> For the complete documentation index, see [llms.txt](https://docs.rierino.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rierino.com/data-science/genai-models/useful-checks.md). # Useful Checks ## "Model not found" error * [ ] Check if the agent id in request matches the GenAI model record id * [ ] Check if the GenAI model is configured to be allowed for the specific runner (or all runners) * [ ] Check if the runner LangChain handler has a "domain" specificiation that doesn't match the model's domain configuration * [ ] Check if the "channel" in request URL path matches the specific runner ## Agent not remembering chat history * [ ] Check if the agent has "memory" parameter configured for an existing state manager on the runner * [ ] Check if the agent memory state manager is a shared state (e.g. not in-memory), if there are multiple replicas running for the runner {% hint style="info" %} Only agents with memory utilize instructions & tools, so it is recommended to havethe "memory" parameter defined except for lightweight chat use cases. {% endhint %} ## Agent not executing tool as expected * [ ] Ask the agent to provide the request body and the response details (such as errors) it is receiving from calling the tool * [ ] If the tool is a saga flow: * [ ] Try to access saga as an API with the same request and review response * [ ] Check to make sure that the saga is allowed to run on the runner of the agent * [ ] Check to make sure that the user making the request has rights to execute the saga (if it is restricted) * [ ] Check to make sure that the saga returns a "message" field in its response * [ ] Check to make sure that the saga input schema is mapped accurately for the flow logic * [ ] If the tool is a state processor: * [ ] Check to make sure that the target state is available on the runner of the agent * [ ] Check to make sure that the user making the request has rights to access the state (if it is restricted) * [ ] If the tool is a system processor: * [ ] Check to make sure that the target system is available on the runner of the agent and has access details configured correctly * [ ] Create a simple saga to test system accessibility through an API --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.rierino.com/data-science/genai-models/useful-checks.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.