Agent Workflows

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.

Recommended Tool Flow

1. Identify context

   Resolve the deal, account, or lender the user is talking about before asking the model to reason about next steps.

   The agent knows which deal, account, or lender the conversation is about.
2. Gather primary records

   Read the smallest set of records needed: deal, financials, placements, term sheets, lender search results, or team context.

   You have the minimum grounding needed to reason — nothing more.
3. Summarize with citations

   Have the agent restate the key facts before it proposes any write or outbound action.

   The user can see the facts the model is reasoning from before anything moves.
4. Request confirmation

   For writes or external actions, require an explicit user confirmation or a review checkpoint.

   No write or outbound action happens without explicit approval.
5. Execute and log

   Perform the bounded action, then return the updated state plus the request_id when relevant.

   The action ran, and you have a `request_id` to trace it if anything surprises you.

Prompt Patterns

You are helping a broker evaluate lender fit.

1. Read the deal, deal financials, and any recent lender search results.
2. Summarize the facts you found.
3. Recommend the next action only if the records are sufficient.
4. If data is missing, say exactly what to fetch next.

Safety and Review

• 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.