alec foster subscribe

education

Education.

How I teach: long-form guides for practitioners, opinionated essays for operators, a weekly newsletter for senior marketing leaders, and live cohort workshops for teams that need to ship a real agent system in the room.

All of the written material is free. The cohort and workshop programs are paid and capacity-limited.

manifesto

flagship essay · 11 min read

Responsible AI Needs Architects, Not Just Advocates

The principles are written. The runtime isn't. Why the next wave of credible RAI leaders will ship middleware, not manifestos.

read the essay →

learning_paths

canon

The pieces I'd hand to someone joining my team on day one.

// guides

  • Claude Code best practices, from a year of daily use 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.
  • The Content Pipeline: how I run a one-person media operation on n8n 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.
  • Deploying Claude Skills across an organization 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.
  • A responsible AI framework for marketing teams 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.

// essays

  • You can't copyright most of what your AI makes, and that's your smaller problem 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.
  • The EU AI Act is a 2026 problem for marketers, not a 2027 one 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.
  • What actually governs your feed in 2026 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.
  • The agent stack, top to bottom Tools, skills, agents — the three-layer mental model that explains every multi-agent system I've reviewed.

workshops

w-01

Skills Sprint

half-day · in person or virtual

Your team leaves with three production-ready Claude skills they wrote themselves, plus the patterns to write the next ten. Built for engineering and ops teams.

request →
w-02

Agent Architecture Review

full-day workshop

Bring your existing or proposed agent architecture. We work through it layer by layer using the Agent Stack model, surfacing the failure modes and the missing governance hooks. Honest, specific, painful in the right ways.

request →
w-03

Responsible-AI Runtime Lab

2-day intensive

For RAI teams and engineering teams together in the same room. We turn your written policies into concrete runtime checks: eval gates, trace filters, capability constraints. You leave with running code, not a deck.

request →

Want a workshop tailored to your team's situation? Tell me the problem and I'll propose a session that hits it directly.