# Telegram Similar to its Twitter counterpart, the Telegram Agent monitors popular channels ranked by performance and spam activity. Every minute, it scans for new messages, triggering a similar classification pipeline that ensures comprehensive coverage of the Telegram landscape: * **Sentiment Analysis**: Messages are scored for sentiment from 0 to 10, allowing for a granular understanding of community sentiment across different channels. * **Ticker Detection**: Tickers are identified through explicit mentions or contextual inference, ensuring that emerging discussions are captured in real time. * **Further Classification**: Detected tickers undergo additional extraction and classification, providing a well-rounded view of market dynamics. For new tickers, the Researcher Agent performs the same comprehensive analysis as with Twitter, ensuring that no vital information is overlooked. This redundancy is crucial for maintaining the integrity and accuracy of the data collected. Once the data is ingested and indexed, the **Agent Journaling** AI takes over to extract key insights, including: * **Previous Performance Highlights**: Analyzing past performance to identify trends and potential future movements. * **Upcoming News**: Keeping track of significant events that may impact market sentiment or specific tickers. * **Historical Mistakes in Predictions**: Learning from past errors to refine future predictions and enhance model accuracy. * **Successful Calls**: Highlighting effective calls based on detected prices in the mentioned tickers and Telegram messages, providing a framework for evaluating the effectiveness of strategies. --- # Agent Instructions: 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: ``` GET https://usestrawberry.gitbook.io/strawberryai/product-suite/markdown/editor/telegram.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.