What was just said
The prototype passes conversation history into the prompt so a follow-up has more than one message to work with.
A chat should feel like one conversation, not a series of fresh starts. Baatwise is an early-stage project exploring how context can make the next reply more relevant.
People add details as they go: a constraint, a preference, a correction. We’re exploring how a conversational assistant can bring those signals into the next answer.
The prototype passes conversation history into the prompt so a follow-up has more than one message to work with.
It includes settings for tone, level of detail, language, and response format.
The current experiment can extract text from a PDF and include it alongside a question.
Baatwise grows out of CogniChat, a public Streamlit prototype. Today, it combines Gemini responses with conversation history, preference settings, a simple focus heuristic, and optional PDF input.
Bring a question, a follow-up, or a document you want to discuss.
The prototype assembles recent conversation and saved preferences as context for the model.
The code is open to inspect. We’re at the beginning and learning what to build next.
EARLY PROTOTYPE · NOT A PUBLIC BETA · NO CUSTOMER OR PERFORMANCE CLAIMS
The current focus heuristic is rule-based; it is an experiment, not a trained attention model.
Baatwise brings an everyday Indian word into a simple idea: a useful AI chat should keep track of what the conversation is about. The visual identity follows the same thought—one continuous line, with room for the next turn.
Baatwise is a working brand name. Company, trademark, and domain availability have not been legally cleared.
Take a look at the code and follow the experiment as it develops.