Build

Agent Workflows

Use these patterns to structure agent prompts, tool sequencing, and human review loops for Lev-backed workflows.

Updated March 2026
Lender matching via MCP is coming soon

This page references lender search results in the recommended tool flow and prompt templates. The MCP tools that drive lender matching (search_lenders_for_deal, get_lender_search_results, search_lender_directory) are documented but not live at launch — see the MCP Tool Catalog for the current status. The REST endpoints continue to work today, so the workflow patterns here apply regardless of surface; only the MCP path is pending.

Workflow Design Principles

  • Retrieve before acting: pull deals, placements, term sheets, and account context before the agent makes a recommendation.
  • Keep tools narrow: prefer smaller reads and explicit actions over one giant prompt that asks the model to infer missing state.
  • Make handoffs visible: when the agent wants to mutate data or message a human, show the exact reasoning and source records first.
  • Use resource pages as contracts: tie prompt instructions to the schemas and constraints in the API reference pages.

Prompt Patterns

Safety and Review

Prefer reviewable agents

An agent that exposes its retrieved records, next action, and exact write payload is more useful than an agent that tries to feel magical.

  • Keep outbound actions gated behind approval.
  • Treat lender search, placements, and term-sheet comparisons as high-value review checkpoints.
  • Use request_id values from the API when you need to trace surprising behavior.
Next steps
More in this section