4The Batch (DeepLearning.AI)·
Andrew Ng on iterative spec-driven agentic coding loops for 0-to-1 prototyping
Andrew Ng shares a practical methodology for using agentic coding loops in rapid prototyping, centered on the principle that AI tokens are cheap while human input is precious. He advocates for starting with an imperfect spec, letting the agent build a prototype quickly, and iterating on the spec based on what the agent produces rather than front-loading design time. He also recommends having agents persist key decisions in files like SPEC.md to combat context/memory loss across long sessions.
Related guides (3)
Related events (8)
Andrew Ng outlines three-loop framework for agentic software development
Andrew Ng describes a 'loop engineering' framework for building software with AI coding agents, comprising an agentic coding loop (agent writes/tests/iterates autonomously), a developer feedback loop (human steers at higher product level), and an external feedback loop (user testing, A/B). The piece contextualizes the buzzphrase popularized by Claude Code creator Boris Cherny and OpenClaw creator Peter Steinberger. Ng argues humans retain a 'context advantage' over AI systems that justifies continued human-in-the-loop involvement in product decisions.
AI-Native Software Development Needs Generalists
Andrew Ng argues that agentic coding tools are reshaping software team structures by accelerating code production so dramatically that product management, design, marketing, and legal review become the new bottlenecks. He contends that the fastest-moving teams are small (2–10 people), co-located, and composed of generalists who can span engineering, product, and other functions. The piece frames this as a structural shift away from large specialist teams toward individuals who combine deep skills with cross-functional breadth.
Claude Code and What Comes Next
A commentary piece from One Useful Thing examining Claude Code and its implications for AI-assisted software development. The author reflects on what agentic coding tools can accomplish with the right scaffolding and considers near-term trajectories. Published in early January 2026, this represents a tier-2 analyst perspective on Anthropic's coding agent product.
Latent Space: Skill engineering and the case against one-shot AI design
Paul Bakaus discusses 'skill engineering' as a design philosophy for AI-assisted workflows, arguing against fully automated one-shot AI pipelines in favor of keeping humans in the loop. The conversation centers on Impeccable, a tool or approach Bakaus is developing, and the concept of 'loopmaxxing' — iterative human-agent collaboration cycles. The piece addresses why current agents still require human steering to produce high-quality outputs.
Introspection co-founder explains autoresearch and self-improving agent loops
Roland Gavrilescu, co-founder of Introspection, discusses the concept of 'autoresearch' — a feedback loop enabling AI agents to iteratively improve themselves — in a Latent Space interview. The conversation covers agent 'recipes,' self-improving loops, and the continued role of humans in what Gavrilescu frames as a software factory paradigm. The piece offers a practitioner-level view of how agentic research pipelines are being designed and operationalized.
Claude Code, Codex and Agentic Coding #8
Zvi Mowshowitz's eighth installment in his ongoing series tracking the agentic coding landscape, covering developments around Claude Code and OpenAI Codex. As a tier-2 commentary source, the piece synthesizes recent progress and trends in coding agents. The series has been running since the initial wave of excitement around coding agents.
The Batch Issue 359: Loop Engineering for Agentic Coding, GLM-5.2 Open-Weights Release, Apple On-Device Models
Andrew Ng's weekly letter introduces a framework of three nested loops for agentic software development (engineering loop, developer feedback loop, external feedback loop), contextualizing the 'loop engineering' trend popularized by Claude Code and OpenClaw creators. The issue also covers Z.ai's GLM-5.2, a 753B MoE open-weights model with 1M token context that claims first place among open models on Artificial Analysis Intelligence Index v4.1 and leads all models on PostTrainBench for long-running agentic tasks. Additional coverage includes Apple's recipe for on-device models and AI education trends.
Coding Agents Accelerate Some Software Tasks More Than Others
Andrew Ng offers a practitioner framework ranking how much coding agents accelerate different software work: frontend development benefits most (agents close the loop via browser feedback), followed by backend, infrastructure, and research in decreasing order. Backend work still requires skilled developers to handle corner cases and security; infrastructure decisions remain largely human-driven due to complex tradeoffs and limited LLM knowledge in that domain; research is least accelerated because ideation and hypothesis iteration are not primarily coding tasks. The commentary is aimed at helping engineering managers set realistic expectations and organize teams accordingly.