https://cubxxw.com/columns/ai-2026-review-forecast/ Tech blog by Xinwei Xiong — AI Builder, open source contributor and digital nomad sharing Kubernetes, Go, AI projects and travel. https://cubxxw.com/assets/og-image.png https://cubxxw.com/ Hugo -- gohugo.io en-us Wed, 15 Jul 2026 09:00:00 +0800 https://cubxxw.com/ai-agent/posts/ai-agent-red-ocean-blue-ocean-2026/ Wed, 15 Jul 2026 18:00:00 +0800 Thu, 16 Jul 2026 03:07:34 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-agent/posts/ai-agent-red-ocean-blue-ocean-2026/ In late 2026, general-purpose and horizontal AI agents (coding, support, sales, scheduling) are a red ocean that foundation model labs can replicate within a single product cycle. The real blue ocean sits in two places: vertical, regulated workflows where someone takes end-to-end accountability, and infrastructure built for agents themselves (runtimes, payment rails, evals). This piece explains why feature moats cannot hold, what a real moat looks like (proprietary data flywheels, domain depth, end-to-end accountability), and offers a red-blue test table, a direction self-check, and an anti-pattern list, with separate bets for solo builders and founders. It closes out the entire 2026 review-and-forecast column. AI LLM Agent Product Strategy Solo Builder Super Individual The red ocean is full — where the blue ocean for AI agents is in late 2026 https://cubxxw.com/ai-agent/posts/trusting-unattended-ai-agent/ Wed, 15 Jul 2026 16:00:00 +0800 Thu, 16 Jul 2026 03:07:34 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-agent/posts/trusting-unattended-ai-agent/ The real bottleneck in handing work to an agent was never whether it can do the work, it is whether you dare use what it hands back. This essay takes apart the trust stack for unattended AI agents: guardrails that authorize before the action fires, regression evals that catch drift, and a morning HITL review. It uses the hard math of compounding error to explain why 95% per-step accuracy leaves you around a third after twenty steps, sorts guardrails into four tiers by reversibility, shows how to cold-start an eval set from your own incident log, and ends with a morning checklist and a list of anti-patterns. Trust does not come from the model behaving. It comes from engineering. AI LLM Agent Harness Engineering Monitoring Security Testing How Do You Get to the Point Where You Trust an AI Agent Nobody Is Watching? https://cubxxw.com/ai-agent/posts/open-model-cost-collapse-agent-fleet/ Wed, 15 Jul 2026 14:00:00 +0800 Thu, 16 Jul 2026 03:07:34 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-agent/posts/open-model-cost-collapse-agent-fleet/ An agent is a workload that burns tokens, and cost is its law of physics. By my own estimate, at comparable intelligence open models are now roughly 90% cheaper, taking a single agent task from a few dollars down to a few cents. For the first time, one person can genuinely afford a fleet of agents running around the clock. This essay works through the arithmetic and one ASCII diagram to explain the token cost collapse, why multi-model routing went from an optimization to the default architecture, and the hidden costs that cheap tokens quietly leave on your plate. AI LLM Agent Open Source Super Individual Solo Builder Open Models Got Roughly 90% Cheaper. How Big an Agent Fleet Can One Person Afford? https://cubxxw.com/ai-agent/posts/proactive-agent-it-prompts-you/ Wed, 15 Jul 2026 12:00:00 +0800 Thu, 16 Jul 2026 03:07:34 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-agent/posts/proactive-agent-it-prompts-you/ The counterintuitive signal of the past six months is that a growing number of AI agents no longer wait for your instruction. They read your context and prompt you instead. This essay places the proactive agent inside the third migration of interaction paradigms, from CLI-style to chat-style to proactive, takes apart the three foundations it needs, persistent memory, an agent runtime, and event triggers, offers an interruption budget model and a speak-up threshold you can apply directly, and makes a forecast for the second half, proactive will become a buzzword, but a wave of these products will die first, because the cost of interruption is badly underestimated and the tradeoff between trust and interruption is the real dividing line. AI LLM Agent Harness Engineering Product Strategy Context Engineering When the AI Agent Starts Prompting You, What Has Actually Changed https://cubxxw.com/ai-agent/posts/ai-auto-news-pipeline-limits/ Wed, 15 Jul 2026 10:00:00 +0800 Thu, 16 Jul 2026 03:07:34 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-agent/posts/ai-auto-news-pipeline-limits/ If you hand an AI the job of tracking a whole field for you, how far does it actually get? This essay takes apart the AI information pipelines that exploded in the first half of 2026: where each of the three technical routes stalls, how much three-stage dedup can cut and what it can never cut, and why compounding error makes long chains drift by construction. Access has been cut to zero, but the output usually stops at a more polished bookmark folder. The real ceiling is structural. AI can know things for you; it cannot judge for you. Includes a build checklist you can copy directly, a list of anti-patterns, and three forecasts for the second half. AI LLM Agent Automation Super Individual Monitoring Where an AI that tracks a whole field for you finally gets stuck