http://opakalex.github.io/tags/talon/Recent content in Talon on Alex Opak | Software ArchitectHugoen-usMon, 22 Jun 2026 00:00:00 +0000http://opakalex.github.io/posts/human-in-the-loop-vigilance/Mon, 22 Jun 2026 00:00:00 +0000http://opakalex.github.io/posts/human-in-the-loop-vigilance/Human-in-the-Loop is sold as a quality guarantee for AI decisions. In practice it is a business-comfort zone – a place where a living person carries the responsibility for decisions they do not actually control.http://opakalex.github.io/posts/code-mode-for-mcp/Fri, 29 May 2026 00:00:00 +0000http://opakalex.github.io/posts/code-mode-for-mcp/LLMs are excellent at writing code, but bad at making business decisions. Cloudflare’s Code Mode idea – let the model write the script, and let an expert system run it – is a natural fit for EITL. A claims-processing example in the Talon language.http://opakalex.github.io/posts/enterprise-ai-orchestration/Thu, 28 May 2026 00:00:00 +0000http://opakalex.github.io/posts/enterprise-ai-orchestration/Managing AI agents in the enterprise means solving for security, knowledge access, and orchestration at the same time. A look at OpenTalon – an EITL-first framework that combines LLMs with expert rules for corporate AI architecture.http://opakalex.github.io/posts/llm-neural-network-or-expert-system/Wed, 27 May 2026 00:00:00 +0000http://opakalex.github.io/posts/llm-neural-network-or-expert-system/Each kind of system makes a different kind of decision. LLMs generate language, neural networks find patterns, expert systems make the call. A look at why the boundary matters – and how the real world runs on it.http://opakalex.github.io/posts/expert-in-the-loop/Wed, 13 May 2026 00:00:00 +0000http://opakalex.github.io/posts/expert-in-the-loop/Why Human-in-the-Loop (HITL) is a bottleneck, and how Expert-in-the-Loop (EITL) with deterministic expert systems alongside LLMs offers a better paradigm for AI-driven decision making.