## Introduction The [coexistence of CALM and the NLU-based system](/content/docs/pro/calm-with-nlu/migrating-from-nlu/index.html) depends on a routing mechanism, that routes messages based on their content to either system. You can choose between two different router components: 1. [`IntentBasedRouter`](/content/docs/reference/config/components/coexistence-routers/#intentbasedrouter/index.html): The predicted intent of the NLU pipeline is used to decide where the message should go. 2. [`LLMBasedRouter`](/content/docs/reference/config/components/coexistence-routers/#llmbasedrouter/index.html): This component leverages an LLM to decide whether a message should be routed to the NLU-based system or CALM. You can only use one of the router components in your assistant. ## IntentBasedRouter [​](/content/docs/reference/config/components/coexistence-routers/#intentbasedrouter/index.html) The `IntentBasedRouter` uses the predicted intent from the NLU components and routes the message dependent on that intent. The router needs to be added to the pipeline in your config file. ### Important The position of the `IntentBasedRouter` needs to be _after_ the NLU components and _before_ the Command Generators. #### Example Configuration Depending on the other components you choose, your config file could look like the following. **config.yml** ```yaml recipe: default.v1 language: en pipeline: - name: WhitespaceTokenizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 - name: LogisticRegressionClassifier - name: IntentBasedRouter # additional configuration parameters - name: CompactLLMCommandGenerator llm: model_group: openai_llm policies: - name: FlowPolicy - name: RulePolicy - name: MemoizationPolicy max_history: 10 - name: TEDPolicy ``` **endpoints.yml** ```yaml model_groups: - id: openai_llm models: - provider: openai model: gpt-5-mini-2025-08-07 timeout: 7 max_tokens: 256 ``` ### Configuration of the IntentBasedRouter [​](/content/docs/reference/config/components/coexistence-routers/#configuration-of-the-intentbasedrouter/index.html) The following mandatory configuration parameters need to be configured: - `nlu_entry`: - `sticky`: List of intents which should route to the NLU-based system in a sticky fashion. - `non_sticky`: List of intents which should route to the NLU-based system in a non sticky fashion. - `calm_entry`: - `sticky`: List of intents which should route to CALM in a sticky fashion. A full configuration of the `IntentBasedRouter` could for example look like the following. **config.yml** ```yaml pipeline: # ... - name: IntentBasedRouter nlu_entry: sticky: - transfer_money - check_balance - search_transactions non_sticky: - chitchat calm_entry: sticky: - book_hotel - cancel_hotel - list_hotel_bookings # ... ``` ### Handling missing intents [​](/content/docs/reference/config/components/coexistence-routers/#handling-missing-intents/index.html) If an intent is predicted by an NLU component, but the intent is not part of any of the intents listed in the `IntentBasedRouter` and the routing session is currently not set, the message is routed according to the following rules: 1. We route to CALM if given the intent any of the NLU triggers of flows are activated (see [NLU triggers documentation](/content/docs/reference/primitives/starting-flows/#nlu-trigger/index.html)). 2. We route to the NLU-based system otherwise. ## LLMBasedRouter [​](/content/docs/reference/config/components/coexistence-routers/#llmbasedrouter/index.html) The `LLMBasedRouter` uses an LLM, by default `gpt-5-mini-2025-08-07`, to decide whether a message should be routed to the NLU-based system or CALM. ### Important In order to use this component for your coexistence solution, you need to add it as the _first_ component to your pipeline in the config file. #### Example Configuration Depending on the other components you choose, your config file could look like the following. **config.yml** ```yaml recipe: default.v1 language: en pipeline: - name: LLMBasedRouter nlu_entry: sticky: ... non_sticky: ... calm_entry: sticky: handles everything around hotel bookings llm: model_group: openai_llm # additional configuration parameters - name: WhitespaceTokenizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 - name: LogisticRegressionClassifier - name: CompactLLMCommandGenerator llm: model_group: openai_llm policies: - name: FlowPolicy - name: RulePolicy - name: MemoizationPolicy max_history: 10 - name: TEDPolicy ``` **endpoints.yml** ```yaml model_groups: - id: openai_llm models: - provider: openai model: gpt-5-mini-2025-08-07 timeout: 7 max_tokens: 256 ``` ### Configuring the LLMBasedRouter component [​](/content/docs/reference/config/components/coexistence-routers/#configuring-the-llmbasedrouter-component/index.html) The `LLMBasedRouter` component has the following configuration parameters: - `nlu_entry`: - `sticky`: Describes the general NLU-based system functionality. By default the value is `"handles everything else"`. - `non_sticky`: Describes the functionality of the NLU-based system that should not result in sticky routing to the NLU-based system. By default the value is `"handles chitchat"`. - `calm_entry`: - `sticky` (required): Describes the functionality implemented in the CALM system of the assistant. - `llm`: Configuration of the llm. - `prompt`: File path to the prompt template (a jinja2 template) to use. You can modify the prompt by writing your own prompt as a jinja2 template and provide it to the component as a file: ```yaml pipeline: # ... - name: LLMBasedRouter prompt: prompts/llm-based-router-prompt.jinja2 # ... ``` ### Handling failures and downtime of the LLM [​](/content/docs/reference/config/components/coexistence-routers/#handling-failures-and-downtime-of-the-llm/index.html) If the LLM predicts an invalid answer, e.g. another character than `A`, `B`, or `C`, or if the API of the LLM is down and the LLM cannot be reached, the message is routed to the NLU-based system in a sticky fashion.