Overview
Every provisional tax period, tax practices lost billable hours to the same exercise: reading each client’s prior-year return, working out which supporting documents the current year’s estimate would require, and drafting the request to the client. It was repetitive, unglamorous work, and done manually it could take an afternoon per client.
Generative AI was already on practitioners’ desks: almost nine in ten of those surveyed in The Tax Faculty’s recent working paper on AI adoption used it. Yet only nine in a hundred had automated a single workflow from beginning to end, and cost ranked only seventh among the obstacles to wider use. The gap was neither adoption nor budget: very few practices had yet built an AI-assisted workflow that covered an entire process.
Rather than discussing AI adoption in theory, the session closed that gap on one workflow, built live: provisional tax information requests. Starting from a client’s prior-year return, an AI skill identified the supporting documents that the current year’s estimate was likely to require, tested the possible scenarios with the practitioner until the client’s position was clear, and finished with an email to the client in the practitioner’s drafts folder, ready to be reviewed and sent. Each run left a file note, so the review took minutes and the audit trail was complete. Practitioners received the starter skill used in the demonstration, a single file to install, run, customise and keep.
Webinar Content
- Part 1: Introduction to AI-assisted workflows: what the term meant, why it was the recommended route to AI adoption in an accounting practice, and what professional bodies around the world had said about it.
- Part 2: What a skill was: one file, with no separate prompting method to learn, and why it ran the same way in Claude and in ChatGPT.
- Part 3: The workflow, built live: provisional tax information requests, from the prior-year return to the current year’s document list and client email, with the practitioner’s knowledge of the client as the one input the machine could not supply, and the skill ensuring that every human-in-the-loop review took place.
- Part 4: The audit trail: what made the workflow defensible rather than merely fast, with a record of what the skill read, what the practitioner corrected, what was sent and when.
- Part 5: From a skill to a workflow: the same skill in VS Code, run across the client list and writing into each client’s own folder.
- Part 6: Picking it back up: weeks later, with the documents in hand, straight through to the calculation, and a review that took minutes because the trail was never lost.
- Q&A and open discussion
Competencies Developed
- Understand what an AI-assisted workflow is, why it was the recommended route to AI adoption in an accounting practice, and what professional bodies internationally had said about its use.
- Explain what an AI skill is and how a single skill file can be installed, run and customised in both Claude and ChatGPT without learning a separate prompting method.
- Identify the supporting documents a client’s provisional tax estimate is likely to require, working from the prior-year return and testing possible scenarios until the client’s position is clear.
- Prepare clear, complete information requests to clients through an AI-assisted process that leaves a reviewed draft email ready to send.
- Keep a defensible audit trail of AI-assisted work, recording what the skill read, what the practitioner corrected, and what was sent and when.
- Exercise professional judgment over AI outputs by applying knowledge of the client and making sure every human-in-the-loop review is completed before anything reaches the client.
- Apply a single skill across a client portfolio so that each engagement’s records stay in the client’s own folder and can be picked up again at the calculation stage.
Presenter
Nestene Botha
Nestene Botha is a registered Chartered Accountant and the Academic Programme Leader for the BCom Accounting Programme at Mancosa. With a Masters Degree in Auditing Education, she has worked with approximately 10 higher education institutions globally and is deeply passionate about education. Nestene has a keen interest in Artificial Intelligence and its applications in the accounting profession, integrating AI and technology into her lectures and research. She is recognized as one of the top 35 under 35 Chartered Accountants in South Africa by SAICA and one of the top 50 women in accounting worldwide by Practice Ignition. Additionally, she is a co-founder of Explore ProTech, an entrepreneurial haven with the vision of saving the global economy - one small business at a time.
CPD
Attending this webinar and the successful completion of the online assessment will secure a certificate of completion for 2 hours of CPD.
Event Investment
Free for Tax Technician, Tax Practitioner, Tax Accountant CPD subscribers and Practice Packages. Not a CPD subscriber yet? Click here to register now.
- Regular price: R460.00
- Group booking discounts available when you register for a group.
Payments and cancellations
- All payments must be made by EFT or by credit card, at least three working days before commencement of an event.
- Kindly note that should payment not be received two days after the event, legal action will be taken.
- Proof of payment will be requested at registration if payment does not reflect in The Tax Faculty’s bank account.
- Only written notice of cancellation will be recognized.
- Conditions:
- If the cancellation occurs more than four working days prior to the event no cancellation fee will be charged.
- If the cancellation occurs less than four working days prior to the event, a 100% cancellation fee will apply.
- Delegates who book and fail to attend will be liable for the full event fee.
- The Tax Faculty’s liability in the case of an event being cancelled will be limited to a refund or credit of the event fee.
- Please click here for the full terms and conditions.