Anthropic’s Building Effective Agents appendix highlights two proven patterns—support agents that pull data and take actions like refunds, and coding agents that iterate against tests—with clear success metrics and human review.
Make’s trigger guide shows how to bootstrap agent scenarios from Slack, Telegram, email, forms, webhooks, or mailhooks, then add tools, knowledge, and instructions—or run on a schedule.
Make’s Feb 2026 AI Agent docs list concrete agent scenarios—support ticket triage, sales outreach, content marketing, market research, candidate screening, SEO reports—plus when to use agents vs fixed scenarios.
A builder pattern for selling Grok Bot work: give each client a studio+client@mail.grokbot.com tag and a routine that only accepts requests from approved contacts.
n8n docs describe first-class agents with tools, knowledge bases, hourly/daily schedules, and sub-agent handoffs—plus embedding agents inside fixed workflows via the Message an Agent node.
Official n8n AI example: a chat agent answers with GPT-4; if unsure it calls a sub-workflow that asks for the user's email and posts the unanswered question to a Slack support channel.
An indie hacker packaged an agency's eight repeated workflows (briefs, client approval with revision counters, quotes with margin checks, content calendars, post-mortems) as free MIT Claude skills.
Indie Hackers guide: Jotform intake → Zapier → Claude/ChatGPT triages priority and drafts a reply → a control form lets you edit → a second Zap finishes CRM/notify actions—only high-priority items pause for review.