Posts, guides, and essays on building and governing AI agents.https://www.alecfoster.comhttps://www.alecfoster.com/guides/content-pipelinehttps://www.alecfoster.com/guides/content-pipelineHow a dozen n8n workflows watch the marketing-AI press, dedupe into one Notion database, post to X and Bluesky, and alert Slack when a run fails.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/ai-copyrighthttps://www.alecfoster.com/essays/ai-copyrightPrompt-only AI output gets no US copyright, and the training-data cases set your liability. What marketers should know as of mid-2026, indemnities included.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/eu-ai-act-marketinghttps://www.alecfoster.com/essays/eu-ai-act-marketingThe EU AI Act's high-risk rules slipped to 2027. Article 50 disclosure still applies August 2, 2026, and it covers AI avatars, voiceovers, and chatbots.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/recommendation-systemshttps://www.alecfoster.com/essays/recommendation-systemsThe filter-bubble story took empirical hits, but feeds now shift specific attitudes, carry mostly AI slop, and face binding rules only in the EU.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/architects-not-advocateshttps://www.alecfoster.com/essays/architects-not-advocatesResponsible AI has its principles and almost none of the runtime that enforces them. The next credible RAI leaders will ship evals and middleware.Tue, 12 May 2026 00:00:00 GMThttps://www.alecfoster.com/blog/mcp-supply-chainhttps://www.alecfoster.com/blog/mcp-supply-chainEvery MCP server you connect is third-party code your model trusts by reading. A pragmatic threat model and the controls that work.Wed, 15 Apr 2026 00:00:00 GMThttps://www.alecfoster.com/blog/evals-vs-vibeshttps://www.alecfoster.com/blog/evals-vs-vibesIf you can't say whether the new prompt beats the old one, you're vibing, not iterating. Here's a 30-minute eval that fixes it.Fri, 20 Mar 2026 00:00:00 GMThttps://www.alecfoster.com/blog/three-orchestration-patternshttps://www.alecfoster.com/blog/three-orchestration-patternsWhen to use routing, parallel fan-out, or orchestrator-workers, and the tradeoffs of each, drawn from the subagents I run every day.Sun, 08 Feb 2026 00:00:00 GMThttps://www.alecfoster.com/guides/deploying-claude-skillshttps://www.alecfoster.com/guides/deploying-claude-skillsHow to write, distribute, and govern Agent Skills across Claude Code, claude.ai, and ChatGPT, and how to write a description that makes a skill trigger.Thu, 15 Jan 2026 00:00:00 GMThttps://www.alecfoster.com/guides/rai-frameworks-marketinghttps://www.alecfoster.com/guides/rai-frameworks-marketingThe five risks specific to marketing AI, four controls that cover most of them, and a one-week plan to set up governance with free templates.Wed, 10 Dec 2025 00:00:00 GMThttps://www.alecfoster.com/essays/the-agent-stackhttps://www.alecfoster.com/essays/the-agent-stackTools, skills, and agents: the three-layer mental model that explains every multi-agent system I've reviewed.Sat, 22 Nov 2025 00:00:00 GMThttps://www.alecfoster.com/essays/protocols-of-powerhttps://www.alecfoster.com/essays/protocols-of-powerMy Cambridge dissertation on Google's Agent2Agent (A2A) protocol, the dominant standard for enterprise AI agents, and a Foucauldian reading of why moving A2A to the Linux Foundation was a political act.Tue, 08 Jul 2025 00:00:00 GMThttps://www.alecfoster.com/essays/the-data-dilemmahttps://www.alecfoster.com/essays/the-data-dilemmaAI governance often treats privacy and fairness as opposing values. This essay tests that binary against GDPR's special-category rules, US self-regulation, Amazon's hiring algorithm, the Apple Card, and IBM's facial-recognition exit.Mon, 10 Feb 2025 00:00:00 GMThttps://www.alecfoster.com/essays/beyond-principleshttps://www.alecfoster.com/essays/beyond-principlesAI ethics has produced many principles and few mechanisms for enforcing them. A critical reading of Rakova et al. (2021) and Marchant (2021), with lessons from the FLA and IAB on where industry self-regulation falls short.Wed, 31 Jul 2024 00:00:00 GMThttps://www.alecfoster.com/essays/esg-echoes-in-ai-ethicshttps://www.alecfoster.com/essays/esg-echoes-in-ai-ethicsESG promised to align corporate behavior with social welfare and largely failed. The essay argues that AI ethics is repeating the pattern and needs enforceable regulation in place of voluntary frameworks.Sun, 30 Jun 2024 00:00:00 GMThttps://www.alecfoster.com/essays/beyond-the-hypehttps://www.alecfoster.com/essays/beyond-the-hypeMicrotargeting and hypernudging raise valid autonomy concerns, but much of the public debate rests on simple narratives that overstate AI's persuasive power. The essay proposes an ethical framework grounded in the evidence.Tue, 02 Apr 2024 00:00:00 GMT