI Step-by-Step

May 24, 2026 · Artificial Intelligence

Learning Agent Architecture from Giants: Blueprint of Hermes and Claude Code

The article breaks down a six‑layer agent architecture—entry, core loop, tool ecosystem, memory & learning, scheduling & orchestration, and output delivery—illustrating how Hermes and Claude Code implement each layer and offering guidance on choosing the right framework for specific needs.

AI AgentsAgent ArchitectureClaude Code

0 likes · 17 min read

Learning Agent Architecture from Giants: Blueprint of Hermes and Claude Code

DataFunSummit

May 22, 2026 · Artificial Intelligence

Why Memory Is the Bottleneck for AI Agents and How MemOS Achieves 200% Cloud Call Growth

The article analyses how memory has become the critical limitation for AI agents, details the MemOS framework’s five‑layer architecture that fuses model‑driven and application‑driven approaches, presents cloud service usage surging over 200%, and explains how these advances address scalability, privacy, and performance challenges in enterprise deployments.

AI memoryAgent ArchitectureCloud AI services

0 likes · 18 min read

Why Memory Is the Bottleneck for AI Agents and How MemOS Achieves 200% Cloud Call Growth

Tech Ocean

May 20, 2026 · Artificial Intelligence

Deep Agents Explained: Skills Manage Internals, MCP/A2A/ACP Manage Externals

The article maps the four core mechanisms of Deep Agents—Skills, MCP, A2A, and ACP—explaining how Skills governs internal agent behavior while the three protocols handle external tool integration, agent‑to‑agent collaboration, and client‑to‑agent communication, and offers guidance on when to adopt each layer.

A2AACPAgent Architecture

0 likes · 7 min read

Deep Agents Explained: Skills Manage Internals, MCP/A2A/ACP Manage Externals

AI Engineer Programming

May 17, 2026 · Artificial Intelligence

ReAct, Plan‑Execute, and Reflection: How Continuous Loops Make Agent Architecture Crucial

While a single LLM call is a stateless function, real‑world tasks require dynamic information gathering, hypothesis testing, and iterative refinement, so agents must operate in a continuous loop; the article analyzes core patterns such as ReAct, Plan‑Execute, Reflection, Multi‑Agent and HITL, highlighting state management, cost, debugging, and observability challenges.

Agent ArchitectureLLMMulti-agent

0 likes · 21 min read

ReAct, Plan‑Execute, and Reflection: How Continuous Loops Make Agent Architecture Crucial