Tag:

  • How to Create Instagram Posts with Grok Bot and the Orauria Prompt Gallery

    How to Create Instagram Posts with Grok Bot and the Orauria Prompt Gallery

    This post continues Orauria’s practical Grok Bot series. Earlier posts explained what Grok Bot is and how Orauria extends it, the MCP and cloud computer architecture, and turning one blog post into social posts. This one is narrower and more hands-on: how to take a ready-made prompt from the Orauria prompt gallery, hand it to a Grok Bot that has the Orauria MCP connected, and get finished Instagram images back in the chat. The story below is an illustrative example, not a client case, and Orauria has no official partnership with xAI or Grok Bot.

    What we say about Grok Bot comes from the public docs at docs.x.ai: Use the computer and apps, checked on November 13, 2026. What we say about the gallery and the MCP comes from orauria.com/gallery and orauria.com/mcp on the same day. What we tested: in a Grok Bot that already had the Orauria MCP connected, we called list_models, get_wallet, generate_image and get_task, using a filled-in prompt from the gallery’s “daily posts” set, and got back a finished 3:4 slide (shown in the last image of this post). What we did not test end to end: re-adding the connector from scratch through the Add a custom connector form, and attaching a product photo as a reference image through the MCP. Those steps are described from the docs and flagged where they appear. The laptop screens in the photos show real screenshots of orauria.com, not the Grok Bot app.

    Key takeaways. The gallery is a library of tested prompt sets, many of them built for Instagram carousels, each with a “Copy prompt” button and fill-in fields in [square brackets]. The Orauria MCP gives an agent six tools: generate_image, generate_video, chat, list_models, get_wallet and get_task. Connect it once in Grok Bot, paste a gallery prompt with your brand details, and the Bot generates, polls and hands you the image. You still review every slide and you still press Post on Instagram yourself.

    Candle shop owner looking stuck at night while her laptop shows a real Orauria gallery page for an Instagram carousel prompt set

    A good product and an empty feed

    Meet Linh. She is an example character: a candle maker in her late twenties who runs a two-person shop in Hội An. She pours soy candles into amber jars, sells a few at the counter to tourists and most of them through Instagram direct messages. Her product photos are honest phone shots on the workbench. Her feed has gaps of two or three weeks.

    She knows what good Instagram looks like. She saves carousels from bigger brands: a bold hook on slide one, a clean product shot, a lifestyle scene, a “how to use it” slide, a call to action. What she cannot do is make them. Design tools give her a blank canvas. Image generators give her a blank text box. Every evening she starts from nothing, writes a vague prompt like “candle on a table, aesthetic”, gets something that looks like a stock photo of someone else’s candle, and gives up.

    The problem was never the product. It was the starting point. Linh did not need more creativity at 10 pm. She needed a prompt someone had already engineered for a carousel, with the places for her product clearly marked, and a way to run it without opening five tabs.

    That is exactly the gap between a prompt library and an agent. The Orauria gallery gives her the engineered starting point. A Grok Bot with the Orauria MCP connected gives her the hands to run it, check it and run it again.

    Shop owner holding a phone with a slide generated through the Orauria MCP, laptop showing a real Orauria gallery prompt page

    What effective looks like, and how to measure it

    We are not going to promise follower numbers or engagement rates. We have no data on Linh, because Linh is an example, and your account is not hers. What we can do is show what “working” looks like and how you can measure it on your own account.

    Effective, in this workflow, means three things. First, you can go from “I need a post” to a finished, on-brand set of slides in one sitting, without starting from a blank prompt. Second, the slides look like they belong to one campaign: same palette, same typography, same product. Third, you, not the Bot, decide what goes live.

    Measure the workflow, not the prompt. Keep a simple sheet for three weeks with these columns:

    • Time to a postable set: minutes from opening the gallery to having slides you would actually post.
    • Keep rate: of the images the Bot generated, how many you kept without edits, kept with a fix, or threw away.
    • Retries per slide: how many times you asked the Bot to regenerate before a slide was right. Text errors and a redrawn product are the usual reasons.
    • Credits per kept slide: the Orauria MCP bills your Orauria wallet at Studio prices, so check get_wallet before and after a session and divide by the slides you kept.
    • Posting rhythm: how many days you posted per week, before and after.
    • Your own Instagram Insights: saves, shares and profile visits per post, compared with your older posts. Look at the trend over weeks, not one post.

    If time to a postable set drops and your posting rhythm rises while the keep rate stays decent, the workflow is doing its job. If you spend more time fixing slides than you used to spend making them, simplify: fewer slides per set, a simpler prompt set, or Studio for the fiddly ones.

    Owner at her home desk in the evening, laptop showing the real Orauria MCP connection page

    How it works: a prompt library, an MCP connector and an agent loop

    Three pieces fit together here. It helps to know what each one does before you set anything up.

    The gallery: engineered prompt sets

    The gallery (also available in Vietnamese, Chinese, Korean and Japanese) is a browsable library. You can filter by categories such as Ads & Product, Brand & Logo, Videos, Illustration & 3D, Posters & Visuals, Photoshoot, Portraits, Wallpaper and Product Marketing, search prompts by keyword, and page through results 10, 20 or 50 at a time. On November 13, 2026, a keyword search for “instagram” returned 36 matching prompts.

    Many recent entries are full sets rather than single images, with titles like “From 3 Product Photos to a Scroll-Stopping Instagram Carousel That Converts” or “From One Olive Oil Photo to a Full Daily-Post Campaign”. Open one and you see every image in the set, the model it was made with (often tt-image-2.5), the number of media, and buttons for Share, Copy prompt and Gen Image. You can also save sets you like.

    The important part is how the prompts are written. Each one starts with “Replace everything in [ ] with your product info; attach your product photo as the reference image.” Then every brand-specific detail is a field with an example, such as [TOOL NAME: e.g. Orauria AI], [HEADLINE LINE 1: e.g. One product photo] or [PRODUCT NAME CAPS: e.g. "DRIZZLE" EXTRA VIRGIN OLIVE OIL]. The layout, typography, colors, lighting and composition are already fixed. Product prompts also include an instruction to keep the product exactly as in the reference photo instead of redrawing it. You only change what is yours.

    The Orauria MCP: six tools billed to your wallet

    MCP (Model Context Protocol) is the standard way an AI agent calls outside tools. According to orauria.com/mcp, the Orauria MCP server lives at the site’s /api/mcp path, authenticates with an sk- API key you create under Profile → API keys, and exposes six tools:

    • generate_image: create an image from a prompt and a model; returns a task.
    • generate_video: start a video job.
    • chat: talk to an Orauria language model, billed per token.
    • list_models: see the available image, video and chat models.
    • get_wallet: check remaining credits before you generate.
    • get_task: poll an image or video job until it is final and has a result URL.

    The page says usage is billed to your Orauria wallet at the same prices as Studio, and that a call fails with an error if your credit is too low. The page shows setup for Cursor, Claude and Codex. It does not mention Grok Bot, which is why the Grok Bot steps below come from Grok Bot’s own docs.

    Grok Bot: the agent loop around the tools

    A Grok Bot is an agent with its own cloud computer, connected apps and memory. When you ask for an image, it does not just forward your text. It reads your request, picks the tool, calls generate_image, waits, calls get_task until the job is final, downloads the result, and can look at it before it shows you. If a headline is misspelled, it can regenerate. That loop is what turns “paste prompt, wait, refresh, download” into one request.

    Two more Grok Bot features matter here. A skill is a saved set of instructions, so your brand fields and rules do not have to be retyped every time. A routine runs on a schedule, which you might use later for a weekly batch. And through all of it, the human stays in the loop: the Bot generates and proposes, and you choose what to post.

    Owner in a cafe, laptop showing the real list of six tools the Orauria MCP exposes

    Setup: from the gallery to your first slide in seven steps

    Here is the path Linh follows. Steps 2 and 3 are described from the docs; we tested steps 4 to 7 with a connector that was already in place.

    1. Create an Orauria account and an API key. Sign in at orauria.com, open Profile → API keys, create a key and copy the sk-… value. It is shown only once. Make sure your wallet has credit.
    2. Add the Orauria MCP to Grok Bot. Grok Bot’s docs say that in the desktop app you choose Add a custom connector at the bottom of Connect apps, enter a Name, and pick the type Remote HTTPS, which takes a Server URL with optional HTTP headers. Use a name like orauria, the server URL https://orauria.com/api/mcp, and the header Authorization: Bearer sk-… with your key. Choose Add plugin to save. (The Orauria page shows the URL with http://; Grok Bot expects a public HTTPS address, so use https://.)
    3. Do not paste your key into the chat. The docs also say a Bot can add an MCP server for you if you ask in chat. That is convenient for servers that use a sign-in, but a header key typed into a conversation sits in that conversation. Put the key in the connector form instead.
    4. Check the connection. In a new chat, ask: “Using the Orauria connector, list the image models and check my wallet.” The Bot should call list_models and get_wallet and answer with a model list and a credit balance. If it says the app is missing or needs auth, open Connect apps and check the connector’s status.
    5. Pick a prompt set from the gallery. Filter by Ads & Product or Product Marketing, or search “instagram” or “carousel”. Choose a set whose structure fits your story, not just one whose colors you like. Open it and use Copy prompt for the slide you want.
    6. Fill in the brackets and send it. Paste the prompt into the chat and replace each [FIELD: e.g. …] with your own value, or ask the Bot to do it from a short brand note. Tell it the model and ratio, for example: “Generate this with tt-image-2.5 at 3:4, one image, then show me the result.”
    7. Review, regenerate, download. The Bot polls get_task until the image is final and returns it. Check spelling, product shape, extra hands and text you did not ask for. Ask for a fix in plain words. When a slide is right, download it and post it yourself.

    In our test, a filled-in hook slide from the olive oil “daily posts” set came back as a 3:4 image with the headline, the calendar card and the wordmark spelled exactly as written. The tool response also included an estimated credit cost for the call, which is useful for the “credits per kept slide” column.

    Pitfalls to expect.

    • The product reference. Gallery prompts are written for a product photo attached as a reference image. In our test we described the product in words instead, which works for a demo but not for a real product, because a model will invent label details. Passing a reference image through the MCP’s params was not part of our test; if your product must look exact, generate those slides in Orauria Studio with the photo attached, or confirm with Orauria which parameter to use.
    • Leftover example values. If you skip a bracket, the model happily prints the example, such as “Orauria AI” or “DRIZZLE”, on your slide. Ask the Bot to list every bracket and your value before it generates.
    • Credits. Every generate call spends wallet credit, including the bad ones. Ask the Bot to check get_wallet before a batch and to stop after a set number of images.
    • Exact text. Keep on-image text short. Long sentences are where spelling errors appear.
    • Rights and claims. Only use your own product photos and claims you can back up. Do not copy another brand’s name or logo into a prompt.
    • Posting. In this workflow the Bot does not post to Instagram. It hands you files. Publishing stays a human action.
    Owner smiling with coffee while the laptop shows a real Instagram slide generated from a gallery prompt via the Orauria MCP

    The optimization journey: from v1 to v3

    Linh’s first week is clumsy, which is normal. What matters is how the setup improves. Here is an illustrative path.

    v1: one prompt, pasted by hand

    She copies the hook slide prompt from an Instagram carousel set, pastes it into the chat with her values typed inline, and asks for one image. The first result is beautiful but says “Orauria AI” in the corner, because she forgot one bracket. The second is right. She posts it with a phone shot as slide two.

    Her lesson: the gallery solves the blank page, but the brackets are a checklist, not decoration.

    v2: a skill with her brand fields

    She asks the Bot to save a skill called “Linh IG set”. It holds her shop name, palette, the short product names she uses, the tone of her headlines and a few rules:

    • Before generating, list every bracket in the prompt with the value you will use, and wait for “ok”.
    • Use tt-image-2.5 at 4:5 or 3:4 unless I say otherwise; one image per call.
    • Check get_wallet first and stop after eight images in one session.
    • After each result, check the spelling of every on-image word against the prompt and say if anything differs.
    • Never post anywhere. Give me the files and a caption draft.

    Now she can say “make the hook and the product slide from this gallery set for the cedar candle” and get a read-back first, then the images. Leftover example text disappears, because the Bot catches it at the read-back.

    Her lesson: the skill turns her taste into rules the Bot applies every time.

    v3: a weekly batch with a review step

    Once the keep rate is steady, she adds a Sunday routine. It asks her which product is the focus that week, picks two prompt sets she has marked as favorites, generates a hook slide and a product slide for each, writes caption drafts and posts a short summary in the chat with the images and the credits used. She reviews on Monday morning, regenerates one slide, and schedules the posts herself.

    We describe this routine from the docs, not from testing this exact setup. A routine that generates images spends credits without you watching, so give it a hard image limit, and keep the reference-image caveat above in mind for products that must look exact.

    Her lesson: automation is worth it only after the manual version is reliable. She did not start with a routine. She started with one slide.

    What to try this week

    Open the Orauria gallery and save three prompt sets whose structure fits your product. Create an sk- key, add the Orauria MCP in Grok Bot as a Remote HTTPS connector with the key in the header, and confirm it with a list_models and get_wallet check. Generate one hook slide from one set, with every bracket filled. Fix it once, post it yourself, and start the three-week sheet: time to a postable set, keep rate, retries, credits per kept slide and posting rhythm. When three posts in a row feel easy, save your brand fields as a skill. Only then think about a weekly routine.

    For more on the pieces behind this workflow, read the MCP, cloud computer and Studio architecture, how to build a weekly social posting routine and how to build a multi-bot team with an Orauria creative path. If you want a prompt library, an MCP or a content pipeline built around your own products and brand, send Orauria a brief and we will help you design it.

  • What Grok Bot Is, and How Orauria Extends It for Product Creative

    What Grok Bot Is, and How Orauria Extends It for Product Creative

    If you already brief work, sort a calendar, or watch a Slack channel in Grok Bot, you have felt the difference between an assistant that talks and an agent that can act. Product creative is still a different job. Listing images, ratio variants, and short product videos need models, credits, and a pipeline you can trust — not one more loose prompt.

    This article is a map, not a partnership announcement. Grok Bot facts come from public pages on x.ai and docs.x.ai, checked on 11 November 2026 (Asia/Saigon, UTC+7). Orauria facts come from Orauria’s own site, including the MCP page, What is Orauria, and Orauria là gì. We describe how the two systems can fit together on paper. We do not claim an official partnership with xAI, and we do not claim that Orauria MCP has already been verified end-to-end inside Grok Bot. A connection tutorial will come only after that test.

    Key takeaways. Grok Bot is an AI teammate with a persistent cloud computer, skills, routines, and Connect apps — including a documented way to add a custom MCP server. Orauria already ships Studio plus an MCP server whose tools generate images and video and bill a credit wallet. The cleanest intended path is to add that server as a Remote HTTPS connector with an Authorization header; a second path is to open Studio in the Bot’s browser when you need a visual UI. Until the connector is tested, treat the first path as documented design, not a finished how-to.

    Official Grok Bot interface in three panels: chat and voice, the shared cloud computer, and Connect apps as described in xAI documentation.

    What Grok Bot is — public facts only

    xAI describes Grok Bot as a proactive AI teammate: an agent with access to a real computer in the cloud, so it can do the kinds of work a person can do on a machine. The overview is on x.ai/bot and in the Grok Bot documentation. Chat is the main interface. You can also start a voice call or send a voice note. The same docs say you can work with Bots on desktop, on mobile, in Slack, or on X.

    That combination is the useful starting point for ecommerce teams. You are not only asking a model for copy. You are handing work to an agent that can keep going after you close the laptop.

    A shared cloud computer and a team of Bots

    Under the hood, your Bots share a persistent cloud computer with a browser, a filesystem, and a terminal. Files, sign-ins, and browser sessions persist between tasks, and work continues while your own laptop is closed. The documentation on using the computer and apps is explicit about the sharing model: every Bot on your account uses the same computer. Browser cookies, signed-in sessions, files, and command-line credentials are visible to every Bot you run. The computer is assigned to your user account, not to one Bot. Each Bot gets its own screen, so several Bots can use browser and desktop tools in parallel, but those screens are separate work surfaces, not separate security boundaries. Durable project files belong in the shared workspace at /workspace.

    You can also run more than one Bot. Official materials describe Bots that message each other, work in a group chat, hand work along, and bring you in to approve, edit, or send something back. That is the collaboration model, not a promise that every workflow is already built for your catalog.

    Skills, routines, and Connect apps

    Grok Bot turns a successful task into a repeatable process in two parts, as described in the skills and routines documentation (that page was last updated 9 November 2026). A skill is a reusable set of instructions for how to do a task: when to use it, required inputs, the sequence of work, how to validate the result, what to return, and what requires approval. A routine tells one Bot when to run a workflow — on a schedule, or when something happens, such as a Slack message, a GitHub, Linear, Sentry, or PagerDuty event, an email, or a webhook. Routines run in the cloud while your laptop is closed. They also have published rate limits: all of your routines together can run up to 300 times an hour, and each routine up to 200 times an hour.

    Bots work more reliably when they use structured app connections rather than only clicking through a website. The overview mentions everyday tools such as Slack, Notion, Drive, and Teams. The computer-and-apps documentation goes further on what a connected app can do, including Google Calendar, Sheets, Docs, Slack, Gmail, Stripe, an X plugin, 1Password, and an Email address for your Bots at mail.grokbot.com. Connected apps belong to the account you used to sign in to Grok Bot and are available to every Bot you run.

    Custom tools are part of the same picture. The official overview states that Grok Bot supports custom tooling, so it can interact with any MCP or API. The Grok Bot 101 guide (11 September 2026) says Grok Bot supports the same MCP servers, plugins, and skills as Cursor. To add a server that is not in the catalog, the computer-and-apps documentation tells you to open Connect apps, choose Add a custom connector, and pick a type: Remote HTTPS takes a server URL, with optional HTTP headers and an OAuth Client ID; Command takes a command and its arguments. You can also ask a Bot to add an MCP server by URL or by a command that runs on its computer.

    Two safety notes from the same public docs will matter later in this series. Do not paste passwords or API keys into ordinary chat; Grok Bot’s documented path is a Vault, a Secure Form, or a secret card. And because the computer is shared, a login or file you leave there is available to your other Bots.

    Side-by-side: official Grok Bot chat and routines on the left, Orauria Studio packshots, generation history, and product apps on the right.

    The product-creative work you still have to attach

    None of the above makes Grok Bot a product photography studio. That is not a criticism. It is a boundary. Grok Bot is strong at intake, coordination, and repetition: a brief in chat, a routine every morning, a mention in Slack, a handoff between specialist Bots, a pause for your approval. Those are real advantages for a merchandising or marketing team.

    Selling a physical product still asks for a different layer. You need a consistent set of packshots, not one pretty frame. You need 1:1 and 9:16 variants from the same SKU. You often need a short video after the stills are clean. You need to know which model you called, whether the wallet still has credit, and how to wait for a long video job without guessing. We have written about that production mindset in pieces such as node thinking in the Workflow Builder — the point here is simply that the agent needs a tool with a contract, not only a browser window and a prompt.

    If you do not attach that layer, the Bot will improvise: scrape a site, invent a pipeline, or stop halfway. If you do attach it, the Bot can call the same capabilities you already use in a studio, then bring the URLs back for you to review.

    Orauria MCP page, the six documented tools, credit packs on the pricing page, and product stills from Studio generation history.

    What Orauria adds: Studio, MCP, and a credit wallet

    Orauria is a creative production workspace for ecommerce and marketing teams — a place to generate and QA product images, video, and campaign variants. If you are new to the product, start with What is Orauria or the Vietnamese introduction Orauria là gì.

    The part that matters for Grok Bot is not only the Studio UI. Orauria also publishes an MCP server. The MCP setup page documents how to connect Cursor, Claude (Code or Desktop), and Codex with an sk-… API key in an Authorization: Bearer header. Image, video, and chat calls use the same wallet and prices as Studio; pricing is public. If credit is too low, the call returns an error rather than silently skipping a charge.

    The tools currently listed on that page are:

    • generate_image — create an image from a prompt and model; returns a result URL.
    • generate_video — start a video job.
    • chat — chat with an Orauria LLM, billed per token.
    • list_models — see available image, video, and chat models.
    • get_wallet — check remaining credits before you generate.
    • get_task — poll an image or video job until it finishes.

    That list is also a list of things the MCP server does not currently expose. The published MCP documentation does not list tools for Workflow Builder, Fashion Poses, marketplace upscale, or the Chrome extensions. Those remain Orauria products you can use on the web (for example Workflows). We will not pretend they are MCP tools until the docs say they are.

    One documentation detail to treat carefully: the MCP page currently shows the endpoint as http://orauria.com/api/mcp. A cloud agent should almost always call a public HTTPS URL. Whether Grok Bot accepts that exact URL, and whether the production endpoint you should save is the HTTPS form, still needs to be confirmed. We will not invent the answer here.

    The framing for every article in this series is the same: how to use Orauria with Grok Bot. That is a user-side integration, not a claim that xAI endorses Orauria or that the two companies have a commercial partnership.

    Architecture of two paths: a documented MCP design from you to Grok Bot to Orauria MCP to Studio, and a second path where the Bot opens orauria.com in its cloud browser.

    Two paths: MCP, and the browser on the cloud computer

    Once you put the public facts side by side, two integration paths appear.

    Path 1 — MCP, the intended default. Grok Bot’s own docs say you can add a custom Remote HTTPS connector with a server URL and optional HTTP headers. Orauria’s MCP docs say the server authenticates with an Authorization: Bearer sk-… header. Those two shapes match. In principle, a Bot could call get_wallet, list_models, and generate_image from chat or from a routine, then return result URLs for you to approve. That is the clean path: structured tools, measurable credit use, and instructions you can save as a skill.

    It is also the path we will not walk through click by click in this article. As of 11 November 2026, Orauria’s MCP page documents Cursor, Claude, and Codex — not Grok Bot. We have not published an official “it works” test of Remote HTTPS plus a Bearer header inside Grok Bot. Until that test exists, Path 1 is a design that follows both sets of public docs, not a verified recipe. If you try it yourself, keep the API key in the connector header or a secret card, never in ordinary chat.

    Path 2 — the cloud browser, for visual work. When you need a canvas, a crop, or on-screen QA, a Bot can open orauria.com in its cloud browser and use Studio or Workflow the way a person would. Grok Bot’s computer documentation is clear that browser sessions persist and that a sign-in for one Bot is available to your other Bots. That is convenient, and it is a reason not to leave extra credentials on the machine. Path 2 does not replace MCP. It is the overflow path for UI that the current MCP tool list does not cover.

    A third layer sits on top of both: skills, routines, and multiple Bots. You can imagine one Bot writing a merchandising brief and another calling image tools, then handing a pack to you. The collaboration model is documented. Wiring it to Orauria, again, waits on a verified connector and on skills we will only publish after they run for real.

    How to read the rest of this series, and what to do next

    This is the pillar for a cluster of guides and design essays around Grok Bot and Orauria. The next piece zooms in on architecture: why MCP should be the default, where the browser path belongs, and how to think about secrets on a shared computer. A step-by-step connection tutorial will follow only after we have tested the connector and updated the MCP page with Grok Bot instructions. Later articles will cover skill templates, image and video workflows, routines, and security — always with a clear label when a step is still unverified.

    If you want to use Orauria from an agent today, start where the docs are already complete: connect Cursor, Claude, or Codex with a key from your profile, check the wallet, and generate one image. If you want a connector, a skill, or a creative Bot built around your own catalog and approvals, that is a software project. Hire Orauria to build it — the same team that already shipped Studio and the MCP server.

    Use Grok Bot for the teammate layer. Use Orauria for the product-creative layer. Keep the language honest: this is how the two systems can work together, not a joint product and not a completed integration announcement.