Use cases/Cost per outcome

Cost per outcome

Partly builtLDG-2274RepoOpsPromptComputeCommitOpsSales as Code

Sales as Code shows cost per forecast and per won deal. Three parts to go.

Use case

Cost per outcome: a workflow across RepoOps, PromptCompute, CommitOps, Sales as Code that starts from monthly, or when spend crosses a budget line.

Who would use it

Founders and engineering leaders paying for agent work.

What value it provides

Spend joined to outcomes across products: dollars per recovered incident, per kept promise and per won deal, with a budget a person approves.

Why it matters to the user

You can defend agent spend in a board meeting, and cut the spend that produces nothing.

The problem

Agent spend arrives as tokens and dollars per vendor. Nobody can say what a recovered incident, a kept promise or a won deal cost.

Expected outcomes

Cost per recovered incident
Cost per kept promise
Share of agent spend tied to an outcome: target above 80%

Each run records its outcome as met, not met or not measured.

How it runs

1. Read spend per outcome (spend_outcome)RepoOpsBuilt

2. Send agent cost back to CommitOpsRepoOpsSwitching on

3. Read cost per forecast and per won dealSales as CodeBuilt

4. Join spend to outcomes across productsPromptReportsPlanned

5. Hold spend above the budget for a person (cumulative limit)PromptComputeBuilt

Products and connections

Product	Role in this workflow	Docs
RepoOps	Read spend per outcome (spend_outcome); Send agent cost back to CommitOps	Reference · RepoOps docs
PromptCompute	Hold spend above the budget for a person (cumulative limit)	Reference · PromptCompute docs
CommitOps		Reference · CommitOps docs
Sales as Code	Read cost per forecast and per won deal	Reference · Sales as Code docs

Outside the family: Your model provider billing export (optional).

What a person approves

Action	Default risk
`credits.top_up`	high
`subscription.plan.change`	medium

Action keys are from the PromptCompute catalog.

How to access it from an agent

An agent will run this workflow through the PromptReports MCP server or API, with an ID agent token. The runner will then call each product for it. Proposed

// MCP: https://mcp.promptreports.ai/mcp (Proposed)
start_run({
  workflow: "cost-per-outcome",
  inputs: { "period": "This month", "budget": "$4,000", "outcomes": "Incidents, promises, deals" },
  dry_run: false
})
// returns { run_id, status: "running", approvals_url }
get_run({ run_id })   // poll, or subscribe to run events

curl -X POST https://api.promptreports.ai/v1/runs \
  -H "Authorization: Bearer $PROMPTREPORTS_AGENT_TOKEN" \
  -d '{"workflow":"cost-per-outcome"}'

Or call the products yourself, step by step:

Product	Endpoint	Tools
RepoOps	`https://mcp.repoops.ai/mcp`	`search_brain` `get_pre_edit_context` `propose_brain_entry` `get_incident_attribution`
PromptCompute	`https://mcp.promptcompute.ai/mcp`	`request_approval` `get_approval` `cancel_approval` `answer_approver`
CommitOps	`https://commitops.ai/api/mcp`	`whoami` `list_assertions` `get_assertion` `promised_not_started`
Sales as Code	To confirm	to confirm

Set it up

Sign in at app.promptreports.ai with PromptReports ID, and pick your org.
Connect RepoOps, PromptCompute, CommitOps, Sales as Code on the Connections page. Link Your model provider billing export (optional) through the product that uses it.
Register the agent that will run it on the Agents page, and give it a version manifest.
Set the approval policy for credits.top_up, subscription.plan.change. Start with Require approval; critical actions are never auto.
Fill in the inputs (Period, Budget, Outcomes) and choose the trigger: monthly, or when spend crosses a budget line.
Start a dry run. It will count no workflow request, and it shows which steps would record missing evidence.
Start the run. Approve each gate in the approvals inbox, then read the signed record when it ends.