Skip to content
PROGRAM 40 · TEAM TRAINING

AI & Data for Audit & Internal Control

Audit more, sample smarter, and report findings that get acted on.

Important: AI supports audit work but does not replace professional judgement or evidence. Audit files and client data are confidential and go only into tools the organisation has approved.

8 sessions3 modules4 hands-on projects3 days · 9 am–5 pmCertificate on completion
CHOOSE A FORMAT
Request a proposalSee the curriculum

Who this course is for

  • Internal auditors and internal control officers
  • Risk, compliance and inspection teams
  • External audit associates and article students
  • Audit teams in banks, NBFIs, insurance, RMG groups, NGOs and listed companies

What your team will be able to do

  • Plan audits, write audit programs and test steps faster with AI
  • Test whole populations in Excel to find duplicates, outliers and exceptions
  • Write clear findings with risk ratings that management acts on
  • Deploy four working automations for your own audit function
How it runs

3 days at your office, 8 sessions

Three sessions a day plus a hands-on build lab every afternoon. Day 3 ends with capstone presentations.

Day 1

9:00 am – 5:00 pm

AI chatbots for audit work

9:00–10:30S1Prompt engineering for audit
10:30Tea break
10:45–12:15S2Audit planning, programs & controls
12:15Lunch & prayer
1:00–2:30S3Findings, reports & follow-up
2:45–4:30LABBuild lab: audit program and findings on your own files
4:30–5:00Q&A and day recap

Day 2

9:00 am – 5:00 pm

Analysis, then the first two builds

9:00–10:30S4Formulas & audit data cleaning
10:30Tea break
10:45–12:15S5Audit analytics & risk insight
12:15Lunch & prayer
1:00–2:30S6Projects 01 & 02: Assistant and alerts
2:45–4:30LABBuild lab: exception tests, assistant and alerts
4:30–5:00Q&A and day recap

Day 3

9:00 am – 5:00 pm

Last two builds and the capstone

9:00–10:30S7Project 03: Finding response & closure
10:30Tea break
10:45–12:15S8Project 04: Voucher & invoice extraction
12:15Lunch & prayer
1:00–3:00LABCapstone build clinic
3:15–4:30LABCapstone presentations
4:30–5:00Certificates and next steps
Group: 10–40 people from one organisationSame content and projects in both formatsBangla delivery with English technical termsEvery session ends with a deliverable
Curriculum

8 sessions, one build in each

3 modules · 8 sessions · 4 hands-on projects

PART 1AI Chatbots for Audit WorkSessions 1–3

Chatbot Landscape & Tool Selection

  • Gemini, ChatGPT, Claude, Copilot and DeepSeek: strengths for audit work (audit programs, policy comparison, long document review, finding write-ups)
  • Free vs paid tiers; a workflow that needs no international payment card
  • Bangla vs English output quality; when to draft in English and translate
  • Which tool for a long document, which for a formula, which for a polished letter

Prompt Engineering Fundamentals

  • What a prompt is; why the same question gives different answers
  • The four-part structure: role, context, task, output format
  • Role prompting: act as an internal auditor, risk manager, control tester or audit committee reviewer
  • Controlling output: length, tone, language, table or bullet format

Advanced Prompting Techniques

  • Few-shot prompting: teaching the model with examples of your own audit work
  • Step-by-step reasoning for multi-part tasks such as assessing the risk of a process with five control gaps or choosing a sample size
  • Constraint prompting: what to include, what to exclude, what to never assume
  • Chained prompts: breaking an audit assignment (risk assessment → program → testing → findings → report → follow-up) into a sequence of smaller steps

Iteration & Prompt Library Building

  • Why the second prompt matters more than the first; refining instead of restarting
  • Diagnosing a bad output: vague instruction, missing context or wrong tool
  • Building reusable prompt templates for repeated audit tasks
  • Testing a prompt before it goes into daily use

Data Privacy & Verification Discipline (Core)

  • What must never be pasted: client and customer records, account and NID numbers, unreported fraud allegations, whistleblower names, draft audit reports, system passwords
  • Anonymising data before prompting; safe vs unsafe audit use cases
  • Hallucination awareness; verifying every figure, date, name and legal reference
  • The verification rule: AI drafts, a person checks before anything leaves the building
DELIVERABLEa personal prompt library of 10 templates for your repeated audit tasks.
PART 2Audit Data Analysis in Excel & Google SheetsSessions 4–5
PART 3Applied Projects: AI Assistants & AutomationSessions 6–8
Applied projects

Four automations, running in your organisation

01Session 6

Policy & Control Reference Assistant

Auditors and process owners ask which control applies and get an answer from your audit manual, policies and DoA, with the section cited.

  1. INAudit manual, policies & DoA
  2. AIGrounded Gemini assistant
  3. OUTAnswer with the section cited
Built with Google AI Studio
02Session 6

Audit Plan & Follow-up Alert Engine

Audit plan dates, management action due dates, audit committee deadlines and inspection timelines checked daily, with alerts 30, 15 and 7 days ahead.

  1. INAudit plan & findings tracker
  2. RUNDaily Make scenario
  3. OUTAlert to the responsible owner
Built with Make · Sheets · Gmail
03Session 7

Finding Response & Closure Workflow

Owners submit progress and evidence, the auditor reviews and closes or rejects, and overdue high-risk findings are escalated.

  1. INFinding evidence form
  2. RULESReview routing in Make
  3. OUTClosed or escalated finding
Built with Make · Forms · Sheets
04Session 8

Voucher & Invoice Audit Extraction

Vouchers, invoices and POs become clean rows, with a three-way match, duplicate and above-limit approval checks, and exceptions flagged.

  1. INVouchers, invoices & POs
  2. AIGemini structured extraction
  3. OUTExceptions in a review sheet
Built with Gemini API · Drive

Capstone presentation

Each person presents one automation built for their own workplace.

Day 3 afternoon
Applied across every session

Responsible & Ethical AI in Audit

Fairness & Non-Discrimination

  • Where bias enters audit decisions: data, wording, criteria and past patterns
  • Proxy discrimination: address, age, gender or background inferred indirectly

Privacy & Data Protection

  • Data minimisation: collect only what the decision requires
  • Retention and deletion of employee, vendor and customer data

Independence, Evidence & Professional Skepticism

  • Audit conclusions rest on evidence, not on AI summaries
  • Protecting whistleblowers and the people named in exceptions

Accountability & Human Oversight

  • Human-in-the-loop by design: AI recommends, a named person decides
  • Who owns an AI-assisted decision when it is challenged

Workforce Impact & Your AI Use Policy

  • Talking to audit teams about AI without triggering job-loss fear
  • Reskilling and role redesign as AI absorbs routine work
Outcomes

By the end, your team can

  • Choose the right AI tool and write prompts that work first time
  • Maintain a prompt library covering your repeated audit tasks
  • Write risk assessments, audit programs and control tests with AI help
  • Run full-population exception tests in Excel and Power Query
  • Write findings and reports that management acts on
  • Build and deploy automations with Make, Apps Script and the Gemini API
  • Apply fairness, transparency and privacy to every AI-assisted decision

And leaves with

Audit program templates and a control test sheet
An exception testing workbook
A findings report template and audit committee dashboard
A grounded policy & control reference assistant your colleagues can use
A audit plan & finding follow-up alert engine that reaches the right owner
Four deployed automations running in your own organisation
A written AI use policy for your own audit and internal control team

Tools your team will use

Chatbots
ChatGPTGeminiClaudeCopilotDeepSeek
Content
CanvaGammaCapCutGoogle Slides
Data
Microsoft ExcelGoogle SheetsPower Query
Workspace
GmailCalendarMeetFormsDrive
Automation & AI builds
MakeGoogle AI StudioApps ScriptGemini API
Audit tools
Excel Power QueryPower BI or Looker StudioIDEA or ACL concepts (optional)

What participants need

  • A laptop with Excel and a Google account
  • Basic audit knowledge and working Excel (filters, Pivot Tables, lookups)
  • One real work file to practise on from Session 2
  • No coding background required; free tiers only

How your team will learn

  • build-along classes (you work while the trainer works)
  • practise on your own workplace file, not dummy data
  • every session ends with a deliverable
  • Bangla delivery with English technical terms
  • recordings, prompt library and setup guides
  • certificate after capstone submission
Request a proposal

Bring this program to your audit team

Tell us about your team. We reply within one working day with a plan built around your own documents and workflows.

  1. 1 · A short discovery call with your audit lead
  2. 2 · We tailor examples to your masked files
  3. 3 · Offline at your office, or online live classes
Chat on WhatsApp
Request a proposal