# AI use cases for AI Employees (markfulton/ai-employees) Repo: [markfulton/ai-employees](https://github.com/markfulton/ai-employees) | Use cases: 4 | Page: https://dedupedai.com/use-cases/markfulton-ai-employees/ Open source AI Employees: folders of scheduled routines, one per business role, that run on your own machine through the AI agent you already use. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a product launch with a GTM Engineer: https://dedupedai.com/use-cases/markfulton-ai-employees/launch-product-with-gtm-engineer/ - Publish one SEO article every weekday: https://dedupedai.com/use-cases/markfulton-ai-employees/publish-seo-articles-every-weekday/ - Triage the customer inbox with drafted replies: https://dedupedai.com/use-cases/markfulton-ai-employees/triage-customer-inbox-with-drafted-replies/ - Watch site health and triage errors automatically: https://dedupedai.com/use-cases/markfulton-ai-employees/watch-site-health-with-web-dev-employee/ ## How to run a product launch with a GTM Engineer with AI Employees Repo: [markfulton/ai-employees](https://github.com/markfulton/ai-employees) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README A scheduled employee drafts launch work and stages it for your review each morning. **Who it is for:** A founder launching a product who has no time to run positioning, outbound drafts, directory forms and a weekly scoreboard by hand. **The problem:** Launch tasks pile up across many channels and most of them stall when nobody is watching the board. **The outcome:** A folder of staged drafts, a launch board and a morning brief listing what needs your click. ### Steps 1. Run `npx ai-employees hire gtm-engineer --to ` or download the GTM Engineer kit from the repo with Code, Download ZIP. (inferred, check the README) 2. Open your agent in that folder and say "Install the GTM Engineer from this folder." 3. Wait for the install to stop and show its first drafts, then review them. 4. Read the next morning's brief and act on the cards under Waiting on you. ### Prompt to paste into your agent ```text Using the ai-employees repo, install the GTM Engineer into and confirm it builds a dashboard and schedules its routines. Expected output: a staged first set of drafts and a brief in the folder. Verify that nothing was sent, posted or submitted before you approved it. ``` ### Caveat Every send, post, submit, publish and spend is held for your click until you release a channel in RELEASES.md. Risk, remote script: The npx command downloads and runs the AI Employees package from npm, so check the source before you run it on your PC. Risk, credentials: The employee drives your signed-in browser as you, so only sign in to accounts you want it to read and use. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/markfulton-ai-employees/launch-product-with-gtm-engineer/ ## How to publish one SEO article every weekday with AI Employees Repo: [markfulton/ai-employees](https://github.com/markfulton/ai-employees) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README An SEO/AEO Employee researches keywords, publishes an article and reviews rankings on a schedule. **Who it is for:** A site owner who wants steady search traffic but cannot write, publish and index an article every weekday. **The problem:** Keyword research, publishing, indexing and rank checks get skipped whenever a busy week starts. **The outcome:** A steady flow of articles, indexing requests and rank reviews, with your visibility in AI answers tracked in the brief. ### Steps 1. Run `npx ai-employees hire seo-employee --to ` (inferred slug, based on the employee name in the README). (inferred, check the README) 2. Open your agent in that folder and say "Install the SEO/AEO Employee from this folder." 3. Check the first keyword list and article drafts it stops to show you. 4. Read the morning brief for publishing, indexing and rank review results. ### Prompt to paste into your agent ```text Using the ai-employees repo, install the SEO/AEO Employee into and confirm its routines are scheduled. Expected output: keyword research, a first article and a rank review in the employee's folder. Verify that each article is reviewed before it is published on your site. ``` ### Caveat Publishing and indexing run through your own signed-in browser, so confirm the first publish on your real site before you let the schedule run unattended. Risk, remote script: The npx command runs the AI Employees package from npm, so confirm the source before you run it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/markfulton-ai-employees/publish-seo-articles-every-weekday/ ## How to triage the customer inbox with drafted replies with AI Employees Repo: [markfulton/ai-employees](https://github.com/markfulton/ai-employees) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README A Customer Satisfaction Employee sweeps your inbox and drafts replies, hardest cases first. **Who it is for:** A small business owner who gets a steady flow of customer email and needs urgent problems and churn risks surfaced first. **The problem:** Important customer messages get buried, and churn risks go unnoticed until a customer has left. **The outcome:** Drafted replies ordered hardest first, plus churn flags with the evidence behind each one. ### Steps 1. Run `npx ai-employees hire customer-satisfaction-employee --to ` (inferred slug, based on the employee name in the README). (inferred, check the README) 2. Open your agent in that folder and say "Install the Customer Satisfaction Employee from this folder." 3. Review the first replies it drafts and the churn flags it raises. 4. Send replies yourself after you read each draft. ### Prompt to paste into your agent ```text Using the ai-employees repo, install the Customer Satisfaction Employee into and confirm it sweeps the inbox on schedule. Expected output: replies drafted hardest first and churn flags with evidence. Verify that no reply is sent until you approve it. ``` ### Caveat Replies are drafted for you, and the README says every send is held for your click, so review each draft before it goes to a customer. Risk, credentials: The employee reads your inbox through your signed-in browser, so only sign in to the mailbox you intend it to read. Risk, remote script: The npx command runs a package downloaded from npm, so check it before running it on your PC. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/markfulton-ai-employees/triage-customer-inbox-with-drafted-replies/ ## How to watch site health and triage errors automatically with AI Employees Repo: [markfulton/ai-employees](https://github.com/markfulton/ai-employees) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README A Web Dev Employee checks site health, triages errors and reviews dependencies on a schedule. **Who it is for:** A solo developer who runs a live site and wants routine checks and small fixes handled without daily attention. **The problem:** Errors and outdated dependencies build up quietly until a visitor reports them. **The outcome:** Regular health checks, a triaged error list and small changes made on a branch for your review. ### Steps 1. Run `npx ai-employees hire web-dev-employee --to ` (inferred slug, based on the employee name in the README). (inferred, check the README) 2. Open your agent in that folder and say "Install the Web Dev Employee from this folder." 3. Read the first health report and error triage in the morning brief. 4. Review any small change the employee made on its branch before you merge it. ### Prompt to paste into your agent ```text Using the ai-employees repo, install the Web Dev Employee into and confirm its health and error routines are scheduled. Expected output: a health report, a triaged error list and any branch changes. Verify that changes stay on a branch until you review them. ``` ### Caveat The README describes small changes on a branch, so keep your site's main branch protected and merge only the changes you have reviewed. Risk, remote script: The npx command runs a package from npm on your machine, so confirm the source first. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/markfulton-ai-employees/watch-site-health-with-web-dev-employee/