diff --git a/src/handlers/eval/ab-test/ab-test.fixture.test.tsx b/src/handlers/eval/ab-test/ab-test.fixture.test.tsx
index b5429f5d9..0812a5c95 100644
--- a/src/handlers/eval/ab-test/ab-test.fixture.test.tsx
+++ b/src/handlers/eval/ab-test/ab-test.fixture.test.tsx
@@ -199,7 +199,7 @@ describe("eval ab-test config-based run", () => {
       ONLINE_EVAL_NAME,
       "--agent",
       AGENT_ID,
-      "--evaluator",
+      "--evaluators",
       EVALUATOR_ID,
       "--sampling-rate",
       "100",
@@ -280,7 +280,7 @@ describe("eval ab-test target-based run", () => {
       TB_ONLINE_EVAL_C,
       "--agent",
       AGENT_ID,
-      "--evaluator",
+      "--evaluators",
       EVALUATOR_ID,
       "--sampling-rate",
       "100",
@@ -300,7 +300,7 @@ describe("eval ab-test target-based run", () => {
       TB_ONLINE_EVAL_T1,
       "--agent",
       AGENT_ID,
-      "--evaluator",
+      "--evaluators",
       EVALUATOR_ID,
       "--sampling-rate",
       "100",
diff --git a/src/handlers/eval/batch-evaluation/batch-evaluation.fixture.test.tsx b/src/handlers/eval/batch-evaluation/batch-evaluation.fixture.test.tsx
index b3b8a8f62..a690811e3 100644
--- a/src/handlers/eval/batch-evaluation/batch-evaluation.fixture.test.tsx
+++ b/src/handlers/eval/batch-evaluation/batch-evaluation.fixture.test.tsx
@@ -128,7 +128,7 @@ describe("eval batch-evaluation (fixture-backed)", () => {
       "evaluate",
       "--agent",
       FIXTURE_EVAL_AGENT,
-      "--evaluator",
+      "--evaluators",
       "Builtin.Helpfulness",
       "--name",
       FIXTURE_EVAL_NAME,
@@ -172,7 +172,7 @@ describe("eval batch-evaluation (fixture-backed)", () => {
       '{"prompt":"{input}"}',
       "--dataset",
       FIXTURE_SIMULATE_DATASET,
-      "--evaluator",
+      "--evaluators",
       "Builtin.Helpfulness",
       "--name",
       FIXTURE_SIMULATE_NAME,
diff --git a/src/handlers/eval/batch-evaluation/batch-evaluation.test.tsx b/src/handlers/eval/batch-evaluation/batch-evaluation.test.tsx
index e76da4395..98d49f7b2 100644
--- a/src/handlers/eval/batch-evaluation/batch-evaluation.test.tsx
+++ b/src/handlers/eval/batch-evaluation/batch-evaluation.test.tsx
@@ -172,7 +172,7 @@ describe("eval batch-evaluation simulate", () => {
     '{"prompt":"{input}"}',
     "--dataset",
     "/tmp/ds.jsonl",
-    "--evaluator",
+    "--evaluators",
     "Builtin.Helpfulness",
     "--name",
     "sim-1",
@@ -181,18 +181,27 @@ describe("eval batch-evaluation simulate", () => {
   test.each<[RegExp, string[]]>([
     [
       /--runtime-id/,
-      ["--payload-template", "{}", "--dataset", "/tmp/ds.jsonl", "--evaluator", "E", "--name", "n"],
+      [
+        "--payload-template",
+        "{}",
+        "--dataset",
+        "/tmp/ds.jsonl",
+        "--evaluators",
+        "E",
+        "--name",
+        "n",
+      ],
     ],
     [
       /--payload-template/,
-      ["--runtime-id", "r-1", "--dataset", "/tmp/ds.jsonl", "--evaluator", "E", "--name", "n"],
+      ["--runtime-id", "r-1", "--dataset", "/tmp/ds.jsonl", "--evaluators", "E", "--name", "n"],
     ],
     [
       /--dataset/,
-      ["--runtime-id", "r-1", "--payload-template", "{}", "--evaluator", "E", "--name", "n"],
+      ["--runtime-id", "r-1", "--payload-template", "{}", "--evaluators", "E", "--name", "n"],
     ],
     [
-      /--evaluator/,
+      /--evaluators/,
       [
         "--runtime-id",
         "r-1",
@@ -213,7 +222,7 @@ describe("eval batch-evaluation simulate", () => {
         "{}",
         "--dataset",
         "/tmp/ds.jsonl",
-        "--evaluator",
+        "--evaluators",
         "E",
       ],
     ],
diff --git a/src/handlers/eval/batch-evaluation/evaluate/index.tsx b/src/handlers/eval/batch-evaluation/evaluate/index.tsx
index 3d4565380..f6c73c512 100644
--- a/src/handlers/eval/batch-evaluation/evaluate/index.tsx
+++ b/src/handlers/eval/batch-evaluation/evaluate/index.tsx
@@ -14,7 +14,7 @@ export const createEvaluateBatchEvaluationHandler = (core: Core, io: AppIO) =>
     description: "evaluate existing sessions service-side (async; returns a job ID)",
     flags: [
       ...SessionSource.flags,
-      flag("evaluator", "evaluator ID(s) to apply", z.array(z.string()).optional()),
+      flag("evaluators", "evaluator ID(s) to apply", z.array(z.string()).optional()),
       flag(
         "ground-truth",
         "session ground truth (JSON SessionMetadataShape[]; inline, file://<path>, or -)",
@@ -28,9 +28,9 @@ export const createEvaluateBatchEvaluationHandler = (core: Core, io: AppIO) =>
       if (!flags["name"]) {
         throw new InputValidationError("required option '--name <name>' not specified");
       }
-      if (!flags["evaluator"] || flags["evaluator"].length === 0) {
+      if (!flags["evaluators"] || flags["evaluators"].length === 0) {
         throw new InputValidationError(
-          "required option '--evaluator <evaluator...>' not specified",
+          "required option '--evaluators <evaluators...>' not specified",
         );
       }
 
@@ -46,7 +46,7 @@ export const createEvaluateBatchEvaluationHandler = (core: Core, io: AppIO) =>
         {
           name: flags["name"],
           description: flags["description"],
-          evaluatorIds: flags["evaluator"],
+          evaluatorIds: flags["evaluators"],
           source,
           groundTruth,
           kmsKeyArn: flags["kms-key-arn"],
diff --git a/src/handlers/eval/batch-evaluation/simulate/index.tsx b/src/handlers/eval/batch-evaluation/simulate/index.tsx
index 45c18641d..a880a3ddf 100644
--- a/src/handlers/eval/batch-evaluation/simulate/index.tsx
+++ b/src/handlers/eval/batch-evaluation/simulate/index.tsx
@@ -33,7 +33,7 @@ export const createSimulateBatchEvaluationHandler = (core: Core, _io: AppIO) =>
       flag("user-id", "Runtime user ID", z.string().optional()),
       flag("dataset", "dataset source: local JSONL path or a dataset ID", z.string().optional()),
       flag("dataset-version", "dataset version (with a dataset ID)", z.string().optional()),
-      flag("evaluator", "evaluator ID(s) to apply", z.array(z.string()).optional()),
+      flag("evaluators", "evaluator ID(s) to apply", z.array(z.string()).optional()),
       flag("name", "batch evaluation name (unique in the account)", z.string().optional()),
       flag("description", "description for the batch evaluation", z.string().optional()),
       flag("kms-key-arn", "KMS key to encrypt evaluation data at rest", z.string().optional()),
@@ -51,9 +51,9 @@ export const createSimulateBatchEvaluationHandler = (core: Core, _io: AppIO) =>
       }
       if (!flags["dataset"])
         throw new InputValidationError("required option '--dataset' not specified");
-      if (!flags["evaluator"]?.length) {
+      if (!flags["evaluators"]?.length) {
         throw new InputValidationError(
-          "required option '--evaluator <evaluator...>' not specified",
+          "required option '--evaluators <evaluators...>' not specified",
         );
       }
       if (!flags["name"])
@@ -95,7 +95,7 @@ export const createSimulateBatchEvaluationHandler = (core: Core, _io: AppIO) =>
           {
             name: flags["name"],
             description: flags["description"],
-            evaluatorIds: flags["evaluator"],
+            evaluatorIds: flags["evaluators"],
             source: {
               origin: "agent",
               agent: flags["runtime-id"],
diff --git a/src/handlers/eval/batch-insights/batch-insights.test.tsx b/src/handlers/eval/batch-insights/batch-insights.test.tsx
index 5a0837ad1..620ec9720 100644
--- a/src/handlers/eval/batch-insights/batch-insights.test.tsx
+++ b/src/handlers/eval/batch-insights/batch-insights.test.tsx
@@ -137,7 +137,7 @@ describe("eval batch-insights run", () => {
       "--insight",
       "Builtin.Insight.UserIntent",
       "Builtin.Insight.ExecutionSummary",
-      "--evaluator",
+      "--evaluators",
       "Builtin.Helpfulness",
       "--json",
     ]);
diff --git a/src/handlers/eval/batch-insights/run/index.tsx b/src/handlers/eval/batch-insights/run/index.tsx
index 032871053..6d9d2a037 100644
--- a/src/handlers/eval/batch-insights/run/index.tsx
+++ b/src/handlers/eval/batch-insights/run/index.tsx
@@ -17,7 +17,7 @@ export const createRunBatchInsightsHandler = (core: Core, io: AppIO) =>
       ...SessionSource.flags,
       flag("insight", "insight ID(s) to run", z.array(z.string()).default([DEFAULT_INSIGHT])),
       flag(
-        "evaluator",
+        "evaluators",
         "optional evaluator ID(s) to run alongside the insights",
         z.array(z.string()).optional(),
       ),
@@ -36,7 +36,7 @@ export const createRunBatchInsightsHandler = (core: Core, io: AppIO) =>
           name: flags["name"],
           description: flags["description"],
           insightIds: flags["insight"],
-          evaluatorIds: flags["evaluator"],
+          evaluatorIds: flags["evaluators"],
           source,
           kmsKeyArn: flags["kms-key-arn"],
         },
diff --git a/src/handlers/eval/ondemand/evaluate/index.tsx b/src/handlers/eval/ondemand/evaluate/index.tsx
index d9bdeea1f..4d50ca7b2 100644
--- a/src/handlers/eval/ondemand/evaluate/index.tsx
+++ b/src/handlers/eval/ondemand/evaluate/index.tsx
@@ -19,7 +19,7 @@ export const createEvaluateOnDemandHandler = (core: Core, io: AppIO) =>
         z.string().optional(),
       ),
       flag("endpoint", "Runtime endpoint qualifier (default DEFAULT)", z.string().optional()),
-      flag("evaluator", "evaluator ID(s) to apply", z.array(z.string()).optional()),
+      flag("evaluators", "evaluator ID(s) to apply", z.array(z.string()).optional()),
       flag(
         "lookback-days",
         "time filter: evaluate sessions from the last N days",
@@ -51,9 +51,9 @@ export const createEvaluateOnDemandHandler = (core: Core, io: AppIO) =>
       if (!flags["agent"]) {
         throw new InputValidationError("on-demand requires '--agent'");
       }
-      if (!flags["evaluator"] || flags["evaluator"].length === 0) {
+      if (!flags["evaluators"] || flags["evaluators"].length === 0) {
         throw new InputValidationError(
-          "required option '--evaluator <evaluator...>' not specified",
+          "required option '--evaluators <evaluators...>' not specified",
         );
       }
 
@@ -84,7 +84,7 @@ export const createEvaluateOnDemandHandler = (core: Core, io: AppIO) =>
       );
 
       const result = await core.eval.evaluate(
-        { traces, evaluatorIds: flags["evaluator"], groundTruth },
+        { traces, evaluatorIds: flags["evaluators"], groundTruth },
         opts,
       );
       ctx.require(JsonRendererKey).renderJson(result);
diff --git a/src/handlers/eval/ondemand/ondemand.fixture.test.tsx b/src/handlers/eval/ondemand/ondemand.fixture.test.tsx
index b1aefddc1..b309340b7 100644
--- a/src/handlers/eval/ondemand/ondemand.fixture.test.tsx
+++ b/src/handlers/eval/ondemand/ondemand.fixture.test.tsx
@@ -61,7 +61,7 @@ describe("eval ondemand evaluate (fixture-backed)", () => {
       WINDOW_START,
       "--end-time",
       WINDOW_END,
-      "--evaluator",
+      "--evaluators",
       "Builtin.Helpfulness",
     ]);
 
@@ -113,7 +113,7 @@ describe("eval ondemand evaluate (fixture-backed)", () => {
       '{"prompt":"{input}"}',
       "--dataset",
       SIMULATE_DATASET,
-      "--evaluator",
+      "--evaluators",
       "Builtin.Correctness",
       "--ingestion-wait-ms",
       isRecording() ? "150000" : "0",
diff --git a/src/handlers/eval/ondemand/ondemand.test.tsx b/src/handlers/eval/ondemand/ondemand.test.tsx
index 58991327d..56892a454 100644
--- a/src/handlers/eval/ondemand/ondemand.test.tsx
+++ b/src/handlers/eval/ondemand/ondemand.test.tsx
@@ -141,7 +141,7 @@ async function runWithRealCore(options: LogsOptions, logger = createSilentLogger
     "evaluate",
     "--agent",
     RUNTIME_ID,
-    "--evaluator",
+    "--evaluators",
     "Builtin.Helpfulness",
     "--session-ids",
     "session-1",
@@ -163,7 +163,7 @@ const BASE = [
   "evaluate",
   "--agent",
   "a-1",
-  "--evaluator",
+  "--evaluators",
   "Builtin.Helpfulness",
 ];
 
@@ -195,22 +195,22 @@ describe("eval ondemand simulate", () => {
     '{"prompt":"{input}"}',
     "--dataset",
     "/tmp/ds.jsonl",
-    "--evaluator",
+    "--evaluators",
     "Builtin.Helpfulness",
   ];
 
   test.each<[RegExp, string[]]>([
     [
       /--runtime-id/,
-      ["--payload-template", "{}", "--dataset", "/tmp/ds.jsonl", "--evaluator", "E"],
+      ["--payload-template", "{}", "--dataset", "/tmp/ds.jsonl", "--evaluators", "E"],
     ],
     [
       /--payload-template/,
-      ["--runtime-id", "r-1", "--dataset", "/tmp/ds.jsonl", "--evaluator", "E"],
+      ["--runtime-id", "r-1", "--dataset", "/tmp/ds.jsonl", "--evaluators", "E"],
     ],
-    [/--dataset/, ["--runtime-id", "r-1", "--payload-template", "{}", "--evaluator", "E"]],
+    [/--dataset/, ["--runtime-id", "r-1", "--payload-template", "{}", "--evaluators", "E"]],
     [
-      /--evaluator/,
+      /--evaluators/,
       ["--runtime-id", "r-1", "--payload-template", "{}", "--dataset", "/tmp/ds.jsonl"],
     ],
   ])("rejects when a required flag is missing (%s)", async (expected, args) => {
@@ -280,13 +280,21 @@ describe("eval ondemand evaluate validation", () => {
   test.each<[string, string[], RegExp]>([
     [
       "requires --agent",
-      ["eval", "ondemand", "evaluate", "--evaluator", "Builtin.Helpfulness", "--session-ids", "s1"],
+      [
+        "eval",
+        "ondemand",
+        "evaluate",
+        "--evaluators",
+        "Builtin.Helpfulness",
+        "--session-ids",
+        "s1",
+      ],
       /--agent/,
     ],
     [
-      "requires --evaluator",
+      "requires --evaluators",
       ["eval", "ondemand", "evaluate", "--agent", "a-1", "--session-ids", "s1"],
-      /--evaluator/,
+      /--evaluators/,
     ],
     ["rejects an empty session source", BASE, /session source/],
     [
diff --git a/src/handlers/eval/ondemand/simulate/index.tsx b/src/handlers/eval/ondemand/simulate/index.tsx
index 3e1ee7f6e..7284666e3 100644
--- a/src/handlers/eval/ondemand/simulate/index.tsx
+++ b/src/handlers/eval/ondemand/simulate/index.tsx
@@ -34,7 +34,7 @@ export const createSimulateOnDemandHandler = (core: Core, _io: AppIO) =>
       flag("user-id", "Runtime user ID", z.string().optional()),
       flag("dataset", "dataset source: local JSONL path or a dataset ID", z.string().optional()),
       flag("dataset-version", "dataset version (with a dataset ID)", z.string().optional()),
-      flag("evaluator", "evaluator ID(s) to apply", z.array(z.string()).optional()),
+      flag("evaluators", "evaluator ID(s) to apply", z.array(z.string()).optional()),
       flag(
         "ingestion-wait-ms",
         "ms to wait for span ingestion before grading (default 180000; 0 to skip)",
@@ -49,16 +49,16 @@ export const createSimulateOnDemandHandler = (core: Core, _io: AppIO) =>
       }
       if (!flags["dataset"])
         throw new InputValidationError("required option '--dataset' not specified");
-      if (!flags["evaluator"]?.length) {
+      if (!flags["evaluators"]?.length) {
         throw new InputValidationError(
-          "required option '--evaluator <evaluator...>' not specified",
+          "required option '--evaluators <evaluators...>' not specified",
         );
       }
 
       const runtimeId = flags["runtime-id"];
       const payloadTemplate = flags["payload-template"];
       const dataset = flags["dataset"];
-      const evaluatorIds = flags["evaluator"];
+      const evaluatorIds = flags["evaluators"];
 
       await withUserCancellation(async (signal) => {
         const opts = coreOptsFromCtx(ctx);
diff --git a/src/handlers/eval/online-eval/create/index.tsx b/src/handlers/eval/online-eval/create/index.tsx
index c5f60f204..7dc88f4c6 100644
--- a/src/handlers/eval/online-eval/create/index.tsx
+++ b/src/handlers/eval/online-eval/create/index.tsx
@@ -24,7 +24,7 @@ export const createCreateOnlineEvalHandler = (core: Core, io: AppIO) =>
         "the traces to evaluate (JSON DataSourceConfig; inline, file://<path>, or - for stdin), as an alternative to --agent",
         z.string().optional(),
       ),
-      flag("evaluator", "the ID(s) of the evaluators to apply", z.array(z.string()).optional()),
+      flag("evaluators", "the ID(s) of the evaluators to apply", z.array(z.string()).optional()),
       flag(
         "sampling-rate",
         "percentage of sessions to sample (0.01-100)",
@@ -64,9 +64,9 @@ export const createCreateOnlineEvalHandler = (core: Core, io: AppIO) =>
           "required option '--sampling-rate <sampling-rate>' not specified",
         );
       }
-      if (!flags["evaluator"] || flags["evaluator"].length === 0) {
+      if (!flags["evaluators"] || flags["evaluators"].length === 0) {
         throw new InputValidationError(
-          "required option '--evaluator <evaluator...>' not specified",
+          "required option '--evaluators <evaluators...>' not specified",
         );
       }
 
@@ -91,7 +91,7 @@ export const createCreateOnlineEvalHandler = (core: Core, io: AppIO) =>
           "filters",
           await source.resolveText("filters", flags["filters"]),
         ),
-        evaluatorIds: flags["evaluator"],
+        evaluatorIds: flags["evaluators"],
         evaluationExecutionRoleArn: flags["role-arn"],
         enableOnCreate:
           flags["enable-on-create"] === undefined
diff --git a/src/handlers/eval/online-eval/online-eval.test.tsx b/src/handlers/eval/online-eval/online-eval.test.tsx
index c56bfb4a9..a749fd103 100644
--- a/src/handlers/eval/online-eval/online-eval.test.tsx
+++ b/src/handlers/eval/online-eval/online-eval.test.tsx
@@ -131,7 +131,7 @@ describe("online-eval CRUDL", () => {
       CONFIG_NAME,
       "--agent",
       FIXTURE_AGENT_ID,
-      "--evaluator",
+      "--evaluators",
       FIXTURE_EVALUATOR_ID,
       "--sampling-rate",
       "10",
@@ -252,7 +252,7 @@ describe("flag validation", () => {
         "create",
         "--name",
         CONFIG_NAME,
-        "--evaluator",
+        "--evaluators",
         FIXTURE_EVALUATOR_ID,
         "--sampling-rate",
         "10",
@@ -274,7 +274,7 @@ describe("flag validation", () => {
         FIXTURE_AGENT_ID,
         "--data-source-config",
         '{"cloudWatchLogs":{"logGroupNames":["/custom"],"serviceNames":["svc"]}}',
-        "--evaluator",
+        "--evaluators",
         FIXTURE_EVALUATOR_ID,
         "--sampling-rate",
         "10",
@@ -296,7 +296,7 @@ describe("flag validation", () => {
         '{"cloudWatchLogs":{"logGroupNames":["/custom"],"serviceNames":["svc"]}}',
         "--endpoint",
         "prod",
-        "--evaluator",
+        "--evaluators",
         FIXTURE_EVALUATOR_ID,
         "--sampling-rate",
         "10",
@@ -316,7 +316,7 @@ describe("flag validation", () => {
         CONFIG_NAME,
         "--data-source-config",
         "not-json",
-        "--evaluator",
+        "--evaluators",
         FIXTURE_EVALUATOR_ID,
         "--sampling-rate",
         "10",
@@ -406,9 +406,9 @@ describe("execution role KMS scoping", () => {
       // Builtin.Correctness is backed by the hand-authored fixture carrying a
       // kmsKeyArn; Builtin.Helpfulness carries none, so this covers both arms of
       // the resolution in one create.
-      "--evaluator",
+      "--evaluators",
       FIXTURE_EVALUATOR_ID,
-      "--evaluator",
+      "--evaluators",
       "Builtin.Correctness",
       "--sampling-rate",
       "10",
@@ -442,7 +442,7 @@ describe("execution role scoping on update", () => {
       WARN_CONFIG_NAME,
       "--agent",
       FIXTURE_AGENT_ID,
-      "--evaluator",
+      "--evaluators",
       FIXTURE_EVALUATOR_ID,
       "--sampling-rate",
       "10",
diff --git a/src/handlers/eval/online-eval/update/index.tsx b/src/handlers/eval/online-eval/update/index.tsx
index 93b638abc..b2f487ce6 100644
--- a/src/handlers/eval/online-eval/update/index.tsx
+++ b/src/handlers/eval/online-eval/update/index.tsx
@@ -30,7 +30,7 @@ export const createUpdateOnlineEvalHandler = (core: Core, io: AppIO) =>
         z.string().optional(),
       ),
       flag(
-        "evaluator",
+        "evaluators",
         "the ID(s) of the evaluators to apply (replaces the existing list)",
         z.array(z.string()).optional(),
       ),
@@ -88,7 +88,7 @@ export const createUpdateOnlineEvalHandler = (core: Core, io: AppIO) =>
             "filters",
             await source.resolveText("filters", flags["filters"]),
           ),
-          evaluatorIds: flags["evaluator"],
+          evaluatorIds: flags["evaluators"],
           agent: flags["agent"],
           endpoint: flags["endpoint"],
           clearEndpoint: flags["clear-endpoint"] === "true",
diff --git a/src/handlers/project/add/online-eval/index.test.ts b/src/handlers/project/add/online-eval/index.test.ts
index 97dc789d9..9967c4b1a 100644
--- a/src/handlers/project/add/online-eval/index.test.ts
+++ b/src/handlers/project/add/online-eval/index.test.ts
@@ -65,7 +65,7 @@ describe("project add online-eval", () => {
         "x",
         "--agent",
         "agent_python_minimal",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "50",
@@ -79,7 +79,7 @@ describe("project add online-eval", () => {
         "x",
         "--log-group-name",
         "/aws/foo",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "50",
@@ -95,7 +95,7 @@ describe("project add online-eval", () => {
         "agent_python_minimal",
         "--endpoint",
         "PROD",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "10",
@@ -111,7 +111,7 @@ describe("project add online-eval", () => {
         "/aws/foo",
         "--service-name",
         "svc",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "25",
@@ -125,7 +125,7 @@ describe("project add online-eval", () => {
         "x",
         "--log-group-name",
         "/aws/foo",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "5",
@@ -141,7 +141,7 @@ describe("project add online-eval", () => {
         "x",
         "--agent",
         "agent_python_minimal",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "5",
@@ -157,7 +157,7 @@ describe("project add online-eval", () => {
         "x",
         "--log-group-name",
         "/aws/foo",
-        "--evaluator",
+        "--evaluators",
         "Builtin.Correctness",
         "--sampling-rate",
         "5",
@@ -182,7 +182,7 @@ describe("project add online-eval", () => {
       "x",
       "--log-group-name",
       "/aws/foo",
-      "--evaluator",
+      "--evaluators",
       "Builtin.Correctness",
       "--sampling-rate",
       "50",
@@ -209,7 +209,7 @@ describe("project add online-eval", () => {
         "x",
         "--agent",
         "a",
-        "--evaluator",
+        "--evaluators",
         "e",
         "--sampling-rate",
         "5",
@@ -218,8 +218,8 @@ describe("project add online-eval", () => {
   });
 
   test.each<[string, string[]]>([
-    ["missing --name", ["--log-group-name", "/x", "--evaluator", "e", "--sampling-rate", "10"]],
-    ["missing --sampling-rate", ["--name", "x", "--log-group-name", "/x", "--evaluator", "e"]],
+    ["missing --name", ["--log-group-name", "/x", "--evaluators", "e", "--sampling-rate", "10"]],
+    ["missing --sampling-rate", ["--name", "x", "--log-group-name", "/x", "--evaluators", "e"]],
     [
       "--agent and --log-group-name are mutually exclusive",
       [
@@ -229,7 +229,7 @@ describe("project add online-eval", () => {
         "a",
         "--log-group-name",
         "/x",
-        "--evaluator",
+        "--evaluators",
         "e",
         "--sampling-rate",
         "10",
@@ -237,7 +237,7 @@ describe("project add online-eval", () => {
     ],
     [
       "neither --agent nor --log-group-name",
-      ["--name", "x", "--evaluator", "e", "--sampling-rate", "10"],
+      ["--name", "x", "--evaluators", "e", "--sampling-rate", "10"],
     ],
     ["no evaluator", ["--name", "x", "--agent", "a", "--sampling-rate", "10"]],
     [
@@ -249,7 +249,7 @@ describe("project add online-eval", () => {
         "/x",
         "--endpoint",
         "PROD",
-        "--evaluator",
+        "--evaluators",
         "e",
         "--sampling-rate",
         "10",
@@ -264,7 +264,7 @@ describe("project add online-eval", () => {
         "a",
         "--service-name",
         "svc",
-        "--evaluator",
+        "--evaluators",
         "e",
         "--sampling-rate",
         "10",
diff --git a/src/handlers/project/add/online-eval/index.ts b/src/handlers/project/add/online-eval/index.ts
index a1a18740c..5ca5f16a1 100644
--- a/src/handlers/project/add/online-eval/index.ts
+++ b/src/handlers/project/add/online-eval/index.ts
@@ -33,7 +33,7 @@ export const createAddOnlineEvalHandler = (config: AddProjectResourceConfig) =>
         z.array(z.string()).optional(),
       ),
       flag(
-        "evaluator",
+        "evaluators",
         "evaluator name(s), Builtin.* IDs, or ARNs to apply",
         z.array(z.string()).optional(),
       ),
@@ -68,7 +68,7 @@ export const createAddOnlineEvalHandler = (config: AddProjectResourceConfig) =>
         endpoint: flags["endpoint"],
         logGroupNames: flags["log-group-name"],
         serviceNames: flags["service-name"],
-        evaluators: flags["evaluator"],
+        evaluators: flags["evaluators"],
         samplingRate: flags["sampling-rate"],
         description: flags["description"],
         enableOnCreate:
diff --git a/src/handlers/project/remove/index.test.ts b/src/handlers/project/remove/index.test.ts
index e691ceb83..c194161bf 100644
--- a/src/handlers/project/remove/index.test.ts
+++ b/src/handlers/project/remove/index.test.ts
@@ -137,7 +137,7 @@ describe("project remove", () => {
           "quality",
           "--agent",
           "agent_python_minimal",
-          "--evaluator",
+          "--evaluators",
           "Builtin.Correctness",
           "--sampling-rate",
           "5",