Skip to content
PROGRAM 28 · TEAM TRAINING

AI & Data for Fintech & MFS Professionals

Faster support, smarter fraud checks, and products customers love.

Important: Customer and transaction data must stay inside approved systems and follow Bangladesh Bank and BFIU requirements. The course uses masked or synthetic data only, and AI never makes final decisions on fraud, KYC, accounts or credit.

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

  • Customer service, complaint and dispute teams
  • Risk, fraud, AML and compliance staff
  • Product, growth and marketing teams
  • Agent and merchant network teams in MFS, PSPs, payment gateways and digital lending

What your team will be able to do

  • Build reply libraries and complaint insight reports for wallet and payment issues
  • Spot unusual transaction patterns in data for human review
  • Analyse product usage, campaigns and agent performance
  • Deploy four working automations without exposing customer data
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 fintech and MFS work

9:00–10:30S1Prompt engineering for fintech & MFS
10:30Tea break
10:45–12:15S2Support, disputes & complaints
12:15Lunch & prayer
1:00–2:30S3Compliance, product & campaigns
2:45–4:30LABBuild lab: prompt library on your own files
4:30–5:00Q&A and day recap

Day 2

9:00 am – 5:00 pm

Masked data, then the first two builds

9:00–10:30S4Formulas & transaction data cleaning
10:30Tea break
10:45–12:15S5Usage, risk signals & network analytics
12:15Lunch & prayer
1:00–2:30S6Projects 01 & 02: Assistant & alerts
2:45–4:30LABBuild lab: dashboard, assistant and alerts on your data
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: Merchant onboarding workflow
10:30Tea break
10:45–12:15S8Project 04: Settlement & KYC 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 Fintech WorkSessions 1–3

Chatbot Landscape & Tool Selection

  • Gemini, ChatGPT, Claude, Copilot and DeepSeek: strengths for fintech work (support replies, policy documents, transaction tables, regulator circulars)
  • 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 a customer support lead, fraud analyst, compliance officer or product manager
  • Controlling output: length, tone, language, table or bullet format

Advanced Prompting Techniques

  • Few-shot prompting: teaching the model with examples of your own fintech work
  • Step-by-step reasoning for multi-part tasks such as checking whether a dispute qualifies for reversal or comparing two cashback designs
  • Constraint prompting: what to include, what to exclude, what to never assume
  • Chained prompts: breaking a complaint insight report (tickets → categories → root causes → fixes → owners) 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 fintech tasks
  • Testing a prompt before it goes into daily use

Data Privacy & Verification Discipline (Core)

  • What must never be pasted: account numbers, wallet numbers, NID data, transaction records, PINs or OTPs, KYC documents, STR details, fraud rules and thresholds
  • Anonymising data before prompting; safe vs unsafe fintech 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 fintech tasks.
PART 2Fintech 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

Compliance & Product Policy Assistant

Support, agent network and product colleagues get answers from product policies, fee and limit schedules, KYC procedures and circular summaries, with the section cited.

  1. INPolicies, fees & KYC procedures
  2. AIGrounded Gemini assistant
  3. OUTAnswer with the section cited
Built with Google AI Studio
02Session 6

Regulatory Reporting & Licence Alerts

Bangladesh Bank returns, BFIU timelines, partner agreements, audits and certificate expiries checked daily, with alerts 30, 15 and 7 days ahead.

  1. INRegulatory & licence tracker
  2. RUNDaily Make scenario
  3. OUTAlert to the right owner
Built with Make · Sheets · Gmail
03Session 7

Merchant Onboarding & Approval Workflow

Merchant requests checked for complete documents, high-risk categories sent to compliance, with SLA tracking and a full record of who approved.

  1. INMerchant onboarding form
  2. RULESMake approval scenario
  3. OUTMerchant logged with status
Built with Make · Forms
04Session 8

Settlement Report & KYC Extraction

Partner settlement reports and merchant licences become clean rows, with settlement gaps and expired or mismatched licence details flagged.

  1. INSettlement reports & licences
  2. AIGemini structured extraction
  3. OUTFlagged items to the officer
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 Fintech

Fairness & Non-Discrimination

  • Where bias enters fintech 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 customer, agent and merchant data

Financial Inclusion, Fairness & Customer Protection

  • AI flags, people decide: no automatic blocking, rejection or credit decision
  • Fraud flags checked for unfair impact on rural, low-income or new users

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 fintech 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 fintech tasks
  • Write support replies, dispute messages and scam awareness content
  • Brief teams on regulation and write product and campaign communication
  • Clean masked transaction data and build a usage and risk-flag dashboard
  • 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

A support reply library and complaint insight report
A circular brief, product FAQ and campaign message set
A usage and risk-flag dashboard on masked data you can defend number by number
A grounded compliance & product policy assistant your colleagues can use
A regulatory reporting & licence alert engine that reaches the right owner
Four deployed automations running in your own organisation
A written AI use policy for your own fintech or MFS 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
Fintech tools
Ticketing and CRM exportsSQL query basicsLooker Studio

What participants need

  • A laptop with Excel and a Google account
  • Basic Excel comfort (VLOOKUP, Pivot Tables) and masked or synthetic sample data approved by your compliance team
  • 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 fintech 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 fintech 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