Posts, guides, and essays on building and governing AI agents.https://www.alecfoster.com/https://www.alecfoster.com/guides/claude-code-best-practices/https://www.alecfoster.com/guides/claude-code-best-practices/How I've configured Claude Code as an operating layer rather than a chat window: adaptive MCP profiles, three-tier subagent routing, verification rules that stop the model grading its own homework, hooks that enforce instead of remind, and why I turned the reasoning effort dial back down.Mon, 27 Jul 2026 00:00:00 GMThttps://www.alecfoster.com/guides/content-pipeline/https://www.alecfoster.com/guides/content-pipeline/A dozen n8n workflows that watch the marketing-AI industry, dedupe everything into one Notion database, and fan drafts out to X and Bluesky — with a Slack alarm when any of it breaks. The architecture, each workflow's job, and how the pieces connect.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/ai-copyright/https://www.alecfoster.com/essays/ai-copyright/Where AI and copyright actually stand for marketers as of mid-2026: why prompt-only output gets no protection after the Copyright Office's 2025 reports and the Thaler ruling, what the training-data cases (Bartz, Kadrey, Thomson Reuters, NYT) mean for the content you publish, and the fine print in your vendor's indemnification that decides who pays when an output infringes.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/eu-ai-act-marketing/https://www.alecfoster.com/essays/eu-ai-act-marketing/Everyone read the headline that the high-risk rules got delayed to 2027. The part that binds marketing teams — Article 50 transparency and disclosure — goes live August 2, 2026, and it covers your AI spokespeople, avatars, voiceovers, and chatbots. What's actually due, and what to do before the deadline.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/recommendation-systems/https://www.alecfoster.com/essays/recommendation-systems/The filter-bubble story took real empirical hits, but recommendation feeds got harder to govern, not easier: feeds now demonstrably shift specific attitudes, AI slop is most of what's in them, and the only rules with teeth are the EU's. Where the evidence, the law, and the brand-safety problem actually stand.Tue, 30 Jun 2026 00:00:00 GMThttps://www.alecfoster.com/essays/architects-not-advocates/https://www.alecfoster.com/essays/architects-not-advocates/The principles are written. The runtime isn't. Why the next wave of credible RAI leaders will ship middleware, not manifestos.Tue, 12 May 2026 00:00:00 GMThttps://www.alecfoster.com/blog/mcp-supply-chain/https://www.alecfoster.com/blog/mcp-supply-chain/Every MCP server you connect is third-party code your model trusts by reading. A pragmatic threat model and the controls that actually help.Wed, 15 Apr 2026 00:00:00 GMThttps://www.alecfoster.com/blog/evals-vs-vibes/https://www.alecfoster.com/blog/evals-vs-vibes/If you can't say whether the new prompt is better than the old one, you're not iterating — you're vibing. The 30-minute fix.Fri, 20 Mar 2026 00:00:00 GMThttps://www.alecfoster.com/blog/three-orchestration-patterns/https://www.alecfoster.com/blog/three-orchestration-patterns/Routing, parallel fan-out, and orchestrator-workers — when to reach for which, with the tradeoffs that bite. Grounded in the subagents I actually run.Sun, 08 Feb 2026 00:00:00 GMThttps://www.alecfoster.com/guides/deploying-claude-skills/https://www.alecfoster.com/guides/deploying-claude-skills/How to author, distribute, and govern Agent Skills so a whole team gets them — across Claude Code, claude.ai, and the ChatGPT equivalents — and how to write a skill that actually triggers when it should.Thu, 15 Jan 2026 00:00:00 GMThttps://www.alecfoster.com/guides/rai-frameworks-marketing/https://www.alecfoster.com/guides/rai-frameworks-marketing/The risks specific to marketing AI, the controls that actually work, and how to stand up your first governance in a week using templates you can download.Wed, 10 Dec 2025 00:00:00 GMThttps://www.alecfoster.com/essays/the-agent-stack/https://www.alecfoster.com/essays/the-agent-stack/Tools, skills, 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-power/https://www.alecfoster.com/essays/protocols-of-power/My Cambridge dissertation on the protocols quietly becoming the governance standard for enterprise AI agents — Google's A2A and Anthropic's MCP — and why the choice to consolidate A2A under the Linux Foundation is a political act, not a technical one.Tue, 08 Jul 2025 00:00:00 GMThttps://www.alecfoster.com/essays/the-data-dilemma/https://www.alecfoster.com/essays/the-data-dilemma/Privacy and fairness are presented as opposing values in AI governance, but the choice between them is not actually a binary. A close look at GDPR exceptions, US self-regulation, the Amazon hiring algorithm, the Apple Card, and IBM's facial-recognition exit.Mon, 10 Feb 2025 00:00:00 GMThttps://www.alecfoster.com/essays/beyond-principles/https://www.alecfoster.com/essays/beyond-principles/AI ethics has produced an oversupply of principles and a desperate shortage of mechanisms. A critical reading of Rakova et al. (2021) and Marchant (2021), with hard-won lessons from the FLA and IAB about why industry self-regulation usually fails.Wed, 31 Jul 2024 00:00:00 GMThttps://www.alecfoster.com/essays/beyond-the-hype/https://www.alecfoster.com/essays/beyond-the-hype/Microtargeting and hypernudging raise valid autonomy concerns, but most of the public discourse is driven by simplistic narratives that overstate AI's persuasive power. A balanced framework — grounded in evidence — is what's actually missing.Tue, 02 Apr 2024 00:00:00 GMThttps://www.alecfoster.com/essays/esg-echoes-in-ai-ethics/https://www.alecfoster.com/essays/esg-echoes-in-ai-ethics/The ESG movement promised to align corporate behavior with social welfare and largely failed. AI ethics is on the same trajectory — unless we replace voluntary frameworks with enforceable structural reform.Thu, 01 Feb 2024 00:00:00 GMT