From understanding LLMs to deploying autonomous agents. Build systems that don't just answer questions — they take actions across your reconciliation, compliance, and reporting workflows.
ask-your-instructorEach module builds on the last — from understanding agent fundamentals to designing your team's pilot.
Click any module to launch its interactive explainer.
Why a chatbot can't close your books or process a wire. The three innovations that turn LLMs into agents — tools, reasoning, and multimodal inputs.
Explore Module →What makes a system "agentic"? Perception, reasoning, action loops. Compare workflow, autonomous, hybrid, and multi-agent architectures with banking examples.
Explore Module →Master 4 workflow patterns — chaining, parallelization, routing, orchestration — applied to reconciliation breaks, credit memo review, and regulatory synthesis.
Explore Module →Four layers that turn Quick into a working agent — Spaces, Chat Agents, Scheduled Agents, MCP Connectors. The mental model every later module hangs off.
Explore Module →The reusable unit of value in Quick. 5-part anatomy, 6-stage lifecycle, audit-defensible patterns, and Alex's three Chat Agents (Weekly Close Status, Break Triage, Credit Memo Reviewer).
Explore Module →The two automation surfaces on top of Chat Agents. Build no-code workflows with 5 step types · schedule them · share them. Plus Quick Research — AI-led investigations with cited reports.
Explore Module →Group capstone. Design a real agentic AI pilot for your team's problem. AI judge scores submissions on autonomy, tools, guardrails, and impact.
Start Capstone →Course recap, six mental models to keep, a searchable glossary, Quick/agentic cheat tables, and the certification path. Print it — it's your take-home reference.
View Module →Optional reference materials for deeper exploration.
The whole course on one interactive canvas — all 8 modules, their subtopics, and the 4 labs. Click to expand branches, drag, and zoom.
Every term from the workshop in plain English — agentic AI, Amazon Quick, and banking/finance shorthand — plus searchable filters and quick-reference cheat tables. Print it.
How agents connect to your core banking systems, document repositories, and APIs. Interactive demo with finance scenarios.
Recall the RAG pipeline from GenAI Essentials — agents extend RAG by adding tool use and multi-step reasoning.
Practical exercises designed for non-developers. No code required.
The gentle on-ramp: create a Space, upload onboarding & compliance procedure documents, and build a grounded agent that answers with citations and generates an induction checklist. No Flows, no MCP.
Go deeper: build a Break Triage Chat Agent, iterate it twice (add a capability + a guardrail), test it, generate a disposition memo, wrap it in a Flow, then connect a real public MCP.
Advanced and optional: combine your Lab 1A + 1B agents into one end-to-end process with Quick Automate — decision branch, document generation, a human approval gate, then commit · deploy · monitor. Enterprise-only; watch or follow along.
Design an agentic AI pilot for your team's actual problem. Submit for AI scoring (autonomy, tools, guardrails, impact). Team voting + presentations.