# Free App Page Read Paste a link into any free chat tool on the site and the persona actually reads that page before replying. It pulls the clean text from the page and uses it to answer, so you do not have to copy and paste the content yourself. Each anonymous session gets a handful of free reads before it asks you to sign up for more. When a visitor pastes a URL into one of the free, no-signup chat tools, the persona fetches that page and reads it before responding. There is no separate button or command: just drop a link in the message and the reply reflects what is actually on the page. The fetch happens at zero marginal cost using a pure-Python extraction engine that strips a page down to its clean article text, discarding navigation, ads, and boilerplate. The only cost is the LLM tokens needed to read that extracted text, so the feature stays available on the free, anonymous tier without a credit card. Each anonymous session gets 5 free page reads, tracked separately from the 5 free chat messages the session gets overall, in the same 30-day window. A read only counts against that cap when the page is actually fetched and produces usable text; a blocked or empty page costs the visitor nothing. Once the cap is reached, the persona tells the visitor plainly that they have hit the limit for this session and that signing up unlocks unlimited page reads on a more capable model, while still offering to keep the conversation going if the visitor pastes the key text themselves. The free reader is deliberately the lightweight half of what the product can actually do. It runs one engine only, a pure-text extractor with no browser behind it, so it reads ordinary articles, blog posts, and docs pages well but cannot render JavaScript. A page that needs its script to run before content appears, a single-page app, a dashboard behind client-side rendering, will often come back empty here. Inside the real product the same idea becomes a four-engine pipeline that adds a headless browser and, for paired desktop users, a real browser fallback, so a signed-up employee can read pages this free tool cannot. ## What counts as a page read Any http or https link in a visitor's message to a free chat tool triggers a read attempt, the first time that link's content is needed for a reply. Only the first link in a message is used; if a page has no extractable article text, blocks automated readers, or the request fails, it does not count against the session's cap because nothing was actually read. The fetch itself is bounded on every side: it gives up after 6 seconds, stops downloading a page body past 2MB, and truncates the extracted text at 6,000 characters with a visible truncation notice if a page runs long. None of that is configurable per visitor; it applies to every free app the same way, so one oversized or slow page can never stall a chat turn or blow up the prompt sent to the model. ## Free tier limit and what happens after Anonymous sessions get 5 page reads before the tool stops fetching new links, counted in the same 30-day session window as the 5 free chat messages. Past that point the persona is explicit about the limit rather than silently ignoring the link or pretending to browse it, and it invites the visitor to either sign up for unlimited reads on a more capable model or paste the relevant text directly so the conversation can continue. Signing up does not just remove the cap. It also switches the visitor's employee from the free reader's single always-on extractor to the product's full web-page-reading tool, which adds a headless browser pass for JavaScript-heavy pages and, for a desktop-paired employee, a fallback through the user's own real browser as a last resort. ## Reading, not browsing or searching This is a single read of one page you name, not a search. The persona never goes looking for a URL on its own and never follows links found inside the fetched page; it only reads the exact address you pasted. If you want it to consider a second page, paste that link in a later message, using another read from the same 5-per-session allowance. ## How It Works **A link in your message becomes real content the persona can reason about** The chat backend scans each incoming message for the first http or https link. If one is found, it is fetched and passed through a content extractor before your persona ever writes a word back, so the reply is grounded in the real page, not a guess about what the link probably says. Safety is built into the fetch: only public web addresses are allowed, so a link that points at an internal network address, a cloud metadata endpoint, or any other private target is refused automatically. If a page cannot be reached or produces no readable text, the persona says so honestly and asks you to paste the key text instead of pretending to have read it. The read counter is tracked per anonymous session, not per account, so it resets naturally with a new session. Every fetch failure is handled quietly: it never breaks the conversation, it just falls back to asking for the text directly. ## Use Cases ### Ask about a blog post or article without copying it in Paste the article URL directly into the chat and ask your question; the persona reads the page and answers based on the actual text. ### Get a quick take on a product or docs page Share a product page or documentation link in a free tool session to get a summary or specific answer grounded in that page's real content. ### Compare a page against your own needs Drop in a competitor page, job listing, or pricing page link and ask the persona to evaluate it against what you are looking for, without leaving the chat to read it yourself first. ## FAQ ### Do I need an account to use this? No. Page reading works in the free, anonymous chat tools with no signup, up to 5 reads per session in a rolling 30-day window. Signing up removes that cap and moves you to a more capable model. ### What happens if the page cannot be read? If the site blocks automated readers, the page is empty, or the request fails for any reason, the persona tells you it could not read the link and asks you to paste the key text yourself instead of guessing at the content. A failed read like this does not count against your 5-read cap. ### Can I use this to read internal or private URLs? No. Only ordinary public web addresses are fetched. Links that resolve to private, internal, or reserved network addresses are refused before any request is made. ### Will it work on a JavaScript-heavy site or single-page app? Not reliably. The free reader uses one extraction engine with no browser behind it, so it reads ordinary HTML pages well but cannot execute a page's JavaScript. A site that renders its content client-side may come back empty. The signed-up product tool adds a headless browser specifically to handle that case. ## Where Free App Page Read fits Free App Page Read is part of Things they can do out of the box. Every AI employee ships with built-in abilities that work out of the box. Search the live web for real-time information, scrape and crawl any website for structured data, and generate images directly in conversation. No plugins to install, no APIs to configure. - [Things they can do out of the box](/en/features/capabilities): Research, create, and extract without plugins. ## Read the guide - [Guide: Free App Page Read](/en/guide/capabilities/web-scraper) ## More in Capabilities - [Web Search](/en/features/capabilities/web_search): Every AI employee can search the live internet for current information and answer with sources, no setup required. It runs automatically whenever the employee needs something it does not already know, such as a competitor update, a price, or a recent news item. Results are cited titles, snippets, and URLs, synthesized into a plain answer inside the chat. - [Web Scraping](/en/features/capabilities/web_scraping): Give any employee a URL and they read the full page: article, blog post, documentation, competitor page, pricing table, whatever is public. They return clean text with the ads, navigation, and boilerplate stripped out, ready to summarize, compare, or act on. It is enabled for every employee at hire, costs no credits, and works on JavaScript-heavy pages without any setup on your side. - [Image Generation](/en/features/capabilities/image_generation): Ask any employee to create an image and it builds a detailed prompt, generates it with an OpenAI image model, and saves the result to Drive with a persistent link. Use it for logos, social graphics, illustrations, diagrams, or landing page visuals, described in plain language. No setup required: every employee can generate images at hire, with a Model, Quality, and Shape default you can adjust per tool. - [Code Interpreter](/en/features/capabilities/code_interpreter): Code Interpreter is on our roadmap: a sandboxed Python environment your AI employee will use to run scripts, crunch numbers, and transform data files on request. Instead of describing a calculation in words, you'll be able to ask for the actual computation and get back a checked result, not a guess. It is not available yet. - [Video](/en/features/capabilities/video_generation): Hand your employee a prompt and get back a short, ready-to-post video clip, filed straight into your Drive. Built for social cuts, ad concepts, and quick product demos. Editing your own footage is coming next. - [B2B Marketplace](/en/features/capabilities/b2b_marketplace): A network of real, vetted businesses living inside Sistava. Ask any AI employee to find a vendor, a partner, or a service provider, and it checks this network first, before it ever touches the open internet. Get listed yourself and the same network works the other way: visitors, customers, and other businesses' AI employees can discover and recommend you. - [Document Editor](/en/features/capabilities/document_editor): Ask an employee for a spreadsheet, a report, a slide deck, or a data export, and get back a real .xlsx, .docx, .pptx, .csv, or .pdf file, not a wall of text pasted into chat. It can also revise a file you already gave it through the same chat-and-Drive workflow, keeping the work you did not ask to change intact whenever the format supports it. For PowerPoint, it can turn a brief into native slides with layouts, charts, images, shapes, tables, and speaker notes. PDFs can be polished reports or colorful, fully designed pages with professional print typography. Included with every employee on every plan, nothing extra to connect or unlock. - [Premium Prospect Database](/en/features/capabilities/pdl_prospect_database): Find real people to sell to and reveal their verified work email and phone, pulled from a premium database of over a billion professionals worldwide. Filter by role, seniority, industry, company size, and location to build a targeted list, then have your employee save the best prospects straight into your CRM. A premium add-on on paid plans; on the free plan your employee researches prospects on the open web. - [Send an Employee to Your Meeting](/en/features/capabilities/meeting_attender): Share a Google Meet, Zoom, or Microsoft Teams link and your employee joins the call as a named participant. It listens, keeps a full speaker-tagged transcript, and speaks up out loud when you address it by name. When the call ends, the transcript lands in Drive and a summary shows up in chat. - [Get a Live Meeting Transcript](/en/features/capabilities/meeting_live_transcript): Your AI employee joins a Google Meet, Zoom, or Microsoft Teams call and captures a full transcript as people speak, tagged by speaker and timestamped. Ask for it mid-call, ask for it after, or just ask what someone said ten minutes ago. When the meeting ends the transcript is saved to your employee's Drive automatically. - [Meeting Summary](/en/features/capabilities/meeting_summary): When a meeting your employee attended ends, it writes a summary and drops it in chat automatically: what got decided, who owns what, and the action items. No need to ask for a recap, it is already waiting when you check in. - [Document Text Extraction](/en/features/capabilities/text_extraction): When you attach a document to a chat message or upload it for training, your employee turns it into readable text on its own. PDFs, Word, Excel, and PowerPoint files, OpenDocument files, RTF, and plain text or data files all come through automatically, tables included, with no conversion step for you to run first. ## Explore - [Every feature](/en/features) - [Hire an AI employee](/en/market) - [Pricing](/en/pricing)