# Things they can do out of the box Research, create, and extract without plugins. 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. Every AI employee arrives with built-in capabilities. Web search delivers real-time information from the live internet. Web scraping extracts structured data from any page. Image generation creates visuals directly in the conversation. These capabilities combine with skills to cover marketing, sales, support, research, writing, and data analysis. Because these are built in, there is nothing to install, configure, or maintain. Research is what most people reach for first. Ask a question and your employee searches the live web, opens the pages it finds, strips out the ads and navigation, and comes back with an answer and its sources instead of a list of links. When you want the page itself rather than a summary, the scraper pulls the full content, including from sites that only render properly inside a browser. Documents you hand over are read the same way, so a PDF, a spreadsheet, or a slide deck attached to a message becomes usable text automatically, tables and all. What comes out of a task is usually a real file rather than a wall of chat text. Ask for a spreadsheet, a report, a deck, or an export and you receive an actual .xlsx, .docx, .pptx, .csv, or .pdf, filed into your employee's Drive and ready to send on. Presentations arrive as native slides with layouts, charts, images, tables, and speaker notes, and PDFs can be plain reports or fully designed pages with proper print typography. Hand back a file you already have and your employee revises it rather than rebuilding it from nothing. Visual work happens in the same conversation. Describe an image and it is generated on the spot, with your brand context already in the room, so you can say make it darker or add the logo and keep iterating instead of starting a fresh prompt somewhere else. Short video clips generate the same way and land in Drive, ready for a social cut, an ad concept, or a quick product demo. Nothing here is a separate subscription you go and set up. Some capabilities go places you cannot. Share a Google Meet, Zoom, or Microsoft Teams link and your employee joins the call as a named participant with its own name and avatar, keeps a speaker-tagged transcript, and answers out loud when somebody addresses it by name. Someone still has to admit it from the lobby, exactly like any other guest. When the call ends, the transcript is saved to Drive and a summary of decisions, owners, and action items appears in chat without you asking for it. Finding people and businesses has its own shortcut. A premium prospect database lets an employee filter by role, seniority, industry, company size, and location and reveal verified work contact details, and a curated network of real businesses inside Sistava gets checked before the open internet when you need a vendor or a partner. The set of capabilities also grows without you administering it, because an employee can list what it already has, search the catalog for the rest, switch things on, and send you a connection link when a real login is genuinely needed. Two more are on the way and are not usable yet: a sandboxed code interpreter for running real calculations on your data, and importing a ready-made skill package from a GitHub repository or a URL. ## At a Glance - **Built-in** No plugins needed - **Real-time** Live web data - **On-demand** Image generation ## Benefits ### Live web search Your AI agent searches the live web, reads the results, filters out noise, and synthesizes a summary tailored to your question. Current data, not stale training knowledge. ### Web scraping Point your agent at any page and it extracts clean, structured data: product listings, pricing tables, contact directories, article archives. The crawler follows links across entire domains. ### Image creation Describe a visual and your AI employee creates it on the spot. Blog headers, social graphics, presentation visuals. Iterate in real time with natural language feedback. ## How It Works **Every AI employee comes with built-in web search, web scraping, and image generation so they can research, gather data, and create visual assets without extra setup.** Web search lets your AI agents pull current information from the internet during any task. A research agent can scan competitor pricing, a support agent can look up the latest documentation for a third-party tool, and a content agent can gather real data before writing. Results are used in context, not dumped into a chat window for you to sort through. Web scraping and crawling let your AI employees extract structured data from any public page. Point an agent at a list of company websites and it returns clean, organized output you can act on. Image generation gives your agents the ability to produce visuals on demand, whether that's a product mockup, a social graphic, or a diagram to include in a report. None of this is a plugin you install, which is why it combines inside a single task instead of forcing you through separate stops. One request can search the web, pull a competitor's pricing page, compare it against a spreadsheet already in Drive, generate a chart image, and hand back a finished document. You did not wire that pipeline together and you are not paying attention to which capability runs when. You asked for the outcome and the employee picked its own route to it. ## Use Cases ### Research any topic with live web search Ask your AI employee to research a competitor, a market, or a technical topic. They search the web in real time and return synthesized findings, not cached snapshots. ### Extract data from any website Point your employee at a webpage and ask them to pull pricing, contact info, or structured data. Web scraping runs without you writing a single line of code. ### Generate images on demand Ask for diagrams, social graphics, concept art, or product mockups. Your employee generates images inline during the conversation and delivers them ready to use. ### Run code to process data or automate logic Your employee writes and executes code to clean a dataset, run calculations, or transform files. Results come back immediately, with the code visible for review. This one is on the roadmap rather than live: the sandboxed code interpreter is not usable yet, so today an employee reasons over your data and produces the file instead of running the script. ## FAQ ### What can an AI employee do out of the box, before I connect anything? Straight after hiring, an employee can search the live web, read and extract any public page, read documents you attach, produce real Excel, Word, PowerPoint, CSV, and PDF files, generate images, and make short video clips. It can also join a Google Meet, Zoom, or Microsoft Teams call and take notes. None of that requires a plugin, an API key, or a connected account from you. ### Do I need to install plugins or buy separate tools for research, files, and images? No. Web search, web scraping, document creation, and image generation are built into every AI employee and switched on the day you hire it. There is no add-on marketplace to shop in and no separate search or design subscription to run alongside. Connected apps such as Gmail or your CRM are a different thing entirely and get added only when you want an employee acting inside a specific account. ### Can an AI employee actually make a spreadsheet or a presentation, not just describe one? Yes. Ask for a spreadsheet, report, deck, or export and you get a genuine .xlsx, .docx, .pptx, .csv, or .pdf saved to the employee's Drive. Presentations come back as native slides with layouts, charts, images, tables, and speaker notes, and Excel files can carry real formulas rather than static numbers. You can also hand back a file you already have and ask for a revision instead of a rebuild. ### Can an AI employee join my Zoom or Google Meet call? Yes. Share the link for a Google Meet, Zoom, or Microsoft Teams call and your employee joins as a named participant with its own name and avatar, not a generic notetaker bot. Someone still has to admit it from the lobby, the same as any guest. It keeps a speaker-tagged transcript, answers out loud when addressed by name, and drops a summary of decisions and action items into chat once the call ends. ### How current is the information an AI employee gives me? As current as the web, because search runs live at the moment you ask rather than relying on what a model absorbed months ago. The employee opens the pages it finds, filters out the navigation and ads, and cites the sources it used so you can check them yourself. For one specific page you can point it straight at the URL and it reads the whole thing, including sites that only render properly in a browser. ### Can it pull data off a website without me writing code? Yes. Give an employee a URL and describe what you want, whether that is pricing, contact details, job listings, or article text, and it returns clean structured output rather than raw HTML. It copes with pages that need a browser to render, and it can follow links across a site when one page is not enough. No scraping tool, no selectors, and nothing to install on your side. ### Which of these capabilities are not available yet? Two are on the roadmap and cannot be used today. A sandboxed code interpreter will let an employee run real Python to crunch numbers and transform data files, so you get a computed result instead of a careful estimate. Importing a ready-made skill package from a GitHub repository or a URL is also planned, and until it ships you build skills inside the workspace instead. ### Do I have to set tools up for my AI employee, or can it handle that itself? It handles most of it. Ask for a capability the way you would ask a colleague, and the employee checks what it already has, searches the catalog for the rest, turns things on, and sends you a connection link when a real login is genuinely required. You keep control of the account approvals, but you are not clicking through an admin panel to get moving. It cannot disconnect your accounts on its own. ## Built-In From Day One Most platforms make you connect a search API, configure a scraping tool, and find a separate image service before your agent can do anything useful on the open web. With Sistava, these capabilities are built in. Every AI employee you hire has access to them immediately, without any configuration from you. These capabilities combine with your agent's memory and connected apps to power workflows that would otherwise require multiple specialized tools. Search the web, extract data from a page, run it through your CRM, and generate an image for the output report, all inside a single agent task. ## How It Works 1. **Search The Live Web**: Your AI agents pull current information from the internet in real time and use it directly in the task at hand. 2. **Scrape And Extract Data**: Point an agent at any public page and it returns clean, structured data you can pipe into reports, databases, or workflows. 3. **Generate Images On Demand**: AI employees create visual assets, mockups, and graphics as part of any task, no separate design tool required. > I asked my research agent to build a competitor matrix. It searched 12 sites, pulled pricing tables, and handed me a formatted spreadsheet in 8 minutes. > > Anita M., Strategy Director ยท SaaS company ## Features 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. - [AI Employee 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. Free accounts get a small one-time allowance, then can continue with paid access or open-web research. - [Presentation Builder](/en/features/capabilities/presentation_builder): A dedicated tool for turning your content into a finished slide deck: give an employee a report, a set of notes, or a topic, and it plans the slide structure, writes the talking points, and lays out a real .pptx file you can open in PowerPoint or Google Slides. - [Audio Transcriber](/en/features/capabilities/audio_transcriber): Give any AI employee an uploaded recording and get a saved written transcript back in the same conversation. It handles common audio and video files, including voice memos, call recordings, webinars, and video walkthroughs. - [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. - [Import a Skill from GitHub or a URL](/en/features/capabilities/skill_import_from_repo): Paste a link to a GitHub repository or a URL that hosts an Anthropic-style Skill package, and your employee will import the whole thing directly instead of you rebuilding it by hand in the Create Skill drawer. This is on our roadmap and is not active yet: the option appears in the Skills toolbar and in the Create Skill drawer today, but importing does not run until we ship it. - [Free AI Tools](/en/features/capabilities/free_ai_tools): Try a real AI employee before you hire one. Sistava's free tools let anyone chat, with no signup and no card, with a named persona built for one job: writing ad copy, drafting an NDA, naming a business, building a pricing strategy, and 50+ more. Each tool runs up to a monthly message cap, then offers to continue the same conversation inside a full account. - [Free App Page Read](/en/features/capabilities/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. - [Self-Service Tool Management](/en/features/capabilities/self_service_tool_management): Ask your employee for a tool the same way you'd ask a coworker. It checks what it already has, searches the catalog for the rest, adds and turns tools on, and hands you a connection link when a real login is needed, all inside the conversation you're already having. ## Explore - [Every feature](/en/features) - [Browse AI employees](/en/agents) - [Pricing](/en/pricing)