Use cases/Graded research

Graded research

Partly builtLDG-227715 Minute MarketsStockGainesAI Source of TruthPromptCompute

The AI Source of Truth scorecard is live. Three parts to go.

Use case

Graded research: a workflow across 15 Minute Markets, StockGaines, AI Source of Truth, PromptCompute that starts from each new research call.

Who would use it

People who buy research on markets and stocks.

What value it provides

Each call is recorded before the outcome, graded when it resolves and shown on a public scorecard. Trading actions stay off by default and wait for a person.

Why it matters to the user

You can judge a research source by its record instead of its confidence.

The problem

Research calls are rarely graded once the event resolves, so a reader cannot tell a good source from a loud one.

Expected outcomes

Calls recorded before resolution: target 100%
Calibration on the scorecard
Trading actions without approval: 0

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

How it runs

1. Record each call with its time and odds15 Minute MarketsPlanned

2. Record each forecastStockGainesPlanned

3. Grade calls when they resolveAI Source of TruthPlanned

4. Show the scorecardAI Source of TruthBuilt

5. Gate any trading action for a personPromptComputeBuilt

Products and connections

Product	Role in this workflow	Docs
15 Minute Markets	Record each call with its time and odds	Reference · 15 Minute Markets docs
StockGaines	Record each forecast	Reference · StockGaines docs
AI Source of Truth	Grade calls when they resolve; Show the scorecard	Reference · AI Source of Truth docs
PromptCompute	Gate any trading action for a person	Reference · PromptCompute docs

Outside the family: None beyond the family.

What a person approves

Action	Default risk
`trade.order.place`	critical
`stockgaines.order.place`	high

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: "graded-research",
  inputs: { "source": "15 Minute Markets or StockGaines", "markets": "Your watch list" },
  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":"graded-research"}'

Or call the products yourself, step by step:

Product	Endpoint	Tools
15 Minute Markets	To confirm	to confirm
StockGaines	To confirm	to confirm
AI Source of Truth	`https://aisourceoftruth.com/v1/family/facts`	to confirm
PromptCompute	`https://mcp.promptcompute.ai/mcp`	`request_approval` `get_approval` `cancel_approval` `answer_approver`

Set it up

Sign in at app.promptreports.ai with PromptReports ID, and pick your org.
Connect 15 Minute Markets, StockGaines, AI Source of Truth, PromptCompute on the Connections page.
Register the agent that will run it on the Agents page, and give it a version manifest.
Set the approval policy for trade.order.place, stockgaines.order.place. Start with Require approval; critical actions are never auto.
Fill in the inputs (Source, Markets) and choose the trigger: each new research call.
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.