# 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.

Need a blog header, a social media graphic, or a presentation visual? Describe it in the conversation and your employee generates it on the spot. "Create a hero image for our Q1 report with a blue gradient and abstract data visualization." The image appears in chat, ready to download or use.

Image generation lives inside the conversation, which means your employee uses context to create better visuals. It knows your brand colors from training. It knows the topic from the current discussion. It knows the intended audience from your duties. This context makes the output more relevant than what you would get from a standalone image generator with a blank prompt.

Iterate in real time. "Make it darker." "Add the company logo in the corner." "Try a different layout." Each revision builds on the last. Your employee treats image generation as part of the workflow, not a separate tool you switch to.

Every image the employee makes is saved rather than shown once and lost. It appears inline in the conversation and lands in that employee's Drive with a stable link, so you can open it a week later, drop it into a document, or hand it to someone without generating it again. Nothing depends on a temporary link quietly expiring in the background while you were not looking.

You get a small set of controls rather than a settings panel to learn. An image can be square, portrait, or landscape, which covers a social post, a phone screen, and a page header between them, and quality can be turned up when the image is going somewhere that matters or left low while you are only trying an idea out. Each employee carries its own defaults, so the one that writes your posts can sit on landscape without changing anything for the rest of your workforce.

The part that matters most is that this is a tool the employee reaches for on its own, not a button you press. Ask for a blog post and it can write the copy and produce the header in the same task, because making an image is a step it can take the way it searches the web or writes a file. You never leave the conversation to brief a separate image tool and then carry the result back by hand.

## Generate Images Directly in the Chat

Sistava includes image generation as a native tool your AI employee can use. Describe what you need, and the agent generates the image inline in the conversation, no switching to a separate tool or uploading prompts to another service.

This integrates image creation into larger workflows. An AI employee preparing a marketing brief can generate concept visuals as part of the same task. An agent building a presentation can create diagrams and illustrations without leaving the workflow.

## Iterate in Conversation

Image generation in Sistava is conversational. If the first version is not quite right, you describe what to change and the agent generates a revised version. You can refine style, composition, content, and detail through natural language without learning prompt engineering syntax.

This back-and-forth iteration is what makes image generation actually useful in production work. Getting to a usable result takes a few exchanges rather than dozens of manually crafted prompts.

## Part of a Larger AI Workforce Capability

Image generation is one tool among many that your AI employee can use. Combined with web search, document creation, and app integrations, the agent can research a topic, write copy, and generate visuals for it, all in a single delegated task.

For teams that produce content regularly, this collapses a multi-person, multi-tool workflow into a single AI employee that can handle the full production chain from brief to finished assets.

## How It Works

**Your AI employees generate images mid-conversation, iterating based on your feedback until the visual is exactly what you need.**

Describe the image you need and your AI employee generates it on the spot, inside the same conversation where you are working. Blog headers, social media graphics, product mockups, presentation visuals, brand illustrations. You see the result immediately and can refine it with plain language. No prompt engineering knowledge required, you talk to the agent the same way you would brief a designer.

Image generation is integrated with the rest of what the agent is doing. If it is writing a blog post, it can generate a header image for each section without you switching tools. If it is preparing a pitch deck, it creates the visuals alongside the slide copy. The output saves to the agent's Drive so you can download or share it at any time.

Because the tool sits inside the conversation, iterating is just talking. Say the color is wrong, ask for the logo in the corner, or ask to see a different layout, and the next version builds on what you already agreed rather than starting from a blank prompt. Every version is kept in the employee's Drive, so an earlier attempt you liked better is still there when you change your mind.

## Use Cases

### Marketing team using an AI employee to produce campaign visuals

Describe the image and the AI agent generates it. No designer needed for first drafts or social assets.

### Content team adding visuals to every piece without a bottleneck

The AI employee generates images inline with content production. Visual and written output happen together.

### Product team using an AI agent to prototype UI concepts visually

Describe the concept and the agent generates a visual reference. Faster than wireframing by hand.

### E-commerce team generating product lifestyle images at scale

The AI employee generates styled product images on demand. No photo shoot required for variations.

## Comparison

| Before | After |
|---|---|
| Every visual asset requires a design request and a wait. | The AI employee generates images on demand as part of any workflow. |
| Visual production is a bottleneck that slows content output. | The AI agent handles image generation inline, no handoff required. |
| Stock photos don't match the specific context you need. | Generate exactly the image you need with a description. |
| Scaling visual content requires scaling the design team. | One AI employee generates unlimited images without additional cost per asset. |

## FAQ

### What image generation model does Sistava use?

Sistava uses state-of-the-art image generation models to produce high-quality results. The specific model may vary based on your plan tier. All generated images are available for download directly from the conversation.

### Can I give feedback and have the image revised?

Yes. Image generation is iterative in Sistava. After the first generation, describe what you want changed in plain language and the agent produces a new version. You can refine through as many iterations as needed.

### Who owns the images generated by my AI employee?

You own all images generated using your account. Generated images are yours to use without restriction, subject to the terms of your Sistava plan and applicable laws.

### Can the AI agent generate images as part of a larger automated workflow?

Yes. Image generation is a standard tool the agent can call autonomously. If a task requires an image, the agent generates one without being explicitly told to, then uses or delivers it as part of the broader output.

### Can my AI agent generate images as part of a conversation or task?

Yes. Image generation is available as an in-conversation tool, so your AI employee can create visuals on request without switching to a separate app. Generated images appear inline in the chat.

### Where do the images my AI employee creates get saved?

Every generated image is saved into that employee's Drive with a stable link, as well as appearing inline in the conversation where it was made. You can open it later, reuse it in a document, or share it with someone without generating it a second time. Nothing relies on a temporary link that expires.

### Can I choose the shape of a generated image, like square or landscape?

Yes. An image can be square, portrait, or landscape, which covers a social post, a phone screen, and a page header respectively. You can ask for a shape in the conversation, and each employee also carries its own default shape and quality that you can change from its Tools tab.

### Do I need to set anything up before my employee can make images?

No. Image generation is switched on for every employee from the moment you hire it, with no key to paste, no account to connect, and no design tool to install. Describe what you want in the conversation and the image comes back in the same thread.

> My content agent writes the post and generates the header image in one go. I used to spend 20 minutes in Canva after every article. Now I just download and publish.
>
> Sophie D., Content Manager · media team

## Where Image Generation fits

Image Generation 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: Image Generation](/en/guide/equip/tools)

## 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.
- [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.
- [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.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)