The Scheduled AI Agent
An AI agent that does one recurring job on your timetable, such as a morning summary of new support emails or a weekly look at competitor pages. It runs on your own server and your own AI account.
Every Monday someone on your team reads the same competitor pages, or starts the day by skimming the support inbox and writing up what matters. The job takes the same shape each time, and it waits whenever that person is busy or away.
We build a small AI agent that does that one job at the times you choose, from every hour to once a month. It reads up to three sources, such as web pages, a news feed, an email folder, a data file or a database query, and sends the result to email, Slack, Teams, a webhook, a file or a database table. You can tell it to stay quiet when it finds nothing worth sending.
The agent runs on your own server and your own OpenAI, Anthropic, Gemini or Mistral account, so you pay the provider directly and we never see your key. Once a monthly cap on its estimated AI spend is reached, it skips further runs, and a failed run sends an alert to the email address or channel you name. You approve the plan before we build, and the source code is yours.
What's included
One job on one timetable, from every hour to once a month, set out in a written plan you approve before we build
Reads up to three sources (web pages, news feeds, a CSV or JSON file, a read-only database query or an email folder) and skips the AI call when nothing is new, so empty runs cost you nothing
Delivers to the place your team already looks: an email list, a Slack or Teams channel, a webhook, a file on your server or new rows in a database table
Can hold a result back when the AI judges there is nothing worth sending, so an hourly check posts only when the AI finds something to report
Runs on your Docker host or Linux server and your own AI account, with a monthly spending cap, a warning at 80% and an alert to your chosen channel when a run fails
Three test runs on your live sources, one tuning pass from your notes, then one round of changes
Instructions, timetable, recipients and cap you can change yourself, plus the source code and a plain-English handover that records where your data goes
Before you order
Have these ready so we can start the moment you order. The delivery clock only runs while we have them.
A Docker host, or a Linux server with PHP 8.2 or later, that we can reach over SSH (you add the deploy key we send)
What the agent should read: page or feed addresses, a file location, a read-only database login, or an email folder that accepts a password or app password
Where the results and the alerts should go, with the mail server, Slack or Teams webhook, or database details they need
An account with billing turned on at OpenAI, Anthropic, Google Gemini or Mistral (you add the key on your server yourself; we never ask for it)
One person who will approve the plan, review the three test runs and send the feedback
How it works
Book it — pay the fixed price and tell us the target environment. No scoping call first.
We deliver — an experienced specialist runs our standard workflow for this exact task. You can watch progress and message them in the portal.
Hand-off — you get the deliverables, the documentation, a rollback snapshot, and a walkthrough if you want one.
Who does it
A salaried Support Resort specialist with more than ten years in the field, working from a runbook we've been refining since 2003 — supervised by senior management, never a marketplace contractor. You'll see who is assigned and can message them about this task directly in your portal.
FAQ
Ask about this task
Our assistant knows the scope document and runbook behind this service. Ask what's covered, what isn't, or whether it's the right task for your situation.
Answers come from our published scope documents. Prefer a person? Switch to the "Email us" tab — a senior manager replies personally, usually the same weekday.
Related services
The AI Workflow Agent (n8n or Make)
An AI workflow, built in your own n8n or Make account, that handles each new lead, email, ticket or form entry as it arrives and updates the apps your team already uses.
The MCP or API Integration
One of your systems, or your AI assistants, connected to a platform you already pay for, such as Xero, HubSpot, Shopify, Stripe or Microsoft 365, so nobody types the same record twice.
The AI Portal
Your best people's AI prompts, turned into simple forms the whole team can use, on your own AI accounts and under a monthly spending cap for each person.
The AI Developer Day
One full day of a senior AI developer working your list: LLM features shipped, prompts and retrieval measured against real cases instead of guessed at, and token bills brought back down.