Skip to content
Tagged articles

R&D automation

7 articles · Page 1 of 1
Smart Era Software Development
Smart Era Software Development
Nov 12, 2026 · R&D Management

Multi-Agent R&D Pipeline: 3 Human Gates, 335 Reqs Delivered in 106-Min Median

Tencent's Social Security Center built a multi-agent end-to-end delivery platform that processes production requirements through nine automated stages with humans only confirming at three gates (requirement review, technical design, acceptance), achieving 335 deliveries with a 106-minute median cycle time and zero production incidents, using structured Specs, state machines, quality gates, and a knowledge base to eliminate handoff losses and context gaps.

AI in software engineeringR&D automationend-to-end delivery
0 likes · 35 min read
Multi-Agent R&D Pipeline: 3 Human Gates, 335 Reqs Delivered in 106-Min Median
Alibaba Cloud Native
Alibaba Cloud Native
Oct 14, 2026 · R&D Management

15 Agents Form an R&D Squad: End-to-End Multi-Agent Collaboration for Software Delivery

The article describes how 15 specialized agents organized via AgentCore collaborate across the full software delivery lifecycle, while AgentLoop continuously improves the team by analyzing execution traces, enabling offline benchmarking against expert commits and online experience accumulation, reducing delivery cycle from a month to a week in a constrained scenario.

AI agentsAgentCoreAgentLoop
0 likes · 12 min read
15 Agents Form an R&D Squad: End-to-End Multi-Agent Collaboration for Software Delivery
JD Tech Talk
JD Tech Talk
Sep 23, 2026 · R&D Management

JD Haibo's AI-Native Knowledge Base: 3-Layer Architecture, OKF Spec & 44% Faster Dev

JD Haibo built a three-layer AI knowledge base (project-domain matrix, role-specific views, executable skills) using the OKF specification, auto-generating structured docs from code, integrating with Harness for context-aware AI assistance, and validating via AB tests showing 44% faster requirement analysis with better coverage.

AI NativeHarnessOKF Specification
0 likes · 35 min read
JD Haibo's AI-Native Knowledge Base: 3-Layer Architecture, OKF Spec & 44% Faster Dev
Infinite Tech Management
Infinite Tech Management
Jul 14, 2026 · R&D Management

How Close Are We to an Autonomous AI‑Native Development Pipeline?

The article examines why AI‑assisted coding speeds up individual developers yet fails to shorten end‑to‑end delivery, proposes an issue‑driven automation platform called IssueOps, outlines four AI coding maturity levels, discusses risk boundaries, tool choices, and evaluates how far organizations are from achieving a fully autonomous L4 development pipeline.

AI OpsDevOpsIssue-driven automation
0 likes · 16 min read
How Close Are We to an Autonomous AI‑Native Development Pipeline?
phodal
phodal
Apr 14, 2026 · R&D Management

How Multi‑Agent AI Redefines Development: The Harness‑Powered Routa Workbench

Routa demonstrates how combining a Harness‑style engineering framework, AI‑driven Coding Agents, and a Kanban‑based task protocol can transform software development into an automated, collaborative workbench, redefining the Definition of Done, enforcing quality gates, and orchestrating multi‑agent handoffs across the entire lifecycle.

AI agentsKanbanR&D automation
0 likes · 12 min read
How Multi‑Agent AI Redefines Development: The Harness‑Powered Routa Workbench
Data Thinking Notes
Data Thinking Notes
Aug 6, 2024 · Artificial Intelligence

How Large Language Models Are Revolutionizing R&D Operations and Telecom Networks

Large language models are increasingly applied in research and development operations, boosting efficiency and automating processes such as coding assistance, testing, requirement analysis, documentation, knowledge management, and network traffic analysis, while also enhancing security and enabling intelligent transformation across industries, especially telecom.

AI in telecomR&D automationlarge language models
0 likes · 3 min read
How Large Language Models Are Revolutionizing R&D Operations and Telecom Networks