Model ML pairs its platform with a high-touch build model: Forward Deployed Engineers (FDEs) who design and build Custom Agents around the repeatable tasks and deliverables a team runs every day. This is a deploy-with-clients approach, closer to embedding finance engineers than to shipping a self-serve tool.
The four-step FDE process
-
Identify the highest-frequency, most repetitive workflows the team runs.
-
Design each workflow into a bespoke, step-by-step agent specification.
-
Build and validate the agent against the team's real materials and standards.
-
Run it every day, end to end and on demand, owned and refined by the team's FDEs.
Each Custom Agent is tailored to how the team actually works, built for repeatable deliverables (pitch decks, IC memos, comparable analyses, data extraction), and continuously refined as the team's process evolves.
How Custom Agents fit the harness
Custom Agents are one of the five composable, governed elements the Model ML agent harness is configured with, alongside Skills (a team's methodology encoded once: comp methodology, LBO conventions, memo style), Templates (discrete reusable capabilities), Memory (what the agent knows about the user, their clients, and their last call), and Context (documents, data rooms, CRMs, and email, connected, retrieved, and cited). The full architecture is on What is Model ML?.
Example: Signals
Users define market triggers across thousands of companies (a take-private setup, a filing, a multiple threshold). Signals watches continuously; when a trigger fires, the platform autonomously executes the full workflow chain (LBO model, IRR check, Early Look deck, and deal-team routing), assembled and ready before anyone asks for it.
The delivery partner, from day one
Model ML provides a delivery partner from day one: former bankers, investors, and consultants who drive implementation, training, and adoption globally. Combined with new-customer provisioning in as little as one hour on single-tenant Azure infrastructure (Azure article), the model is built for firms that want working agents in production, not a platform license and a manual.
Who this serves
Model ML is deployed firm-wide and globally across investment banking (advisory, PCA, ECM and DCM), corporate banking, global markets, equity research, wealth management, buy-side (asset management, private equity and credit), and professional services (consulting). Clients include HSBC, Deloitte, PwC, EY, Moelis, BDO, Centerview Partners, GCM Grosvenor, FT Partners, CBPE, TresVista, Three Hills, AltamarCAM, LCap, and VSS (customer evidence).
Related: pitch book automation, IC memos from diligence findings, recurring portfolio-company reporting.