> ## Documentation Index
> Fetch the complete documentation index at: https://docs.interchange.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Demand inbox
> The front-of-house ledger of every buyer brief your storefront answered — proposal, feedback, and result, with grades and an agent-vs-human scoreboard.
## Overview
The **demand inbox** is your storefront's front-of-house ledger: one place that
answers *what demand came in, how did my agent respond, and did we win?* Each
row is one buyer brief your Merchandising Agent answered, joined to the proposal
it produced and the commercial result that followed. It is the human-readable
scoreboard on top of your [intelligence runs](/v2/storefront/intelligence-runs/overview).
Every number is computed **only from what actually happened**. A metric with no
inputs yet reads as *unavailable* — never a fabricated `0`. A historical brief
captured before canonical artifact persistence reads as *artifact unavailable*
rather than being reconstructed.
## The metrics strip
| Metric | Meaning | When unavailable |
| -------------- | ----------------------------------------------------------------------------- | --------------------------------- |
| Briefs YTD | Briefs received this calendar year | Never — a true count (may be `0`) |
| Answered | Share of this year's briefs the agent answered with a proposal | No briefs yet |
| Win rate | Won ÷ (won + lost) across briefs with a decided result (see scope note below) | No result recorded yet |
| Avg grade | Mean seller grade (A–F) rounded to the nearest letter | Nothing graded yet |
| Agent vs human | Split of briefs led by the agent vs a human who took over | No run has recorded attribution |
The scoreboard covers this year's briefs and counts your agent's **first
response** to each brief. Renegotiation (refine) passes are not yet rolled up to
their originating brief, so the win rate reflects first-response briefs rather
than the full negotiation.
## The ledger row
Each row carries the brief, the buyer, when it came in and went out, who led the
response (agent or human), the buyer's feedback, the commercial result
(**won**, **lost**, or **pending**), and your letter grade.
* **Result** derives from that brief run's own attributed commercial outcome: a
forwarded or delivered buy is `closed_won`, a rejected buy is `closed_lost`,
and anything still in flight (or not yet attributed) is `pending`. A booking
attributed to a later renegotiation pass is not rolled up here (see the scope
note above). There is no separate result to keep in sync — it always reflects
the run's real state.
* **Grade**, **feedback**, and **led-by** are seller-authored annotations you
record against a row. Grade and feedback default to empty; led-by defaults to
the agent, since every composed response is agent-led until a human takes it
over.
## Money
Each row shows the buyer's **stated budget range** exactly as it arrived on the
brief (buyers state it in `filters.budget_range`; when a buyer doesn't, the
column reads absence rather than a guess). A won row also shows the **won
value** — the delivered spend when reporting exists, otherwise the booked
media-buy budget — always in the money's own currency, never converted. The
**Booked YTD** tile totals this year's won money per currency; multiple
currencies are disclosed rather than summed together.
## Filters
Filter the ledger by **buyer** from the widget header to focus on one
relationship. Sector filtering is not available yet — sector is not captured
per brief today.
## Related
The per-request detail behind each ledger row.
The aggregate performance view across many runs.