NotebookLM just supercharged custom chats with a new upgrade

For anyone who’s been using NotebookLM to digest massive PDFs or brainstorm via the Audio Overview feature, you probably ran into a big limitation: the chat customization field. Until now, if you wanted to tell Google’s research tool how to talk to you, you were boxed into a meager 500 characters.

That changes now. Google has expanded the limit to a massive 10,000 characters, 20 times the previous limit. Now you have plenty of space to set tone, context, goals, constraints, and personality without butchering your instructions. The NotebookLM team confirmed the update on X.

This update affects the “Configure notebook” settings in the chat interface, where you set the AI’s goal, style, and role. In late October 2025, Google polished the underlying engine to improve context understanding, but that power was often bottlenecked by the short instruction leash. With this restriction lifted, the model’s improved reasoning capabilities can actually stretch their legs.

This change lands on the heels of a major upgrade cycle NotebookLM has been pushing through over the past months. The service recently improved how long conversations are retained, how much context the model can handle, and how coherent responses remain over time.

Those improvements already laid a stronger foundation, but the 10,000-character limit seems like the missing piece. Before, Custom mode was too limited for anyone working on long projects. If you wanted to build a steady editorial assistant, set rules for a research partner, or create a writing companion with a unique voice, there just wasn’t enough space.

Here are a few sample prompts Google used to demonstrate the expansion:

• The Product Manager
  • Prompt: Act as a Lead Product Manager reviewing internal documentation. Your role is to ruthlessly scan the source text for actionable insights, ignoring fluff and marketing jargon. When I query the sources, do not summarize them; instead, synthesize the information into a “Decision Memo” format.
    Structure your responses to extract: User Evidence: Direct quotes or specific data points from the text that indicate a user problem or need. Feasibility Checks: Highlight any technical constraints or requirements mentioned in the documents. The “Blind Spots”: Explicitly list what is missing from the source text (e.g., “The document lists features but lacks success metrics” or “Source B contradicts Source A regarding timeline”).
    Use bullet points for speed. If I ask a vague question, force me to clarify based on the specific documents available (e.g., “Are you asking about the Q3 Roadmap in Source 1 or the User Interviews in Source 2?”).
• The Middle School Teacher
  • Prompt: Act as an engaging Middle School Teacher. Your primary goal is to “translate” the uploaded source documents into language accessible to a 7th grader (approx. 12 years old). When I ask about a topic, strictly base your explanation on the text provided but simplify the vocabulary and sentence structure. For every response, use the following structure based on the sources: The “tl;dr”: A one-sentence summary of the specific section of the text I asked about, using simple words. Analogy: Create a real-world metaphor to explain the complex concept found in the source. Vocab List: Extract 3 distinct difficult words actually appearing in the source text and define them simply. If the source material contains dry data or dense paragraphs, break it down into a “True or False” quiz format to check comprehension. Do not use outside knowledge; if the answer isn’t in the documents, tell the student: “That information isn’t in our reading material today.”
• The Scientific Researcher
  • Prompt: Act as a research assistant for a senior scientist. Your tone must be strictly objective, formal, and precise. Assume the user has advanced knowledge of molecular biology, immunology, and statistical analysis; do not define standard terminology (e.g., “p-value,” “CRISPR,” “cytokine”) or simplify complex concepts. Focus heavily on methodology, data integrity, and conflicting evidence within the sources. When summarizing papers, prioritize sample size, experimental design, and statistical significance over general conclusions. Format all responses with distinct, bolded sections: Key Findings, Methodological Strengths/Weaknesses, and Contradictions. Always cite specific sections of the source text using [1], [2] format. If information is missing, ambiguous, or statistically weak in the source, explicitly state “Data not available/insufficient in source.” Avoid all conversational filler.

This update doesn’t touch the platform’s upload limits or daily usage caps, so the broader framework of NotebookLM remains unchanged. Still, the way people use the tool will likely change. Longer prompts allow for richer personas, clearer task instructions, and fewer generic replies.