Consulting, agency, freelance and productized services delivered online.
38 workflows
A Tines example workflow fires on a Stripe cancellation, lets an AI agent look up the customer's support tickets and account history, and posts a structured churn brief to Slack.
A solo founder's step-by-step method for pulling cancellation reasons from Stripe, surveys and support tickets into one place, tagging them by theme, and ranking themes by how much revenue they cost.
A CRO consultant describes exporting a GA4 funnel as a table, giving Claude the product context and constraints, and asking for the three biggest leaks with a hypothesis, change, metric and ICE or PIE score for each.
A shared n8n template pulls last week's Stripe revenue, Notion deal pipeline and a Sheets row of support numbers, has Claude write a three-paragraph summary, and emails and posts it to Slack.
A founder-focused guide to trialing Grok for market scans, outreach drafts, document analysis and meeting recaps with a six-step test that splits public from private data and keeps human review.
The README for Nous Research's open-source Hermes Agent describes persistent memory, skills it creates after complex tasks, a natural-language scheduler and one gateway for chat apps.
A business-automation blog shows how to let several Hermes agents message each other in Telegram so a research agent can hand work to a writing agent in a content pipeline.
An infrastructure vendor's guide sets out business uses for OpenClaw and a phased rollout: pilot a low-risk workflow, add guardrails and approvals, then scale once value and safety are shown.
A hosting company's tutorial lists 25 OpenClaw workflows, including scheduled KPI posts, client onboarding folders and emails, expense logging and content repurposing, with security advice for running it safely.
Manus's own blog lists small-business workflows: researching top competitors' pricing into a dashboard, turning a rough plan into documents and a deck, and updating ClickUp, calendars and email.
A review of Manus describes goal-to-deliverable runs such as an eight-page market analysis with a price comparison in about 15 minutes, with tips for scoping tasks and the credit costs and failures to expect.
An experiment where AI agents audited 154 small-business sites and built static sites under strict approval gates, with a verifier that found a third of its sampled audits cited problems already fixed.
An open-source set of Claude skills that builds a shared context file, then produces positioning, customer research, competitive briefs, pricing and packaging and launch plans that build on each other.
A newsletter post gives a nine-step sequence and six prompts to find the outcome clients buy, standardise repeatable parts, design three package tiers, price by value and build a productized service.
An MIT-licensed plugin of Claude Code skills that guides a founder from an idea scorecard and competitor matrix through MVP scope, pricing strategy, go-to-market and a pitch deck outline, saving each output to a project folder.
A creator used Claude Design to build a brand system and landing page from her existing copy, Claude Code to build the assessment site, and an email tool to send profile-specific sequences.
A paid newsletter tutorial uses one prompt to define activation milestones and then prompts for a welcome email and follow-ups at days 3, 7, 14 and 30 to move new customers toward activation.
A newsletter author describes a small services business that classifies enquiries, drafts a first reply and tags the owner in Slack, with human review and fixed follow-up rules, cutting handling time per lead.
A framework for choosing a first AI automation by its worst-case outcome, connecting an inbox read-only, watching the first twenty runs, and naming who verifies output before widening the agent's permissions.
A solo automation engineer lists seven n8n workflows for agencies, from CRM-triggered onboarding to proposal reminders, with AI used for inbox triage and content repurposing drafts.
A freelancer's guide to the business side of building document chatbots for small clients: discovery call, a small free demo, a one-page scope, testing, handover and monthly support.
An AI engineer describes a retrieval-augmented chatbot deployed for one client with over 500 PDFs, with the chunking and retrieval choices, and reports 94% answer accuracy against 61% for plain GPT-4.
An automation engineer describes an n8n workflow that pulls analytics, search and ad data each Friday, has Claude write a plain-English comparison with the prior week, and emails clients a Google Doc.
A paid newsletter post says a prompt reverse-engineered from replied-to emails produced 167 replies and 43 meetings from 500 sponsorship cold emails, with each prompt version tested on 40 prospects.