Skip to content
PROGRAM 29 · TEAM TRAINING

AI & Data for Microfinance Professionals

Less paperwork for field staff, clearer portfolios for managers.

Important: Member data is personal and financial. AI drafts messages, notes and reports; it never decides who gets a loan, how much, or what action is taken on an overdue member. A credit officer or manager decides, following your own credit policy and MRA requirements.

Who books it: Microfinance institutions and NGOs with credit programmes, for their branch, area and regional teams.

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

  • Field and credit officers in group and individual lending
  • Branch, area and regional managers
  • MIS, monitoring, audit and training teams in MFIs
  • NGO staff running savings, microenterprise and agriculture loan programmes

What your team will be able to do

  • Write clear Bangla member messages, appraisal notes and branch reports in minutes
  • Read collection, overdue and PAR data and explain what is happening
  • Turn field staff policy manuals into a grounded Q&A assistant
  • Deploy four working automations for branch and head office work
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 microfinance work

9:00–10:30S1Prompt engineering for microfinance
10:30Tea break
10:45–12:15S2Member communication & field writing
12:15Lunch & prayer
1:00–2:30S3Loan appraisal notes & branch reports
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

Portfolio data, then the first two builds

9:00–10:30S4Formulas & microfinance data cleaning
10:30Tea break
10:45–12:15S5Portfolio analytics & management reports
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: Loan exception workflow
10:30Tea break
10:45–12:15S8Project 04: Loan application 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 Microfinance WorkSessions 1–3

Chatbot Landscape & Tool Selection

  • Gemini, ChatGPT, Claude, Copilot and DeepSeek: strengths for microfinance work (simple Bangla messages, appraisal note drafting, policy summaries, collection sheet formulas)
  • 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 credit officer, branch manager, internal auditor or MFI trainer
  • Controlling output: length, tone, language, table or bullet format

Advanced Prompting Techniques

  • Few-shot prompting: teaching the model with examples of your own microfinance work
  • Step-by-step reasoning for multi-part tasks such as checking a member's repayment capacity from household income and expense notes
  • Constraint prompting: what to include, what to exclude, what to never assume
  • Chained prompts: breaking a monthly branch report (collection → overdue → PAR → causes → action plan) 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 microfinance tasks
  • Testing a prompt before it goes into daily use

Data Privacy & Verification Discipline (Core)

  • What must never be pasted: member names with NID numbers, phone numbers, loan balances by name, guarantor details, photos of members or their homes
  • Anonymising data before prompting; safe vs unsafe microfinance 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 microfinance tasks.
PART 2Microfinance 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

Credit Policy & Operations Assistant

Field officers and branch managers get answers from the credit policy, operations manual, savings rules and member protection policy, with the section cited.

  1. INCredit policy & ops manual
  2. AIGrounded Gemini assistant
  3. OUTAnswer with the section cited
Built with Google AI Studio
02Session 6

Branch Compliance & Deadline Alerts

MRA returns, rent agreements, audit findings, donor reports and staff training dates checked daily, with alerts 30, 15 and 7 days ahead.

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

Loan Rescheduling & Exception Workflow

Rescheduling, top-up and exception requests routed to the branch and area manager, with repeat and disaster-affected requests flagged.

  1. INException request form
  2. RULESApproval routing script
  3. OUTDecision logged, officer notified
Built with Apps Script · Forms
04Session 8

Loan Application Extraction Pipeline

Scanned loan applications become clean rows, checked against the branch collection sheet, with missing signatures and documents flagged.

  1. INScanned loan applications
  2. AIGemini structured extraction
  3. OUTMIS staging rows for review
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 Microfinance

Fairness & Non-Discrimination

  • Where bias enters microfinance 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 member, guarantor and borrower household data

Member Protection & Fair Treatment

  • No pressure, shame or public disclosure in collection practices
  • Transparent pricing: members understand what they will repay

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 microfinance 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 microfinance tasks
  • Write member messages, appraisal notes and branch reports quickly and safely
  • Clean collection and loan data and measure PAR and recovery
  • Explain portfolio trends to managers in clear language
  • 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 15-message Bangla member message library
An appraisal note template and a branch report template
A branch portfolio dashboard with PAR, recovery and dropout
A grounded credit policy & operations manual assistant your colleagues can use
A branch compliance & deadline alert engine that reaches the right owner
Four deployed automations running in your own organisation
A written AI use policy for your own microfinance institution

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
Microfinance tools
MFI MIS exportsLooker StudioGoogle Translate

What participants need

  • A laptop with Excel and a Google account
  • Basic Excel comfort and an anonymised extract of your branch collection or loan data
  • 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 microfinance 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 microfinance 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