AI Automation
AI-assisted back-office workflows that summarise, sort and draft from documents and emails, with human review where it matters.
Custom quote after a short consultation · Timeline agreed in your quote
Overview
AI automation applies language models to repetitive back-office work that follows a pattern but still needs judgement: summarising incoming documents, sorting and tagging emails, extracting key details or drafting first replies. Unlike a chatbot, these workflows run in the background on triggers and pass results into the tools your team already uses.
RF ETS starts by mapping the current manual process, the inputs and the point where a person must stay in control. We then build the workflow, usually in Python with GPT models, connect it to your apps and add a human review step so outputs are checked before they reach customers or records.
The Advanced tier covers a multi-step workflow, or up to five workflows, connected to up to six apps, with logging and output quality checks so you can see what the automation did and spot weak results. Every tier ends with handover documentation. Model usage fees are billed by the provider to your own account.
Who it’s for
- Operations teams handling a steady flow of similar emails, forms or documents
- Small businesses that want routine admin drafted or sorted before a person reviews it
- Agencies and service firms that summarise client material or meeting notes every week
- Teams that tried ad hoc AI prompts and now want a repeatable, logged process
Problems it solves
- Spend less time reading, sorting and summarising routine documents and emails
- Get consistent first drafts that a person approves instead of writing from scratch
- Keep a record of what the automation processed and where it needed correction
- Connect AI steps to existing apps rather than copying text between windows
What RF ETS delivers
- Process map showing triggers, AI steps, integrations and review points
- Working AI workflow(s) connected to the agreed apps
- Prompt and configuration set, stored where your team can edit it
- Human review step and, on Advanced, logging and output quality checks
- Handover documentation covering how to run, monitor and adjust the workflow
How we work
Map the manual process
We document the current steps, inputs, outputs and the decisions that must stay with a person.
Design the workflow
We agree triggers, AI steps, app connections and review points, and confirm the tier or quote.
Build and test
We build the workflow, test it on real examples you provide and tune prompts against weak outputs.
Handover
You get documentation and a walkthrough so your team can run, monitor and adjust the automation.
What we need from you
- A description of the current manual process and who does it
- A set of real example inputs, such as anonymised emails or documents
- Access to the apps the workflow should connect to
- Your own AI-model or API account for usage billing
How pricing works
This work varies too much for fixed packages. We scope it with you, then send a written quote with price, timeline and deliverables before any work starts.
Tell us what you need
Use the quote form or book a consultation and describe your goal, constraints and deadline.
We scope it with you
We review your material and agree deliverables, assumptions and what is out of scope.
Written quote
You receive a fixed price or milestone plan, timeline and revision terms before any work starts.
Not included
- AI-model / API usage fees (paid by you)
- Guaranteed accuracy of AI outputs
- Third-party costs: domains, hosting, paid plugins and themes, software licences, API or AI-model usage fees, data-provider credits
- Work outside the written scope agreed before work starts (handled as an add-on or a custom quote)
- Ongoing support after the delivery and launch-support window unless a support package is bought
Need something different?
Tell us what you need, and we’ll prepare a solution and pricing based on your requirements.
AI Automation: common questions
How does pricing work for AI automation?
The tiers show typical scope with 'from' prices. Because integrations and document types vary, we confirm the final price in a written quote after reviewing your process. See the packages above for what each tier covers.
Who pays the AI-model usage fees?
You do. Model and API usage is billed by the provider to your own account, which keeps costs transparent and leaves you in control of the account. We help estimate usage during design, but those fees are not part of our price.
Will the AI outputs always be correct?
No AI system is fully reliable, so we do not promise accuracy. That is why workflows include a human review step from the Professional tier, and the Advanced tier adds logging and quality checks so weak outputs are visible and can be corrected.
How is this different from your AI chatbot service?
AI automation runs behind the scenes on triggers such as a new email or file, and passes results into your tools. A chatbot answers questions in a conversation, usually from your documents. If you need both, we can scope them together.
What if we need changes or more workflows later?
Revisions within the agreed scope are included as listed for your tier. Additional workflows can be added as an add-on, and larger changes are confirmed in an updated quote before work starts.
Often combined with
Workflow & Business Process Automation
We map a repetitive business process and build automated workflows between your apps, with branching logic, error alerts and clear process documentation.
Custom quoteView service →AI & Machine LearningAI Chatbot & RAG Development
AI chatbot and RAG development: assistants that answer from your documents, with citations, website embed, integrations and quality testing.
Custom quoteView service →Automation & Business SolutionsCRM, Lead & Reporting Automation
Automated lead capture, CRM updates and scheduled reporting, joined into one lead-to-report pipeline so sales data stays current without manual entry.
Custom quoteView service →