AI Agents Use /goal and /loop Primitives to Run 5-10 Tasks Autonomously
Updated
Updated · O'Reilly Media · Nov 2
AI Agents Use /goal and /loop Primitives to Run 5-10 Tasks Autonomously
3 articles · Updated · O'Reilly Media · Nov 2
Summary
Addy Osmani says he now runs five to 10 AI agents in parallel, using /goal for bounded tasks with measurable stop conditions and /loop for recurring checks on a timer.
Those primitives turn loop engineering into a self-correcting cycle: an agent acts, tests results, and retries until a defined target is met or a turn limit is reached.
Concrete uses include raising Lighthouse scores above 90, reviewing the last 10 GitHub issues, and checking repositories every hour for new bugs or pull requests.
Osmani argues the setup works only when verification is explicit—ideally with a separate agent checking output—because vague goals, sensitive systems, and subjective design still require close human judgment.
The approach reflects a broader shift toward autonomous software agents, but with practical limits: recurring loops expire after seven days, are session-scoped, and move to cloud routines only through /schedule.
Will AI agents free us from tedious tasks, or trap us in invisible digital walled gardens controlled by tech giants?
If AI agents do all our shopping and reading, how will websites survive when human eyeballs disappear?
When a malicious website tricks your AI assistant into draining your bank account, who is legally responsible?
Surpassing Human Baselines: GPT-6 Astra, the Agentic Web, and the Economic Shockwave of 2026
Overview
In September 2026, OpenAI launched GPT-6 Astra, a powerful AI model trained on over 100,000 GPUs, marking a major leap in autonomous computer use and enterprise workflows. Astra’s advanced capabilities led to high pricing and forced companies to rethink ROI and management structures, as AI agents began replacing routine tasks and coordinator roles. However, Astra’s autonomy also brought critical cybersecurity risks, prompting OpenAI to restrict its use and withhold certain features. As organizations adopted these agents, new regulatory and safety challenges emerged, including unreliable evaluation methods and increased data breaches, ultimately leading OpenAI to pause further releases due to unresolved security concerns.