diff --git a/README.md b/README.md
index 0b2b11c..b5c6da9 100644
--- a/README.md
+++ b/README.md
@@ -14,7 +14,7 @@ pip install qiskit-transpiler-service
 
 By default, the package tries to authenticate to IBM Quantum services with the defined Qiskit API token, and uses your token from the `QISKIT_IBM_TOKEN` environment variable or from the file `~/.qiskit/qiskit-ibm.json` (under the section `default-ibm-quantum`).
 
-*Note*: This library requires Qiskit 1.0 by default.
+_Note_: This library requires Qiskit 1.0 by default.
 
 ## How to use the library
 
@@ -24,37 +24,37 @@ The following examples demonstrate how to transpile circuits using the Qiskit tr
 
 1. Create a circuit and call the Qiskit transpiler service to transpile the circuit with `ibm_sherbrooke` as the `backend_name`, 3 as the `optimization_level`, and not using AI during the transpilation.
 
-    ```python
-    from qiskit.circuit.library import EfficientSU2
-    from qiskit_transpiler_service.transpiler_service import TranspilerService
+   ```python
+   from qiskit.circuit.library import EfficientSU2
+   from qiskit_transpiler_service.transpiler_service import TranspilerService
 
-    circuit = EfficientSU2(101, entanglement="circular", reps=1).decompose()
+   circuit = EfficientSU2(101, entanglement="circular", reps=1).decompose()
 
-    cloud_transpiler_service = TranspilerService(
-        backend_name="ibm_sherbrooke",
-        ai=False,
-        optimization_level=3,
-    )
-    transpiled_circuit = cloud_transpiler_service.run(circuit)
-    ```
+   cloud_transpiler_service = TranspilerService(
+       backend_name="ibm_sherbrooke",
+       ai='false',
+       optimization_level=3,
+   )
+   transpiled_circuit = cloud_transpiler_service.run(circuit)
+   ```
 
-*Note:* you only can use `backend_name` devices you are allowed to with your IBM Quantum Account. Apart from the `backend_name`, the `TranspilerService` also allows `coupling_map` as parameter.
+_Note:_ you only can use `backend_name` devices you are allowed to with your IBM Quantum Account. Apart from the `backend_name`, the `TranspilerService` also allows `coupling_map` as parameter.
 
-2. Produce a similar circuit and transpile it, requesting AI transpiling capabilities by setting the flag `ai` to `True`:
+2. Produce a similar circuit and transpile it, requesting AI transpiling capabilities by setting the flag `ai` to `'true'`:
 
-    ```python
-    from qiskit.circuit.library import EfficientSU2
-    from qiskit_transpiler_service.transpiler_service import TranspilerService
+   ```python
+   from qiskit.circuit.library import EfficientSU2
+   from qiskit_transpiler_service.transpiler_service import TranspilerService
 
-    circuit = EfficientSU2(101, entanglement="circular", reps=1).decompose()
+   circuit = EfficientSU2(101, entanglement="circular", reps=1).decompose()
 
-    cloud_transpiler_service = TranspilerService(
-        backend_name="ibm_sherbrooke",
-        ai=True,
-        optimization_level=1,
-    )
-    transpiled_circuit = cloud_transpiler_service.run(circuit)
-    ```
+   cloud_transpiler_service = TranspilerService(
+       backend_name="ibm_sherbrooke",
+       ai='true',
+       optimization_level=1,
+   )
+   transpiled_circuit = cloud_transpiler_service.run(circuit)
+   ```
 
 ### Using the AIRouting pass manually
 
@@ -108,9 +108,9 @@ The synthesis respects the coupling map of the device: it can be run safely afte
 
 The following synthesis passes are available from `qiskit_transpiler_service.ai.synthesis`:
 
-- *AICliffordSynthesis*: Synthesis for [Clifford](https://docs.quantum.ibm.com/api/qiskit/qiskit.quantum_info.Clifford) circuits (blocks of `H`, `S` and `CX` gates). Currently up to 9 qubit blocks.
-- *AILinearFunctionSynthesis*: Synthesis for [Linear Function](https://docs.quantum.ibm.com/api/qiskit/qiskit.circuit.library.LinearFunction) circuits (blocks of `CX` and `SWAP` gates). Currently up to 9 qubit blocks.
-- *AIPermutationSynthesis*: Synthesis for [Permutation](https://docs.quantum.ibm.com/api/qiskit/qiskit.circuit.library.Permutation#permutation) circuits (blocks of `SWAP` gates). Currently available for 65, 33, and 27 qubit blocks.
+- _AICliffordSynthesis_: Synthesis for [Clifford](https://docs.quantum.ibm.com/api/qiskit/qiskit.quantum_info.Clifford) circuits (blocks of `H`, `S` and `CX` gates). Currently up to 9 qubit blocks.
+- _AILinearFunctionSynthesis_: Synthesis for [Linear Function](https://docs.quantum.ibm.com/api/qiskit/qiskit.circuit.library.LinearFunction) circuits (blocks of `CX` and `SWAP` gates). Currently up to 9 qubit blocks.
+- _AIPermutationSynthesis_: Synthesis for [Permutation](https://docs.quantum.ibm.com/api/qiskit/qiskit.circuit.library.Permutation#permutation) circuits (blocks of `SWAP` gates). Currently available for 65, 33, and 27 qubit blocks.
 
 We expect to gradually increase the size of the supported blocks.
 
@@ -126,9 +126,9 @@ For sub-circuit to be synthesized by the AI synthesis passes, it must lay on a c
 
 To complement the synthesis passes we also provide custom collection passes for Cliffords, Linear Functions and Permutations that can be imported from `qiskit_transpiler_service.ai.collection`:
 
-- *CollectCliffords*: Collects `Clifford` blocks as `Instruction` objects and stores the original sub-circuit to compare against it after synthesis.
-- *CollectLinearFunctions*: Collects blocks of `SWAP` and `CX` as `LinearFunction` objects and stores the original sub-circuit to compare against it after synthesis.
-- *CollectPermutations*: Collects blocks of `SWAP` circuits as `Permutations`.
+- _CollectCliffords_: Collects `Clifford` blocks as `Instruction` objects and stores the original sub-circuit to compare against it after synthesis.
+- _CollectLinearFunctions_: Collects blocks of `SWAP` and `CX` as `LinearFunction` objects and stores the original sub-circuit to compare against it after synthesis.
+- _CollectPermutations_: Collects blocks of `SWAP` circuits as `Permutations`.
 
 These custom collection passes limit the sizes of the collected sub-circuits so that they are supported by the AI synthesis passes, so it is recommended to use them after the routing passes and before the synthesis passes to get a better optimization overall.
 
diff --git a/ai-transpiler-demo.ipynb b/ai-transpiler-demo.ipynb
index 6ae40f9..d4c0c42 100644
--- a/ai-transpiler-demo.ipynb
+++ b/ai-transpiler-demo.ipynb
@@ -212,7 +212,7 @@
     "\n",
     "qiskit_lvl3_transpiler_service = TranspilerService(\n",
     "    backend_name=\"ibm_torino\",\n",
-    "    ai=False,\n",
+    "    ai='false',\n",
     "    optimization_level=3,\n",
     ")"
    ]
@@ -281,7 +281,7 @@
    "source": [
     "qiskit_lvl3_ai_transpiler_service = TranspilerService(\n",
     "    backend_name=\"ibm_torino\",\n",
-    "    ai=True,\n",
+    "    ai='true',\n",
     "    optimization_level=3,\n",
     ")"
    ]
diff --git a/documentation-examples.ipynb b/documentation-examples.ipynb
index 76e8c5d..494179d 100644
--- a/documentation-examples.ipynb
+++ b/documentation-examples.ipynb
@@ -22,7 +22,7 @@
     "\n",
     "cloud_transpiler_service = TranspilerService(\n",
     "    backend_name=\"ibm_sherbrooke\",\n",
-    "    ai=False,\n",
+    "    ai='false',\n",
     "    optimization_level=3,\n",
     ")\n",
     "transpiled_circuit_no_ai = cloud_transpiler_service.run(circuit)"
@@ -50,7 +50,7 @@
     "\n",
     "cloud_transpiler_service = TranspilerService(\n",
     "    backend_name=\"ibm_sherbrooke\",\n",
-    "    ai=True,\n",
+    "    ai='true',\n",
     "    optimization_level=1,\n",
     ")\n",
     "transpiled_circuit_ai = cloud_transpiler_service.run(circuit)"
diff --git a/qiskit_transpiler_service/transpiler_service.py b/qiskit_transpiler_service/transpiler_service.py
index ac98514..9741123 100644
--- a/qiskit_transpiler_service/transpiler_service.py
+++ b/qiskit_transpiler_service/transpiler_service.py
@@ -27,7 +27,7 @@
 """
 
 import logging
-from typing import Dict, List, Union
+from typing import Dict, List, Union, Literal
 
 from qiskit import QuantumCircuit
 
@@ -42,8 +42,8 @@ class TranspilerService:
 
     :param optimization_level: The optimization level to use during the transpilation. There are 4 optimization levels ranging from 0 to 3, where 0 is intended for not performing any optimizations and 3 spends the most effort to optimize the circuit.
     :type optimization_level: int
-    :param ai: Specifyies if the transpilation should use AI or not, defaults to True.
-    :type ai: bool, optional
+    :param ai: Specifies if the transpilation should use AI or not, defaults to True.
+    :type ai: str, optional
     :param coupling_map: A list of pairs that represents physical links between qubits.
     :type coupling_map: list[list[int]], optional
     :param backend_name: Name of the backend used for doing the transpilation.
@@ -57,7 +57,7 @@ class TranspilerService:
     def __init__(
         self,
         optimization_level: int,
-        ai: bool = True,
+        ai: Literal['true', 'false', 'auto'] = 'true',
         coupling_map: Union[List[List[int]], None] = None,
         backend_name: Union[str, None] = None,
         qiskit_transpile_options: Dict = None,
diff --git a/qiskit_transpiler_service/wrappers/transpile.py b/qiskit_transpiler_service/wrappers/transpile.py
index d3014a4..053b126 100644
--- a/qiskit_transpiler_service/wrappers/transpile.py
+++ b/qiskit_transpiler_service/wrappers/transpile.py
@@ -11,7 +11,7 @@
 # that they have been altered from the originals.
 
 import logging
-from typing import Dict, List, Union
+from typing import Dict, List, Union, Literal
 
 import numpy as np
 from qiskit import QuantumCircuit, QuantumRegister, qasm2, qasm3
@@ -43,7 +43,7 @@ def transpile(
         optimization_level: int = 1,
         backend: Union[str, None] = None,
         coupling_map: Union[List[List[int]], None] = None,
-        ai: bool = True,
+        ai: Literal['true', 'false', 'auto'] = 'true',
         qiskit_transpile_options: Dict = None,
         ai_layout_mode: str = None,
     ):
diff --git a/tests/test_transpiler_service.py b/tests/test_transpiler_service.py
index fc8af7f..4661ab0 100644
--- a/tests/test_transpiler_service.py
+++ b/tests/test_transpiler_service.py
@@ -32,7 +32,7 @@
 @pytest.mark.parametrize(
     "optimization_level", [1, 2, 3], ids=["opt_level_1", "opt_level_2", "opt_level_3"]
 )
-@pytest.mark.parametrize("ai", [False, True], ids=["no_ai", "ai"])
+@pytest.mark.parametrize("ai", ['false', 'true'], ids=["no_ai", "ai"])
 @pytest.mark.parametrize(
     "qiskit_transpile_options",
     [None, {"seed_transpiler": 0}],
@@ -56,7 +56,7 @@ def test_rand_circ_backend_routing(optimization_level, ai, qiskit_transpile_opti
 @pytest.mark.parametrize(
     "optimization_level", [1, 2, 3], ids=["opt_level_1", "opt_level_2", "opt_level_3"]
 )
-@pytest.mark.parametrize("ai", [False, True], ids=["no_ai", "ai"])
+@pytest.mark.parametrize("ai", ['false', 'true'], ids=["no_ai", "ai"])
 @pytest.mark.parametrize(
     "qiskit_transpile_options",
     [None, {"seed_transpiler": 0}],
@@ -85,7 +85,7 @@ def test_qv_backend_routing(optimization_level, ai, qiskit_transpile_options):
     ],
 )
 @pytest.mark.parametrize("optimization_level", [1, 2, 3])
-@pytest.mark.parametrize("ai", [False, True], ids=["no_ai", "ai"])
+@pytest.mark.parametrize("ai", ['false', 'true'], ids=["no_ai", "ai"])
 @pytest.mark.parametrize("qiskit_transpile_options", [None, {"seed_transpiler": 0}])
 def test_rand_circ_cmap_routing(
     coupling_map, optimization_level, ai, qiskit_transpile_options
@@ -108,7 +108,7 @@ def test_qv_circ_several_circuits_routing():
 
     cloud_transpiler_service = TranspilerService(
         backend_name="ibm_brisbane",
-        ai=True,
+        ai='true',
         optimization_level=1,
     )
     transpiled_circuit = cloud_transpiler_service.run([qv_circ] * 2)
@@ -129,7 +129,7 @@ def test_qv_circ_wrong_input_routing():
 
     cloud_transpiler_service = TranspilerService(
         backend_name="ibm_brisbane",
-        ai=True,
+        ai='true',
         optimization_level=1,
     )
 
@@ -138,7 +138,7 @@ def test_qv_circ_wrong_input_routing():
         cloud_transpiler_service.run(circ_dict)
 
 
-@pytest.mark.parametrize("ai", [False, True], ids=["no_ai", "ai"])
+@pytest.mark.parametrize("ai", ['false', 'true'], ids=["no_ai", "ai"])
 def test_transpile_layout_reconstruction(ai):
     n_qubits = 27