GAI101FFOUNDATION (FINANCIAL SERVICES)
Applied Generative AI for Financial Services
Build responsible AI workflows for financial-services work
Explore where generative AI can help in financial services, and where careful review matters. Work through practical examples without treating the output as the final decision.
- Audience
- Financial services professionals
- Duration
- 18.5 hours
- Format
- 3 days · In person
- Level
- Beginner
- Coding
- No coding
- Prerequisite
- Secondary education; no prior AI, coding or finance qualification
- Full fee
- S$1,750
01What you’ll build
No coding · 3 days · In person
What you’ll build: A compliance-aware assistant, a human-reviewed automation, a safe knowledge brain and a multi-model financial-services workflow.
A compliance-aware AI assistant
Ground it in approved knowledge files and test it with fictional financial-services scenarios.
A human-reviewed automation
Classify and summarise synthetic client email, draft a reply and log the work before approval.
A multi-model financial workflow
Use at least two AI tools with traceable evidence, verification checks and responsible controls.
02Curriculum
18.5 hours
Curriculum
Day 01
- Understand how generative AI and LLMs work, and why their capabilities matter in financial services.
- Compare ChatGPT, Claude and Gemini while recognising hallucination, bias, knowledge cut-off, context-window and confidentiality risks.
- Use task, context, format, role, few-shot and structured-output prompt patterns with verification habits.
- Practise on relationship-manager notes, product terms, complaint categorisation and a loan scenario using fictional data.
- Create image, voice and slide drafts while retaining the required compliance sign-off.
- Build a client-education or internal-briefing asset with an appropriate tool and review path.
- Clean, summarise, analyse and chart synthetic branch-transaction and complaints datasets.
- Spot-check figures and reconcile findings against the source data before reporting them.
Day 02
- Configure reusable assistants in Custom GPTs, Gems and Claude Projects for a defined financial-services task.
- Set instructions, persona, tone, scope, model configuration and approved knowledge sources.
- Add refusal, escalation and moderation guardrails, then run adversarial tests and iterate.
- Build and version a GlobalFin Bank Compliance FAQ Assistant using synthetic and approved content.
- Map repetitive financial-services work into triggers, actions, connectors and human review points.
- Use Zapier, with Make as an alternative, to build a no-code workflow.
- Process a synthetic client email through classification, summarisation, reply drafting and a spreadsheet log.
- Add human approval, error handling, an audit trail and embedded guardrails before identifying opportunities in your own role.
Day 03
- Find answers from a supplied document collection with retrieval-augmented generation (RAG): indexing, retrieval and generation, and what RAG does and does not fix.
- Build a safe Obsidian knowledge vault with approved sources, provenance, links and review dates.
- Test cited answers, missing-information behaviour, retrieval quality and basic anonymisation.
- Apply PDPA obligations, MAS FEAT principles, bank-secrecy expectations and responsible vendor-risk questions.
- Compose prompts, assistants, automations, RAG and a curated knowledge brain into one toolkit.
- Build a traceable workflow using at least two generative-AI models and explain the tool-selection rationale.
- Apply the workflow to relationship management, compliance, operations or research using fictional or approved data.
- Assess impact, feasibility and estimated time saved, then frame a responsible pilot proposal.
03Your instructor
Metacamp trainer
Your instructor: Vincent Leow
Tech Lead, Neutral Trade.
His background spans data, machine learning, software engineering and applied technology education, which he brings to financial-services scenarios and responsible review.
04Course FAQ
A few things worth knowing before you choose.
Still unsure? Write to team@metacamp.sgFull fee
S$1,750
Funding to be confirmed
Start with GAI101 if you are new to applied generative AI. Choose GAI101F to build within a financial-services context, AI101 to analyse financial data with Python, or GAI201 after GAI101 or equivalent experience to orchestrate multi-agent systems.
GAI101 and GAI101F require no prior AI or coding experience. AI101 teaches Python from the fundamentals and requires tertiary education. GAI201 requires GAI101, GAI101F or equivalent working generative-AI fluency, but no coding experience.
Funding is course-specific. Eligible Singapore Citizens may use up to S$500 from their Opening SkillsFuture Credit toward the remaining fee. SkillsFuture Mid-Career Credit cannot be used. Available subsidies and final fees depend on the approved course run and your eligibility; confirm the prevailing amount before enrolment.
Something you built and know how to use. Depending on the course, this may be a custom assistant and automation, a financial-services AI workflow, a Python data-analysis capstone or a tested multi-agent system.
Yes. We offer private programmes for organisations and functional teams. Examples and exercises can be shaped around relevant roles, workflows and business goals.
AI will continue changing after your course. We teach principles and ways of thinking that remain useful as tools evolve. Graduates can also continue learning with the Metacamp community as new sessions and programmes are announced.