Tagged articles
task decomposition
35 articles · Page 1 of 1
This article analyzes how AI shifts from boosting individual productivity to reshaping organizational work systems, proposing a four-layer model—task decomposition, context management, governed execution, and feedback loops—to help enterprises convert isolated AI capabilities into reliable, reusable collective intelligence.
AI governanceAI organization designR&D management
0 likes · 38 min read

Anthropic deployed 750 Claude agents to formalize the toughest step of Fermat's Last Theorem in Lean, using a shared database and Git to coordinate 2,418 tasks, ultimately verifying 54 of 60 propositions and showcasing scalable multi-agent proof engineering.
AI agentsAnthropicClaude
0 likes · 14 min read

Anthropic deployed 750 AI agents to formalize Fermat's Last Theorem in Lean, concentrating on the Langlands–Tunnell theorem bottleneck, using a shared Postgres database and Git for coordination, decomposing the proof into 2,418 tasks, and completing 54 of 60 propositions in 28.7 hours.
AI coordinationAnthropicFermat's Last Theorem
0 likes · 11 min read

Anthropic deployed 750 AI agents to formalize the proof of Fermat's Last Theorem in Lean, overcoming the Langlands–Tunnell theorem bottleneck by decomposing the proof into 2,418 tasks coordinated via a shared database and Git, completing 54 of 60 propositions in 28.7 hours.
AI agentsAnthropicFermat's Last Theorem
0 likes · 15 min read

This article demonstrates how to translate mission tasks into concrete engineering threads by assigning specific people, tools, and actions to each step, using a coffee-making example to expose resource contention, handoff gaps, and the difference between paper parallelism and real-world feasibility.
Execution PlanningHandoff VerificationMEG 2.0
0 likes · 22 min read

This article uses hand-drip coffee as a case study to demonstrate mission engineering task analysis: decomposing tasks, specifying inputs/outputs/start conditions/completion criteria for each step, linking dependencies via quality gates, handling missing items, and distinguishing material independence from resource contention, all while remaining implementation-agnostic.
Coffee Case StudyDependency MappingImplementation-Agnostic Design
0 likes · 16 min read


ArchitectSep 18, 2026 · Artificial Intelligence
Anthropic's 11-day project formalizing Fermat's Last Theorem in Lean with 30,000 machine-checked theorems exposes five critical patterns for multi-agent systems: verifiable artifacts, dynamic task graphs, evidence-based planning, verification-gated state changes, and recoverable execution state.
Fermat's Last TheoremLean theorem proverProve2Me
0 likes · 26 min read


ArchitectSep 12, 2026 · Artificial Intelligence
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

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

This article presents a comprehensive framework for effective AI interaction, detailing a six-component prompt structure, task decomposition strategies, JSON output stabilization techniques, and a reusable template to transform vague requests into verifiable, production-ready results through iterative alignment and validation.
AI interactionAI reliabilityJSON output
0 likes · 20 min read

The article demonstrates how the pyramid principle — conclusion-first, categorized grouping, and layered decomposition — turns vague client requests into structured, verifiable AI prompts, using a contract bulk-import example to show a four-level breakdown from delivery conclusion to executable tasks.
AI collaborationAI promptingacceptance criteria
0 likes · 21 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

The article argues that AI development pipelines should not automate everything from requirement to production, but instead establish a governed delivery system with eight stages—requirement specification, task decomposition, parallel development, automated verification, code review, integration testing, pre-release acceptance, and production release—where quality gates and human decisions ensure reliability over speed.
AI development pipelineautomated verificationcode review
0 likes · 19 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

This article reviews a Berkeley PhD thesis that argues powerful foundation models still need task decomposition, detailing six contributions—including LLM‑grounded diffusion, video diffusion, self‑correcting loops, detailed local description, adaptive parallel reasoning, and ThreadWeaver—to organize computation across multiple agents for more controllable, reliable AI systems.
AI systemsLLMmulti-agent systems
0 likes · 16 min read

The article analyzes the growing “Skill Hell” problem in AI agent engineering—where excessive rules and redundant skills overload context—and presents Matt Pocock’s step‑by‑step methodology for classifying triggers, streamlining skill documents, using concise leading words, splitting tasks, and applying a deletion test to create lean, reliable agent skills.
AI AgentContext ManagementPrompt Engineering
0 likes · 12 min read

After OpenAI released GPT-5.5, researcher VittoStack claimed a successful jailbreak using suffix triggers and task decomposition, prompting a split reaction in the security community over technical feasibility, potential misuse, and responsible disclosure practices.
AI securityGPT-5.5VittoStack
0 likes · 5 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


ArchitectMay 27, 2026 · Artificial Intelligence
The article analyses Claude Code's new parallel‑working features—Subagents, Agent View, and Agent Teams—explaining when each should be used, how to break engineering work into clear boundaries, manage permissions and budgets, gather verifiable evidence, and avoid hidden coordination costs in real projects.
AI codingAgent TeamsClaude Code
0 likes · 23 min read

The article argues that as AI coding agents evolve from autocomplete to task‑level assistants, developers’ most valuable skill shifts from writing code to orchestrating context, breaking down tasks, defining boundaries, and managing agents within the software production workflow.
AI programmingcoding agentscontext engineering
0 likes · 11 min read

The article explains that a production‑grade business agent must combine LLM‑driven intent understanding with deterministic rule‑based control, using a perception‑understanding‑planning‑execution‑feedback loop, two‑round prompting, strict JSON schemas, permission checks, and a state‑machine architecture to avoid unsafe, uncontrolled behavior.
Agent ArchitectureBusiness AgentLLM
0 likes · 23 min read

The article explains why many AI product managers struggle with multi‑agent concepts, outlines the three structural bottlenecks a single agent faces, shows how task decomposition and specialized agents improve quality, and provides concrete product‑design decisions—including orchestration, context passing, failure handling, and human‑in‑the‑loop—to determine when multi‑agent architectures are appropriate.
AI Product Managementmulti-agentorchestration
0 likes · 16 min read


FunTesterApr 20, 2026 · Artificial Intelligence
The article analyzes why letting the same AI Agent generate and self‑evaluate results in over‑confident but flawed outputs, especially for subjective tasks, and proposes a three‑stage multi‑agent architecture with independent evaluation, concrete standards, and prompt‑based calibration to improve reliability as models evolve.
AIPrompt EngineeringSelf-Evaluation
0 likes · 9 min read

The article outlines a practical SOP that transforms AI agents from passive responders to autonomous executors by introducing task decomposition, exception handling, and human‑in‑the‑loop audit checkpoints, enabling organizations to supervise multi‑model collaborations while avoiding chaos and ensuring alignment with business goals.
AI workflowAgent orchestrationhuman-in-the-loop
0 likes · 6 min read

The article explains why routing every request to the most powerful LLM hurts cost, speed, and throughput, and presents a three‑layer task decomposition that assigns execution‑level tasks to cheap small models, intermediate tasks to mid‑size models, and high‑risk judgment tasks to large models, with concrete examples and a minimal routing strategy.
Cost OptimizationLLMagent design
0 likes · 8 min read

The article analyzes how multi‑agent systems emulate human team dynamics through role specialization, structured handoffs, and cross‑validation, detailing the orchestration layer’s responsibilities—task decomposition, dependency‑graph scheduling, routing, and conflict resolution—while exposing common pitfalls, cost concerns, and framework choices.
LLM cost controlState Managementcommunication protocols
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

This lesson explains how to extend a single‑agent system with multi‑agent collaboration, covering context isolation, Handoff and Router patterns, flat coordinator architecture, code examples, task decomposition, and practical run‑time demos for building complex AI workflows.
AICoordinatorLLM
0 likes · 20 min read

This article provides a comprehensive guide to AI Agent planning modules, covering their core responsibilities, architectural designs, major planning paradigms such as ReAct, Plan‑and‑Execute, Hierarchical Planning and Reflexion, detailed prompt engineering, execution frameworks, and practical case studies in data analysis and intelligent customer service.
AI planningAgent ArchitecturePrompt Engineering
0 likes · 25 min read

The article discusses how defining clear problem boundaries is essential for AI agents, explains the challenges of vague tasks for large language models, and proposes multi‑stage decomposition, self‑reflection, and human‑in‑the‑loop strategies to improve AI performance on complex, dynamic tasks.
AIAgent Architecturehuman-AI collaboration
0 likes · 13 min read

This guide explains how effective communication with AI—through clear prompts, step‑by‑step task breakdowns, and critical‑thinking techniques—can unlock deeper reasoning, avoid hallucinations, and boost personal productivity across various work scenarios.
AI promptingCritical ThinkingDeepSeek
0 likes · 18 min read

The article explains OpenAI's 2020 Scaling Laws that show larger transformer models, more data, and greater compute consistently improve performance, introduces the concept of emergent abilities at critical size thresholds, and outlines the core principles of parallel computing such as multi‑processor usage, task decomposition, concurrent execution, and inter‑processor communication.
Scaling Lawscommunicationconcurrency
0 likes · 6 min read


ITPUBOct 20, 2023 · Artificial Intelligence
This article shows programmers how to harness ChatGPT beyond simple Q&A by using advanced prompting techniques for knowledge summarization, task decomposition, code reading, refactoring, generation, unit‑test creation, and plugin integration, turning AI into a practical development assistant.
AI for developersChatGPTPrompt Engineering
0 likes · 18 min read

The article shows how developers can transform ChatGPT from a simple Q&A bot into a powerful productivity assistant by mastering prompt engineering and applying it to tasks such as technical document summarization, task decomposition, code reading, optimization, generation, unit‑test creation, and plugin integration, thereby augmenting their workflow.
AIChatGPTDeveloper Tools
0 likes · 18 min read


转转QAAug 5, 2022 · Operations
This article explains how to improve overall delivery efficiency by systematically breaking down testing tasks, setting realistic schedules based on clear goals, preparation steps, granular time estimates, dependency considerations, and post‑execution reviews, while emphasizing a target testing effort not exceeding half of development time.
Process ImprovementQAScheduling
0 likes · 7 min read
