Tagged articles
parallel execution
63 articles · Page 1 of 1
DeepSeek Harness adds a workflow subsystem where models write JavaScript orchestration scripts to fan out tasks to parallel sub-agents via five hooks (agent, parallel, pipeline, phase/log), replacing serial delegation with a replayable script that returns a single JSON result, though it remains a synchronous developer preview with high token usage and no resume or timeout controls.
AI codingDeepSeek HarnessWorkflow
0 likes · 7 min read


Geek LabsAug 29, 2026 · Artificial Intelligence
PASEO provides a daemon‑plus‑client architecture that lets developers schedule, monitor, and control various AI coding agents such as Claude Code, Codex, and Copilot from a single UI on desktop, web, CLI, or mobile, enabling parallel orchestration, cross‑device visibility, and privacy‑first execution.
Paseoai-coding-agentscross-device
0 likes · 12 min read

The article explains that effective multi-agent collaboration requires identifying dependencies first, then decomposing tasks into four types (exploration, contract, implementation, integration), following four principles (independent boundaries, explicit inputs, verifiable outputs, controllable conflicts), and executing in four phases (contract-first, independent parallel, unified integration, system verification), illustrated with a batch import example.
AI agent coordinationDependency ManagementR&D management
0 likes · 19 min read

This lesson walks through configuring the cmux session manager, the superpowers skill‑sharing layer, and the OpenClaw orchestration engine to enable multiple AI agents to work in parallel, avoid serial bottlenecks, and coordinate their outputs through isolated worktrees and unified reporting.
AI orchestrationGit WorktreeOpenClaw
0 likes · 13 min read

The article argues that AI agents are transforming specialized development roles into unified delivery owners who orchestrate multiple agents to achieve business goals, requiring skills in task decomposition, parallel scheduling, multi-layer result review, and quality control rather than just coding.
AI agentsDelivery OwnershipQuality Control
0 likes · 19 min read

The article explains that Graph Engineering isn’t a brand‑new concept but an evolution of Prompt, Loop, and Harness engineering, detailing how LangGraph has been used for three years, the core components of graph‑based agents, practical patterns, pitfalls, and when to choose graphs over other approaches.
AI workflowAgent GraphsGraph Engineering
0 likes · 13 min read

The article explains how traditional Loop Engineering for AI agents is being replaced by Graph Engineering, detailing nodes as tasks, edges as data contracts, parallel execution, barriers, validation, isolation, dynamic workflows, and cost‑effective topology design for scalable agentic systems.
AI agentsAgent ContractsClaude
0 likes · 19 min read

SwarmAgent evolves from a conceptual multi-agent template into a verifiable MVP by implementing true parallel execution, reliable result passing, standard MCP compliance, security boundaries, and comprehensive contract tests, while honestly documenting its current limitations.
MCPMVPSwarmAgent
0 likes · 11 min read

The article analyzes why AI agents quickly consume token quotas and presents seven practical strategies—shortening sessions, avoiding parallel sub‑agents, giving concise prompts, providing precise context, pre‑defining rules, automating mechanical tasks, and investing in clear prompts—to dramatically reduce token usage and lower operational costs.
AI agentsautomationparallel execution
0 likes · 10 min read

The article explains how Hermes' sub‑agent delegation transforms a serial, context‑heavy workflow—such as researching multiple vector databases—into parallel, isolated sub‑tasks, detailing three‑layer isolation, orchestrator role, heartbeat monitoring, approval safety, credential handling, and compares industry approaches.
AI agentsHermesOrchestrator
0 likes · 18 min read

The article compares OpenAI's Codex and Anthropic's Claude Code across architecture, token efficiency, benchmark scores, feature sets, installation steps, and real‑world use cases, helping developers decide which tool aligns with their workflow, security preferences, and budget.
AI coding assistantBenchmarkClaude Code
0 likes · 16 min read

The article explains how LLM context windows are a scarce resource plagued by breadth‑vs‑depth, long‑task attention decay, and serial‑parallel trade‑offs, and proposes task atomization—splitting work into independently loadable, executable, and verifiable units with isolated contexts and parallel sub‑agents—to achieve clean context, local rollback, and scalable performance.
AI workflowLLM contextmicroservice analogy
0 likes · 16 min read

This article explains the concept of Function Calling in large language models, walks through defining function schemas, shows step‑by‑step API call flows, demonstrates multi‑tool orchestration, parallel execution, tool‑chain composition, and integrates Function Calling with LangChain, while providing best‑practice guidelines and code examples.
AI agentsBest PracticesFunction Calling
0 likes · 16 min read

The article analyzes the limitations of Claude Code's monolithic execution, introduces a JavaScript‑based dynamic workflow system with two core APIs, and details six reusable patterns—Classify‑and‑Act, Fan‑out‑and‑Synthesize, Adversarial Verification, Generate‑and‑Filter, Tournament, and Loop‑until‑Done—along with concrete use cases, trade‑offs, and practical tips.
AI agentsClaude CodeJavaScript
0 likes · 11 min read

Claude Code introduced dynamic workflows on May 28, 2026, enabling the AI to automatically decompose tasks, run dozens to hundreds of sub‑agents in parallel, and cross‑validate results, which acts like a project manager and can cut multi‑hour jobs down to minutes while offering guidance on when to use or avoid the feature.
AI automationClaude Codedynamic workflows
0 likes · 9 min read

Claude’s new Dynamic Workflows move planning and coordination out of the chat context into executable JavaScript, enabling hundreds of parallel sub‑agents, adversarial verification, and checkpoint recovery, which the article demonstrates with a Bun migration case study, a novel‑generation workflow, and detailed architectural analysis.
AI agentsClaudeadversarial verification
0 likes · 32 min read

GitHub Copilot CLI’s /fleet command turns the AI assistant into an orchestrator that splits a large task into parallel subtasks, runs multiple agents with separate context windows, and aggregates the results, letting a single developer modify several files, run tests, and update documentation simultaneously.
AI orchestrationCLIDeveloper Productivity
0 likes · 6 min read

This article dissects LangGraph's core execution engine, showing how it transforms LLM calls into a state‑machine workflow with mutable State, Nodes, Edges, Reducers, a scheduler loop, conditional branching, and parallel fan‑out/fan‑in execution.
JavaScriptLLMLangGraph
0 likes · 12 min read

StreamingVLA introduces action‑flow matching and adaptive early observation to parallelize generation, execution, and perception in vision‑language‑action models, cutting per‑action latency from 49.9 ms to 31.6 ms, reducing stall time 6.5‑fold, and achieving up to 2.4× end‑to‑end speedup in LIBERO benchmarks and real‑world robot tests.
LIBEROStreamingVLAlatency
0 likes · 13 min read

This guide explains how to install the Spatie Fork package, meet its requirements, and use its run, before, after, and concurrent methods to execute multiple PHP closures in parallel within CLI environments, including handling return values and database connections.
CLIConcurrencyPHP
0 likes · 7 min read

This article analyzes the trade‑offs between single‑agent and multi‑agent large language model architectures, identifies three scenarios where multi‑agent setups excel, explains context protection, parallelism and tool specialization, and provides concrete design patterns, code examples, and verification strategies to avoid common pitfalls.
Agent Orchestrationcontext managementmulti-agent systems
0 likes · 17 min read

This article analyzes the challenges of using AI coding agents for large‑scale, long‑running tasks such as bulk file migration or code review, and presents a systematic engineering approach—including task decomposition, parallel execution, persistent progress files, resumable workflows, and multi‑level retry strategies—backed by concrete script examples and real‑world case studies.
AI agentsMeta Skillparallel execution
0 likes · 31 min read

The article explains that multi-agent systems typically operate in three patterns—sequential execution, parallel execution, and an evaluator-optimizer loop—covers when each pattern is appropriate, and offers interview tips on how to discuss these designs effectively.
AI InterviewEvaluator-optimizerSequential Execution
0 likes · 3 min read

This article dissects the shortcomings of single‑agent LLM pipelines, introduces the Supervisor‑based Multi‑Agent architecture with LangGraph, demonstrates parallel task execution, robust error handling, and result merging, and provides concrete interview guidance backed by real performance data.
AI ArchitectureLLMLangGraph
0 likes · 19 min read

This guide explains how to decompose a software project, schedule specialist AI agents, run them in parallel, and integrate their outputs, using OpenClaw and Sisyphus to build a full‑stack blog system and a user‑authentication service while covering best‑practice patterns, monitoring, and troubleshooting.
AI orchestrationOpenClawmulti-agent collaboration
0 likes · 18 min read

In eight days the author used a recursively evolving AI agent orchestrator to generate 40,000 lines of TypeScript, 17 plugins, and 3,288 tests, demonstrating parallel task decomposition, self‑healing CI, and a fully pluggable architecture that automates code review and deployment.
AI agentsAgent OrchestrationCI automation
0 likes · 16 min read

This article explains how sharding a knowledge base and using decentralized retrieval can boost the reliability, precision, and latency of AI agents, providing code examples, a LangGraph workflow, and a performance comparison that shows a 28% speed gain over a monolithic setup.
AI agentsLangChainRAG
0 likes · 12 min read

Oh‑My‑OpenCode replaces a single AI coder with six specialized agents—Sisyphus, Oracle, Explore, Librarian, Visual Engineering, and Writing—automating task decomposition, parallel execution, and expert analysis, delivering 3‑8× speedups across code understanding, bug fixing, refactoring, documentation, and full‑stack development, as shown in real‑world case studies.
AIAgentsOh-My-OpenCode
0 likes · 20 min read

This article walks through a reliability‑focused design pattern for agentic AI—competitive agent ensembles—by initializing diverse LLMs, defining structured Pydantic models, creating parallel competitor nodes, evaluating their outputs with a judge node, and demonstrating a 63% speedup and higher quality results.
Agentic AILLMLangChain
0 likes · 14 min read

This article presents the hierarchical agent‑group design pattern for reliable agentic AI, explains how specialized orchestrator and executor agents exchange structured Pydantic data, demonstrates a LangGraph workflow, and shows that the hierarchical approach yields faster execution (13.57 s vs 18.34 s) and higher‑quality reports compared with a monolithic agent.
Agentic AILangGraphhierarchical agents
0 likes · 15 min read

This article demonstrates how a competitive ensemble of diverse LLM agents—Claude 3.5 Sonnet and two Llama 3 variants—combined with a structured evaluation node can improve both output quality and execution speed in agentic AI systems, using LangGraph, Pydantic models, and parallel execution.
LLMLangGraphPydantic
0 likes · 13 min read

This article presents a hierarchical agent‑group design pattern that improves the reliability of agentic AI systems, explains its specialized executor agents, shows how structured Pydantic models and LangGraph orchestrate parallel execution, and compares its speed and report quality against a monolithic agent on an investment‑report task.
Agentic AILangGraphPerformance Analysis
0 likes · 14 min read

This article explains how the easy‑agent project evolved from a single monolithic AI into a multi‑agent architecture with specialized Foreman, Coder, and Researcher agents, covering design principles, communication mechanisms, task decomposition, fault tolerance, parallel execution, observability, and future extensions, complete with code examples and open‑source links.
AIGoOpenTelemetry
0 likes · 13 min read

This article explains the motivation behind LangGraph, walks through a quick start, details its core syntax and state management, demonstrates conditional branching, parallel execution, tool integration, multi‑agent orchestration, and real‑time monitoring, and finally discusses future directions for the framework.
LLMLangGraphPython
0 likes · 32 min read

The article compares Selenium and Playwright for web automation, showing how Playwright’s multi‑browser support, smart waiting, session persistence, headless stability, PDF export, and parallel testing make it a more reliable and efficient choice for robust automation tasks.
Headless TestingPlaywrightparallel execution
0 likes · 8 min read

This article explores how Hu Jia‑chun and the Huolala testing team tackled the exploding complexity of mobile app testing across Android, iOS, and HarmonyOS by applying task decomposition, parallel execution, cloud‑based device farms, OCR‑driven precise control, and custom multi‑device synchronization tools to dramatically improve coverage and speed.
OCR automationcloud testingmobile testing
0 likes · 22 min read

This article explains how to configure XXL‑JOB with a sharding‑broadcast strategy in a SpringBoot application, use ID modulo hashing to partition large tables, implement the task with XxlJobHelper, write MyBatis sharding SQL, and verify correct parallel processing through detailed logs.
MyBatisShardingSpringBoot
0 likes · 7 min read

This article introduces AsyncTool, a Java concurrency framework that enables flexible parallel, serial, dependent, and callback‑driven task orchestration, explains its core components (worker, callback, wrapper), and provides multiple code‑first examples illustrating complex workflow compositions.
Callbackasyncparallel execution
0 likes · 9 min read

The article explains how to dramatically reduce the response time of an API that must call multiple downstream services by converting serial calls into parallel ones using Java 8's CompletableFuture, covering its relationship to Future, core APIs, task composition, exception handling, and practical best‑practice recommendations.
Asynchronous ProgrammingCompletableFutureConcurrency
0 likes · 20 min read

This comprehensive guide explains Java's CompletableFuture API, covering its fundamentals, creation methods, chaining operations, exception handling, and best practices for parallel execution, while providing clear code examples and performance tips for building efficient asynchronous workflows in backend development.
Asynchronous ProgrammingCompletableFutureConcurrency
0 likes · 20 min read

This guide shows how to enhance Bash scripts with text‑based animations, local GUI notifications, parallel task execution, simple GUI dialogs, and styled terminal output using built‑in commands and utilities like printf, notify‑send, zenity, and tput.
animationbashgui notification
0 likes · 9 min read

The article introduces Alibaba Cloud's Graph Database (GDB), detailing its product features, supported query languages, high‑performance and high‑availability architecture, parallel execution engine based on the Volcano model and Morsel‑driven parallelism, and showcases real‑world use cases such as DingTalk friend recommendation and Hema Fresh recommendation.
Alibaba CloudDatabase ArchitectureMorsel Parallelism
0 likes · 10 min read

This article details a novel approach to overcoming CPython's Global Interpreter Lock by implementing a multi-interpreter architecture that isolates execution states, manages shared variables through thread-specific data, and introduces a subinterpreter pool to significantly enhance multi-core CPU utilization and algorithm execution performance.
CPythonConcurrencyGIL Optimization
0 likes · 15 min read


Code DAODec 11, 2021 · Artificial Intelligence
The article analyzes how Nimble reduces GPU scheduling overhead and enables parallel execution through ahead‑of‑time scheduling and automatic multi‑stream assignment, achieving up to 22.3× inference speedup over PyTorch and significantly improving GPU utilization for deep learning workloads.
GPU schedulingPerformance Accelerationahead-of-time
0 likes · 9 min read


ITPUBJun 9, 2021 · Databases
This article walks through using ADDM to pinpoint problematic SQL statements in Oracle, creating and executing a SQL Tuning Advisor task, evaluating profile and index recommendations, and applying parallel execution to dramatically improve performance and resource usage.
ADDMOracleSQL Tuning Advisor
0 likes · 11 min read

This article explains how cloud databases use cost‑based parallel query engines to overcome I/O bottlenecks, select tables for parallel scans, implement parallel joins and aggregations, and achieve linear speedups on TPCH benchmarks, highlighting the key techniques and architectural components.
Cloud DatabaseParallel QuerySQL Performance
0 likes · 13 min read

The article explains how designing atomic automation test cases—each focusing on a single function with minimal UI interaction—provides precise feedback, shortens test chains, improves coverage, enables parallel execution, and offers practical strategies for data injection and handling non‑testable applications.
UI testingatomic test casesautomated testing
0 likes · 8 min read

This article explains Hive performance tuning techniques, including enabling parallel execution, configuring strict mode to prevent risky queries, reusing JVMs to reduce overhead, and using speculative execution to mitigate slow tasks, with configuration examples and practical considerations.
HiveJVM ReusePerformance Tuning
0 likes · 8 min read

A production Oracle database suddenly ran queries with an excessively high degree of parallelism, prompting a DBA to investigate, discover an unexpected SYS‑owned SQLPROFILE as the root cause, and reflect on the need for stricter operational oversight.
DBAOracleSQLPROFILE
0 likes · 5 min read

This guide explains how to evaluate the return on investment of Selenium‑based cross‑browser test automation by defining key metrics, outlining calculation formulas, discussing common pitfalls, and offering practical steps to maximize efficiency, coverage, and risk reduction.
ROITest AutomationTesting Metrics
0 likes · 18 min read

This article explains how to set up a Windows environment with Node.js, Python, and Appium, dynamically generate desired capabilities for multiple phones, launch parallel Appium services and tests using multi‑process techniques, and handle port detection and release to achieve efficient multi‑device automation.
AppiumPythonautomation
0 likes · 5 min read

This article demonstrates how to efficiently remove duplicate rows from a million‑record MySQL table by comparing created_time and item_name, exploring various approaches such as correlated subqueries, joins, user‑defined variables, index optimization, window functions, and parallel execution with shell scripts and MySQL events to achieve significant performance gains.
MySQLSQL PerformanceWindow Functions
0 likes · 21 min read


ITPUBNov 24, 2018 · Databases
This article walks through diagnosing unexpected Oracle parallel execution, resolving DBLINK‑induced plan anomalies after a database upgrade, and fixing ORA‑00604 errors caused by missing domain indexes, providing step‑by‑step queries, parameter checks, and corrective ALTER statements to restore normal performance.
DBLINKDomain IndexOracle
0 likes · 12 min read

This article introduces asynchronous programming concepts, focusing on Promise-style APIs, their differences from synchronous and callback approaches, and practical usage patterns in backend development.
Asynchronous ProgrammingCompletableFutureListenableFuture
0 likes · 17 min read

EOS.IO introduces a novel blockchain architecture that combines delegated proof‑of‑stake consensus, OS‑like account and permission models, deterministic parallel transaction execution, and flexible resource and governance mechanisms, enabling million‑user scale, low‑latency, fee‑free decentralized applications while addressing security, upgradeability, and cross‑chain communication.
DPOSEOSIOgovernance
0 likes · 36 min read


ITPUBFeb 10, 2018 · Operations
This guide explains why serial shell loops become a bottleneck for large‑scale tasks, then demonstrates three pure‑bash techniques—background execution, a simulated queue using arrays, and a FIFO‑based token system—to run multiple loop iterations concurrently while controlling the number of active processes.
FIFObashparallel execution
0 likes · 12 min read

The article describes how a Python‑based nosetests framework was extended with a Master‑Runner architecture and pyzmq messaging to run test cases in parallel across multiple runners, reducing execution time from over ten minutes to just a few minutes and enabling fast feedback in CI/CD pipelines.
CI/CDPythonTest Automation
0 likes · 9 min read

This article explains the theory behind SQL Server's parallel execution, illustrates its performance gains with Amdahl's Law, lists operators that block parallelism, discusses configuration settings, warns of deadlocks and thread starvation, and presents practical MapReduce‑style optimizations for real‑world workloads.
Amdahl's LawMapReducePerformance Tuning
0 likes · 16 min read

This article introduces Fabric, a Python-based automation tool for server management and application deployment, explains its core features, showcases real-world use cases like Instagram, and provides step‑by‑step code examples covering basic commands, parameter passing, local and remote execution, role‑based tasks, parallel execution, and installation instructions.
FabricPythonparallel execution
0 likes · 7 min read


ITPUBApr 22, 2016 · Databases
This article explains Oracle's parallel execution features—including parallel query, DML, and DDL—covers object, session, and statement level settings, provides practical SQL examples, discusses common pitfalls, and presents performance test results that demonstrate significant speed improvements for large data migration tasks.
OraclePerformance TuningSQL
0 likes · 10 min read

This article explains Oracle's parallel query feature, covering its benefits, resource costs, required conditions, various data‑distribution methods such as broadcast, replicate and hash, how to read parallel execution plans, and practical monitoring techniques to avoid performance pitfalls.
Database PerformanceHash JoinOracle
0 likes · 31 min read

This guide explains Oracle Real‑Time SQL Monitoring, covering terminology, activation conditions, how to access it via Enterprise Manager Cloud Control, and detailed walkthroughs of its various panels, metrics, and practical examples for diagnosing and optimizing long‑running queries and index builds.
DBAOraclePerformance Tuning
0 likes · 29 min read

In this detailed DBA case study, the speaker explains how improper settings of Oracle's parallel execution parameters on an AIX‑based 10gR2 database led to process saturation, undo‑related wait events, and temporary connection issues, and describes the step‑by‑step diagnosis, parameter adjustments, and lessons learned for future tuning.
AIXOracleParallel Parameters
0 likes · 12 min read
