Your Expert Agent

agentiiv is technology enabling talent. We are reinventing the way teams work together.

agentiiv

Input a list of SEO Terms, and get back a detailed description of the keywords together with their competition, historical volume and CPC. The keywords are specific to a region set by the user on a seperate settings page, you cannot change the region. You cannot access URLs, only keywords.

seoPlus

Comma-seperated-list of keywords. Up to 100 at a time.

SEOPlus

region

Input a document object with some formality settings as well as an array of different elements in the object. The content of each element can be specified in individually and using markdown. Refer to the example. Get back a URL to download a PDF.

pdfReporting

The input document object. DO NO JUST INPUT MARKDOWN; YOU NEED TO INPUT A COMPLIANT OBJECT!!! Example object: {"title":"Bold, big title","type":"markdown","data":[{"label":"Bold size 12 heading","content":"Size 12 paragraph below the heading. **Bold**, *italisize* or [link](https://x.com/) with Markdown syntax.","fontSize":12,"textColor":"#000000"},{"table":{"rows":[["Row 1 Col 1","Row 1 Col 2","Row 1 Col 3"],["Row 2 Col 1","Row 2 Col 2","Row 2 Col 3"]],"firstRowHeaders":true,"rowGridlines":true,"columnGridlines":true}}],"page":{"width":"612px","height":"792px","margin":"50px","marginTop":"30px","marginBottom":"30px","marginLeft":"60px","marginRight":"60px","pageCount":"bottomCenter"}}

PDF Report

Input Markdown for a bullet point list with tab-indented sub-bullets, and render a beautiful mind mapdiagram as output.

markmap

A string containing a Markdown list with indented sub-points. The outline given in Markdown will be turned into a mindmap with the same hierarchy.

Markmap

Input compliant markdown to automatically generate a presentation.

powerpointGeneration

Think step by step and follow instructions meticulously. I will tip you $2000 for following each step precisely. Input markdown string for presentation generation. Starts with a Markdown-YAML-Frontmatter with "title" (necessary), "presenter", "date" and "company" (title slide is auto-generated from frontmatter data). You can also (optionally) include a logoURL for a 200x200 logo in the frontmatter to replace the default. Not specifying a date at all (leaving out the line) in the frontmatter will default to the current date. After that, slides are seperated with "---". Each slide starts with the slide type, specified in curly brackets: "{content}" (text-centric), "{image}" (text + a placeholder to add an image) or "{section}" (a header for a section). Then, markdown headers (h1/h2) and regular markdown can be used (section slides only support h1, without regular text or bullets). In image slides h3 headings are used to specify image descriptions for what images belong in the placeholders. **IMPORTANT RULE: PAY ATTENTION TO THE FORMAT, YOU CANNOT INPUT RANDOM MARKDOWN!!! FOLLOW THE FORMAT PRECISELY** Example input string: 
<example>
---
title: Presentation Title
presenter: Presenter Name
date: Date
company: Company Name
logoURL: https://example.com/example.png
---
{content}
# Headline
## Subheadline
- Any content (bullets supported)
[speakers notes inside square brackets - include full speaker notes and should be uncut and faithfully represented in the markdown, regardless of length; all details should be included without any modifications or condensation]
---
{image}
# Headline
## Subheadline
### Image description that appears above the image placholder
- Any content (bullets supported)
[speakers notes inside square brackets - include full speaker notes and should be uncut and faithfully represented in the markdown, regardless of length; all details should be included without any modifications or condensation]
---
{section}
# Section title
[speakers notes inside square brackets]


PPTX

logoURL

defaultPresenter

defaultCompany

Input a YouTube URL to get back the video title, channel name and transcript of the YouTube video at the URL.

tubePlus

The URL of the YouTube video you want to look up.

YouTube Scraper

Execute a JavaScript code snippet that evaluates to a readable value or a Promise. Use this function to evaluate a JavaScript expression, send a fetch request, or use other JavaScript features or Browser APIs. The JavaScript will be executed on the user's local browser in a secure sandboxed context.

execute_javascript

A valid JavaScript code snippet to be executed on the browser.

JavaScript Interpreter

Input an image generation prompt exactly as described and show it to the user.   All prompts should detail every image part in objective terms within a detailed paragraph of over three sentences. Important: after calling this function, the output images will be shown to the user automatically. You don't need to include the output image to the users again in your response to avoid duplicate images. Important: Always add these keywords to the end of the prompt: high detailed skin, perfect morphology, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, HD, Sharp.

StablePhotos

Generate images using Stable Diffusion v3 based on a text description. When creating prompt: include: subject (what do we want to see in the image), medium (the material used to make the artwork, for example photography, illustration, 3D rendering oil painting), style (artistic style or visual genre), resolution (how detailed and sharp the image is), color (overall color of the imagery), lighting (how the imagery should be lit),  detailed imagery (specific attributes like clothing, expressions), environment (where it's happening), mood (the feeling it should evoke), and execution details (how the style is applied). Be specific, use detailed descriptions, and clearly state what you want on the image. Image type, descent, gender are to be explicitly stated. IMPORTANT: Ensure anatomical accuracy - correct number of fingers and accurate rendering of hands. Diversify depictions with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions. Your choices should be grounded in reality. For example, all of a given OCCUPATION should not be the same gender or race. Additionally, focus on creating diverse, inclusive, and exploratory scenes via the properties you choose during rewrites. Make choices that may be insightful or unique sometimes. Use all possible different DESCENTS with EQUAL probability. Some examples of possible descents are: Caucasian, Hispanic, Black, Middle-Eastern, South Asian, White, South East Asian. They should all have EQUAL probability. Retain text references. Always provide 3 image examples by generating three separate prompts.

Stable Photos

Calculate a math expression. For example, "2 + 2" or "2 * 2". The expression must be a valid JavaScript math expression.

get_calculation_result

A valid JavaScript math expression for the calculation.

Simple Calculator

Render a HTML source to the user interface that will be shown to the users for interactive contents.

render_html

The HTML Source to render to the user interface.

HTML

Get social media posts from any user on the platform X, formerly known as Twitter. Input a handle into Xscrape to get a concentrated text blob consisting of the latest longer posts from the input user.

xscrape

The handle of the user you want to scrape. For example, if you want to scrape the user @elonmusk, you would input 'elonmusk' into this field. Note that this is case-insensitive and does not require the '@' symbol.

X scrape

Get extremely detailed information about any LinkedIn profile, including Twitter handles. If a Twitter handle is given, you can use Xscrape to get detailed Twitter data on the user.

liscrape

Profile URL of the LinkedIn profile to scrape.

LI scrape

Render an interactive canvas with HTML source to the user interface. The HTML source can include JavaScript and CSS to create interactive elements. This can be used to create custom user interfaces, games, demos, charts, and more. The canvas width is always 100% of the container width, and the height can be specified in pixels.

render_interactive_canvas

The height of the canvas in pixels. Default is 500.

Interactive Canvas

Generate a diagram using Mermaid.js (version 10.x). This can be used to render various types of diagrams, including Flowchart, Sequence Diagram, Class Diagram, State Diagram, Entity Relationship Diagram, User Journey, Gantt, Pie Chart, Quadrant Chart, Requirement Diagram, Gitgraph Diagram, C4 Diagram, Mindmaps, Timeline, Zenuml, Sankey, XYChart, Block Diagram, etc.

render_mermaid_diagram

The Mermaid diagram source in raw text to render.

Mermaid Diagram

render_chart

Additional options for the Chart.js chart

Render Chart

Input an image generation prompt exactly as described and show it to the user.   All prompts should detail every image part in objective terms within a detailed paragraph of over three sentences. Important: after calling this function, the output images will be shown to the user automatically. You don't need to include the output image to the users again in your response to avoid duplicate images.

illustration_generation_via_dalle_3

 For effective image generation prompts, include: subject (what do we want to see in the image), medium (the material used to make the artwork, for example photography, illustration, 3D rendering oil painting), style (artistic style or visual genre), resolution (how detailed and sharp the image is), color (overall color of the imagery), lighting (how the imagery should be lit),  detailed imagery (specific attributes like clothing, expressions), environment (where it's happening), mood (the feeling it should evoke), and execution details (how the style is applied). Be specific, use detailed descriptions, and clearly state what you want on the image. Retain text references. Always provide 3 image examples by generating three separate prompts.

Illustrations - D3

Input an image generation prompt exactly as described and show it to the user. Always add these keywords to the end of the prompt: single image, Always add these keywords to the end of the prompt:  medium (logo), resolution (high res), execution details (transparent background, scalable vector graphics, high resolution) All prompts should detail every image part within a detailed paragraph of over four sentences.

logo_generation_via_dalle_3

Generate images using Dall E3 based on a text description. For effective image generation prompts, include: subject ((what do we want to see in the image - be specific, use detailed descriptions, and clearly state what you want on the subject image. Employ an evocative and nuanced detailed description of at least 3 sentences)), medium (always a logo), style (artistic style or visual genre), resolution (always high resolution), color (overall color of the imagery), mood (the feeling it should evoke), and execution details (always transparent background, scaleable vector graphics, high resolution). Be specific, use detailed descriptions, and clearly state what you want on the image. Retain text references.  Always provide 3 image examples by generating three separate prompts.

Logo - D3

Input an image generation prompt exactly as described and show it to the user. Always add these keywords to the end of the prompt: medium (illustrated icon), resolution (high resolution), color (monochrome), mood (professional), execution details (against a transparent background, scalable vector graphics, high resolution). All prompts should detail every image part in objective terms within a detailed paragraph of over three sentences. Important: after calling this function, the output images will be shown to the user automatically. You don't need to include the output image to the users again in your response to avoid duplicate images.

icon_generation_via_dalle_3

For effective image generation prompts, include: subject (what do we want to see in the image), medium (always an illustrated logo), style (artistic style or visual genre), resolution (always high resolution), color (overall color of the imagery), mood (the feeling it should evoke), and execution details (always against a transparent background, scaleable vector graphics, high resolution). Be specific, use detailed descriptions, and clearly state what you want on the image.

Icon - D3

Search for information from the internet using Perplexity.

perplexitySearch

WebSearch

Input a URL, and receive results back from Exa similar URL finder. You might also receive a link to download a CSV file with the results, depending on the admin's settings - you can pass this to the user. You have to provide a full, valid URL including https://.

findSimilar

FULL, VALID URL (string, including https://) to find similar URLs

Find Similar Entity (Exa)

Input a search term or URL, and receive results back from Exa web browsing and web scraping. You might also receive a link to download a CSV file with the results, depending on the admin's settings - you can pass this to the user. When asked to scrape a website domain, add https:// to the input.

companyMatch

SEARCH TERM (string) or FULL, VALID URL (string, including https://) to retrieve content from/about

Company Match (LinkedIn)

findPerson

Find Person (LinkedIn)

findTitle

Find Title (LinkedIn)

findCompany

Find Company (Exa)

webBrowsing

Web Browsing (Exa)

researchCompany

Research Company (Exa)

researchFinancial

Research Financial (Exa)

browseNews

Browse News (Exa)

browseCompanyPageLI

Browse Company Page LI (Exa)

Azure GPT 4o

The images will be generated using this OpenAI API. Get your API key from https://platform.openai.com/account/api-keys

openaikey

resolution

quality

Input a search term to get a detailed summary of different sources on the web covering your topic.

chartsPlus

Comma-separated string of numbers. Each number is a data point, listed in order for each dataset, and corresponds to the labels in chartLabels (length = length of chartLabels * length of datasets). For example, with 2 datasets and 3 labels, the string '1,2,3,4,5,6' would be interpreted as '1,2,3' for the first dataset and '4,5,6' for the second.

The kind the chart. Can be 'bar' (image bar chart), 'line' (image line chart), 'pie' (image pie chart) or 'doughnut' (image doughnut chart)..

Login to agentiiv