Credentials. The ticketing system API key and customer records will pass through a locally running agent, so use a scoped key and test with a sandbox account first.
Who it is forA support lead at a small business whose customers message on WhatsApp and whose tickets live in a separate system.
The problemSupport requests on WhatsApp get collected into email and then stall, because the agent cannot act in the ticketing system.
The outcomeA WhatsApp agent that uses your own ticketing integration to look up and resolve requests.
What you need first
- Node.js 22 or newer
- A WhatsApp Cloud API app from Meta's developer portal with a phone number, access token, and app secret
- A model API key from OpenAI, Anthropic, or Gemini, or a local Ollama install
- A Google account, only if you use the Gmail/Calendar assistant
Steps
- Run
npm create @wappy_ai/agentand answer the setup questions. - Run
cp .env.sample .envand add your model key and WhatsApp credentials, plus any credentials your ticketing system needs. - Run
npm install. - Add a tool in the generated project that calls your ticketing system's API, since the business logic is yours to write. (inferred, check the README)
- Run
npm run dev, send a test support request from WhatsApp, and check that a ticket changes in your system.
Prompt for your agent
In the csr1010/wappy-kit repo, scaffold a project with `npm create @wappy_ai/agent` into ./<project-dir>, then add one tool that calls a ticketing API at <ticketing-api-url>. Expected output: a tool that returns a ticket status to the agent. Verify that the test call uses a sandbox ticket account and not production data.
Caveat. None of the business agents ship pre-built, so you write the ticketing integration yourself.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page