MGMT 675: Generative AI for Finance
Before building an AI agent, consider the alternative — a conventional app with menus, dropdowns, and input fields.
If a conventional UI can cover 90% of use cases simply, you may not need an agent. Agents earn their keep when the task is open-ended or hard to anticipate in advance.
Exercise 4B asked you to build a chatbot that lets users query an M&A database in plain English — 200 transactions across three tables (transactions, advisors, financing).
Sample queries: “What are the five largest completed deals?” · “Which banks advised the most deals?” · “What is the average EV/EBITDA multiple for tech acquisitions?”
Could a conventional app replace this?
The more open-ended and unpredictable the user’s needs, the stronger the case for an agent.
Dashboards are the traditional way to make data accessible to decision-makers:
An agent does the same job — surfaces data for decisions — but without the constraints:
Dashboards answer the questions you planned for. Agents answer the questions you didn’t.
Everything surrounding the model — except the model itself — is called the harness. The harness has three main parts:
Orchestration
Infrastructure
Governance
For 18 months, teams built this themselves using open-source frameworks or custom code. Now the AI vendors are shipping it as a product.
As of April 2026, every major AI vendor has shipped its own harness — but they disagree on pricing:
| Provider | Product | Launched | Pricing Model |
|---|---|---|---|
| Anthropic | Managed Agents | Apr 2026 | $0.08/session-hour + tokens |
| OpenAI | Agents SDK (open source) | Mar 2025 | Tokens only, no runtime fee |
| Vertex AI Agent Engine | Apr 2025 | Per-component consumption | |
| Microsoft | Foundry Agent Service | May 2025 | Per-model + per-tool consumption |
| AWS | Bedrock AgentCore | Oct 2025 | Runtime primitives (coming) |
Anthropic bundles everything into a session-hour fee. OpenAI gives away the harness and charges only for model usage. Google and Microsoft meter individual components. These are fundamentally different bets.
Andrej Karpathy built an agent called Dobby that replaced six separate smart home apps with a single WhatsApp conversation.
Before: The App Archipelago
After: One Conversation
The method matters more than the demo. Dobby didn’t use pre-built integrations. It scanned the local network, found devices, and figured out how to control them — like a developer learning a new codebase.
Dobby illustrates a deeper shift: from Graphical User Interface to Language User Interface.
The apps don’t disappear — but the user never touches them. The agent becomes the universal interface layer between people and software.
Interface Collapse
Nuance Over Sliders
APIs Over UIs
Access Democratized
Claude Code already does the Dobby pattern: you describe what you want in natural language, and it picks tools, runs code, queries data, writes files.
So why do we need agent software development kits (SDKs) and managed runtimes?
Claude Code / Desktop
Agent SDKs / Managed Agents
Claude Code is the universal agent for interactive work. The SDK layer is for agents that act on their own — overnight compliance monitoring, auto-triaging customer tickets, or a research agent that runs while you sleep.