SALES

Margin-aware deal-desk reviewer that drafts an approval recommendation

When a discount is requested, an agent pulls the deal's cost and margin data, checks it against discount policy.

CategorySales
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerOpportunity flagged for discount reviewSalesforce
  • ActionPull line items and cost/margin dataSalesforce
  • ActionLook up product costs in pricing tablePostgreSQLPostgres
  • LogicEvaluate against discount and margin-floor policy
  • OutputPost reasoned recommendation to deal-desk SlackSlack

What it does

This agent-driven workflow does the analysis a deal-desk analyst would do before a human signs off. On a discount request it gathers the opportunity's product mix, list price, cost, and resulting margin, evaluates the ask against your discount and floor-margin policy, and writes a clear recommendation — approve as-is, approve with conditions, or escalate — with the reasoning spelled out. The recommendation is posted to Slack for the approver to act on.

When to use it

Use it when discount decisions need margin context that lives across systems and you want approvers to start from an informed recommendation instead of a raw percentage. Good for complex product catalogs where the true cost of a discount isn't obvious.

How it works

  1. 1A Salesforce opportunity flagged for discount review triggers the agent.
  2. 2The agent pulls line items, costs, and margin data from the opportunity and a Postgres pricing table.
  3. 3It evaluates the request against discount tiers and the minimum-margin floor.
  4. 4It composes a recommendation with rationale and any suggested conditions.
  5. 5It posts the recommendation and a decision prompt to the deal-desk Slack channel.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SalesforceAccounts, opportunities, cases.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.