> ## Documentation Index
> Fetch the complete documentation index at: https://docs.genesiscomputing.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Prover Consult Agent
> Built-in ruling service that measures one implementer reason against an open comparison finding and the ticket that produced it.
**Genesis Prover now has its own section.** What the Prover is, how its components
fit together, how a run works and who may approve what all live under
[Genesis Prover](/docs/Genesis-Prover/Overview). This page covers the **Prover
Consult** agent itself; Consult's place in the whole is described in
[Overview → The consult agents](/docs/Genesis-Prover/Overview#5-the-consult-agents).
**Prover Consult** (`bot_id`: `Consult`, display name *Prover Consult*) is a
built-in Genesis system agent. Any agent carrying `source_contract_tools` can bring
it one proposed reason not to fix, not to change, or to read a ticket a particular
way. Consult measures the dispute with read-only estate queries; it does not submit,
settle, close, or license findings.
In the MCP agent list, its short description is: *Prover ruling service. Rules on ONE proposed reason not to fix or not to change something by measuring it against the ticket; use it before relying on such a reason. It cannot record or license anything itself.*
Rule on one grounded disagreement about an open comparison finding: an
explanation, a ticket reading, or a claim that the check is malformed.
The finding ledger, ticket context, compiled readings, check SQL, and the two
named databases. Probes are read-only `SELECT` statements.
Consult emits a measured verdict and provenance. It has no submission channel,
and an agent ruling never licenses a finding by itself.
## Availability
Genesis seeds the non-editable **Prover Consult** system agent during startup with
the stable `bot_id` `Consult` — never renamed, because it keys threads, loadouts and
every recorded ruling. Its direct tool loadout contains only `data_connector_tools`;
callers reach it through `request_consult_ruling` in the `source_contract_tools`
group, which the pinned seats (Consult itself, the Adjudicator, the Court-Attorney)
deliberately do not carry. The constitution Consult works under is packaged with
Genesis and recorded by name and content hash when the agent is initialized.
Snowflake metadata-backed installs also seed this seat; see
[Snowflake metadata cache storage](/docs/Setup/Connections#snowflake-metadata-cache-storage)
for where it is stored and how startup handles seed failures.
## What a ruling is, and is not
A caller brings the open finding, exactly one **dispute shape** — an *explanation*, a
*reading* of the ticket, or a claim of a *check defect* — and the implementer's
position in its own words. Everything else is hydrated from the finding ledger, which
is the point: **a caller that could describe the finding could describe it
favourably.**
Consult returns a verdict about the merits — `ACCEPTED_SUPPORTING` (the ticket
licenses the position, and it survives an elimination probe) or `REJECTED` — plus
`INVALID_DOCKET` for a request that must be repaired before it can be ruled on. The
result carries the thread, the round number, the rationale, the probes actually run,
any mechanical guard, and a `spec_flag` when Consult found an axis the ticket leaves
undetermined.
Two properties are worth stating plainly:
* **Consult is never shown an oracle.** No verifier outcome, no benchmark score, no
prior review decision reaches it. Its ruling must be grounded in the ticket and in
measurable estate data.
* **It cannot escalate by choosing to.** Escalation is mechanical: a dispute has a
bounded number of rounds, and the call that reaches the bound records the
escalation — with the implementer's values standing and every ruling attached —
after which further calls on that measurement are refused. A new position appeals
in the same thread.
A `spec_flag` is a **record stored on the finding for a person to read**. It names
whether the ticket left an axis undetermined or over-specified a check — opposite
repairs — along with the verbatim ticket sentence it turns on. It is not sent to a
spec author, opens no handoff, and never reopens a sealed specification.
For the call itself — parameters, defaults, cost and the full result shape — see the
[`source_contract_tools` reference](/docs/Genbot-Toolkit/Additional-Tool-Groups#source-contract-tools).
## How a ruling reaches the board
`estate_char.consult.apply_mode` decides what a recorded ruling does, and it is read
when the ruling is applied. The shipped default is `human_approval`.
| Mode | Effect |
| - | - |
| `advisory` | The ruling is recorded on the finding and changes nothing. |
| `human_approval` **(shipped default)** | Recorded, and the finding reads *ruling pending approval*. It stays in the open, unlicensed count until a person approves, or an agent approves for them through an eligible Prover request — which then seeds and ratifies the ruling in one action. See [Prover roles and approvals](/docs/Genesis-Prover/Roles-And-Approvals#who-can-approve). |
| `auto` | Seeds a **provisional** direction in the ruling library for the finding's ambiguity class. It applies immediately, is reversible by unsettling, and is queued for ratification; the finding reads *ruled — provisional* until a person ratifies it. Declining withdraws what the acceptance applied. |
An unreadable or unrecognised configuration reads as `advisory`, not as the shipped
default — the failure a wrong guess must never cause is a finding leaving the open
count on an unratified agent ruling.
Seeding also requires the ruling library itself: `estate_char.rulings.enabled` must be
true and `estate_char.rulings.fairness_hold` false. Those switches outrank the apply
mode. If either blocks the overlay, or the finding carries no ambiguity class, the
ruling is recorded as a finding event only. Rejections, escalations, invalid dockets
and an acceptance Consult never probed all record without seeding a direction.
Approving or declining a recorded ruling is a person's act. See
[Roles and approvals](/docs/Genesis-Prover/Roles-And-Approvals) for what that
signature attests to.
## Cost and safety
One call spends one full Consult bot turn plus read-only `SELECT` probes against the
named delivered and build databases, and can take seconds to minutes. Do not call it
speculatively, in a loop, or for a finding you have not read.