docs: remove batch cli eval pattern

Author: christso

apps/web/src/content/docs/docs/next/evaluation/batch-cli.mdx

@@ -302,92 +302,6 @@ tests:
         value: "Matches the reference answer: {{ expected_output }}"
 ````
 
-## Batch CLI
-
-Evaluate external batch runners that process all tests in one invocation:
-
-```yaml
-description: Batch CLI demo (AML screening)
-providers:
-  - batch_cli
-
-prompts:
-  - "{{ input }}"
-
-tests:
-  - id: aml-001
-    criteria: |-
-      Batch runner returns JSON with decision=CLEAR.
-    vars:
-      input:
-        - role: system
-          content: You are a deterministic AML screening batch checker.
-        - role: user
-          content:
-            request:
-              type: aml_screening_check
-              jurisdiction: AU
-              effective_date: 2025-01-01
-            row:
-              id: aml-001
-              customer_name: Example Customer A
-              origin_country: NZ
-              destination_country: AU
-              transaction_type: INTERNATIONAL_TRANSFER
-              amount: 5000
-              currency: USD
-      expected_output:
-        - role: assistant
-          content:
-            decision: CLEAR
-
-    assert:
-      - name: decision-check
-        type: script
-        command: [bun, run, ./scripts/check-batch-cli-output.ts]
-        cwd: .
-
-  - id: aml-002
-    criteria: |-
-      Batch runner returns JSON with decision=REVIEW.
-    vars:
-      input:
-        - role: system
-          content: You are a deterministic AML screening batch checker.
-        - role: user
-          content:
-            request:
-              type: aml_screening_check
-              jurisdiction: AU
-              effective_date: 2025-01-01
-            row:
-              id: aml-002
-              customer_name: Example Customer B
-              origin_country: IR
-              destination_country: AU
-              transaction_type: INTERNATIONAL_TRANSFER
-              amount: 2000
-              currency: USD
-      expected_output:
-        - role: assistant
-          content:
-            decision: REVIEW
-
-    assert:
-      - name: decision-check
-        type: script
-        command: [bun, run, ./scripts/check-batch-cli-output.ts]
-        cwd: .
-```
-
-### Batch CLI Pattern Notes
-
-- `target: batch_cli` -- configure the CLI provider with `batch_requests: true`
-- The batch runner reads the eval YAML via `--eval` flag and outputs JSONL keyed by `id`
-- Put structured data in `user.content` as objects for the runner to extract
-- Use `vars.expected_output` with object fields for structured expected output
-- Each test has its own grader to validate its portion of the output
-
 ## Shared Prompt Context
 
 Share a common prompt or system instruction across all tests with top-level