Why does AI chat usually give you wrong answers about documents?
Most AI document tools summarize your file first, then answer questions from that summary. This is fast and cheap, but it means the AI is answering from a lossy compression of your document, not the document itself. Details, nuance, and anything the summarizer deemed unimportant are gone.
The other common failure is fabricated citations. When a model does not know which page something came from, it guesses. Students trust the citation, look up the page, and find nothing there. This is a subtle but serious reliability problem.
Ask Max is built differently. The full text of your document is sent to the model with every query. Max is instructed to cite only page boundaries that actually exist in the parsed text, and to acknowledge uncertainty when it does not know the exact location of a claim.
How does Ask Max work?
The moment you open a document in Recitare, the full parsed text is available for chat. Here is the end-to-end flow:
Open a document
Upload a PDF, DOCX, TXT, PPTX, image, or paste a URL. Recitare parses the full text and inserts page markers (--- Page 1 ---, --- Page 2 ---) so the model knows exactly where each page begins.
Open the chat panel
Click the chat icon in the toolbar. The panel slides in on the right. Your document is already loaded, no extra upload step.
Ask anything
Type any question: "What methodology did they use?", "Summarize the limitations section", "Find every mention of dopamine", "What is the author's main argument?" Max reads the entire document to answer.
Get a cited answer
Max responds with the answer and [Page X] references for every claim. Click a citation to jump directly to that page in your document.
Keep asking
Follow-up questions carry full conversation context. Max remembers everything you've discussed in the current session, so you can drill down, push back, or ask for clarification without repeating yourself.
Does Max actually read the whole document?
Yes, and this is the technical detail that matters most. Ask Max is powered by Gemini 2.5 Flash with a 1 million token context window. One million tokens is roughly 750,000 words, or about the length of three full textbooks. In practice, this means Max can fit any document you would realistically upload: undergraduate papers, PhD theses, technical manuals, entire course readers.
For documents longer than 20,000 characters (around 5,000 words), Recitare uses context caching. Your document is cached with Google's API for 30 minutes. Subsequent questions in the same session skip the re-processing cost and come back faster. This is entirely invisible to you. The chat just gets snappier as the session goes on.
Context window comparison
How accurate are the citations?
Recitare's PDF parser inserts explicit page markers into the text as it processes each document: --- Page 12 ---. These markers are included in the text sent to Gemini, so the model knows the exact page boundary of every sentence. When Max cites [Page 12], it is referencing a real boundary in your document, not estimating.
Max is also instructed to express uncertainty honestly. If the relevant content spans multiple pages or Max cannot pinpoint the exact page, it will say so rather than fabricate a confident but wrong citation.
- Citations are grounded in explicit page markers from the parser, not inferred
- Max acknowledges uncertainty instead of guessing
- Every answer links to verifiable text in your document
- No hallucination of facts not present in the source
What is Ask While Listening?
One of the most common friction points in active reading is the moment you want to ask a question but don't want to stop your listening session to type. Ask While Listening solves this.
A floating "raise your hand" button appears in the bottom corner of the screen whenever TTS playback is active. Tap it and:
Playback pauses instantly
The TTS stops at the exact sentence it was reading. Your position is saved.
Chat panel opens
Type your question. Max answers with the full document context, not just the section you were listening to.
Dismiss and resume
Close the chat panel and TTS picks up from the exact sentence where it paused. No scrubbing, no losing your place.
Ask While Listening is available on Reader ($5/mo) and Pro ($18/mo) plans, where TTS playback is API-powered and supports precise sentence-level pause and resume.
How does Ask Max compare to ChatGPT and NotebookLM?
AI document chat is not new, but the implementation details matter enormously for accuracy and workflow.
| ChatGPT | NotebookLM | Ask Max | |
|---|---|---|---|
| Context window | 128K tokens | ~500K tokens | 1M tokens |
| Page citations | Sometimes, often wrong | Yes (passage-level) | Yes, parser-grounded |
| Reads whole doc | Truncated for long docs | Yes | Yes |
| TTS + chat together | No | No | Yes (Ask While Listening) |
| Conversation memory | Yes | Yes | Yes |
| Integrated reading env | No (separate tool) | Partial | Yes (same screen) |
The key difference is context. NotebookLM and Ask Max both read the full document, but Ask Max is purpose-built for reading flow: chat lives alongside the document, TTS pauses for questions, and citations link directly to the page in view.
What is happening under the hood?
For those who want the technical picture:
Document parsing
PDFs are parsed client-side with pdfjs-dist. DOCX, TXT, and PPTX files are parsed server-side. All formats produce plain text with --- Page N --- markers. Images are OCR'd with Tesseract.js.
Gemini 2.5 Flash with context caching
The full document text + conversation history is sent to Gemini 2.5 Flash on every request. Documents over 20K characters are cached for 30 minutes, giving a 75% input token cost reduction on repeat queries.
Citation grounding
The system prompt instructs Max to cite [Page X] using the --- Page N --- markers in the document text. The model is trained to prefer explicit evidence over inference and to express uncertainty when it cannot locate the exact page.
Conversation history
Each API call to /api/chat includes the full message history from the current session. The model receives: system prompt + document text + prior Q&A pairs + new user question. This allows genuine multi-turn conversations.
Who is Ask Max for?
Students reading dense papers
Ask Max to explain a concept before you read it, then ask follow-up questions as you go. Never get stuck on jargon again.
Researchers doing literature reviews
Upload a paper and ask "what does this add that the 2022 Ioannidis study doesn't cover?" in seconds. Triage dozens of papers without reading each one in full.
Auditory learners using TTS
Listen to a lecture or paper while commuting, then ask clarifying questions mid-listen without losing your place.
Professionals reading reports
Ask "what does this say about Q3 performance?" or "find the risk factors section" without manually scanning a 60-page PDF.
Frequently asked questions
Does Max actually read the whole document?
Yes. Max uses Gemini 2.5 Flash with a 1 million token context window, which fits roughly 750,000 words, more than War and Peace. Your entire document is included in the prompt, not a summarized excerpt. This means Max can answer questions about a specific footnote on page 84 just as accurately as questions about the introduction.
How accurate are the page citations?
Very accurate. Max is instructed to cite [Page X] using the page markers that Recitare's PDF parser inserts into the text. When Max says "see Page 12", it is referencing the actual page boundary from your document. If Max is not confident about which page something appeared on, it will say so rather than hallucinate a citation.
Do follow-up questions remember the conversation?
Yes. Every message in the chat panel is sent with the full conversation history, so Max remembers what you asked before. You can say "tell me more about that" or "how does that relate to what you said earlier" and Max will follow the thread. The conversation builds on itself like talking to a tutor who has been in the room the whole time.
What is Ask While Listening?
Ask While Listening is a floating button that appears during TTS playback. Tap it and playback pauses so you can type a question. Max answers in the chat panel, and when you dismiss the answer, playback resumes from exactly where it stopped. It means you never have to choose between listening and asking. You do both in sequence.
How many questions can I ask per day?
Free users get 5 chat messages per day. Paid subscribers (Reader at $5/month and Pro at $18/month) get unlimited chat with a soft fair-use cap of 1,000 messages per month, a limit virtually no one hits in normal use.
Does it work with all document types?
Yes. Document chat works with every format Recitare supports: PDFs, DOCX files, TXT files, PowerPoint slides (PPTX), images processed via OCR, and web content added via URL. The parsed text from all formats flows through the same chat pipeline.
What is context caching and why does it matter?
For documents over 20,000 characters (~5,000 words), Recitare caches the document context with Google's API for 30 minutes. This means your second, third, and subsequent questions in a session cost 75% less to process than the first. It also makes follow-up responses faster because the model does not re-read the full document every time.
Can Max answer questions about charts or figures in my PDF?
Max can discuss chart data and figure descriptions when that information is represented as text in your document (captions, data tables, surrounding prose). For visual figures that exist only as images in the PDF, use the Snap-to-Explain Snap-to-Explain: draw a rectangle over the figure and Max will analyze it at 300 DPI via vision AI.