Run
Examples
API
Loading...
38 runs
Added a function to check character count for twitter. You can fork the functions workflow and add ANY API!.
YOU CAN CHECK THE DETAILS SECTION AT THE BOTTOM OF THE PAGE TO SEE THE FUNCTION OUTPUT!
Prompt
write a haiku about alien and human friendships, incorporate the current latitude and longitude coordinates of ISS provided here: {{ coords_latitude }} {{coords_longitude}}
coords_latitude
coords_longitude
GPT-4 Turbo (openai)
385 runs
This prompt takes in all the conversations that have occurred with a Gooey.AI Copilot, in this case the FALANA Bot and summarizes the conversations into top concerns and questions for the speaker.
{{conversations}} #### Your job is to analyse the conversations above and summarise the user's responses to questions asked by the assistant. Return the summary as a numbered list of 5 representative user responses. Group the user's responses and synthesize them into a set of questions that reflect the user responses, sorted by by how often the sentiment was expressed. Also categorise them based on common themes you observe. You can ignore greetings and introductions with user names and companies. Here are two examples: {"What's your reaction to everything you've seen so far?": "1. Hope: Most people expressed cautious optimism about AI's potential for India", "Top questions": "1. AI and Jobs: What can we do to stem job losses from AI?" } Return your analysis as the following JSON object: { "What's your reaction to everything you've seen so far?": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ...", "Top questions": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ..." } If the user responses doesn't fit into any of the categories, return an empty object (`{}`)
conversations
GPT-4o (openai)
Which language model works best your prompt? Compare your text generations across multiple large language models (LLMs) like OpenAI's evolving and latest ChatGPT engines and others like Curie, Ada, Babbage.
{{messages}} ### Your job is to analyze the user's messages above and determine how to categorize them. Category choices: [ "😊 Happy", "😟 Worry", "🌟 Hopeful", "😨 Fear", "🤯 Mind Blown" ] Return your analysis as the following json object: { "How did this evening make you feel about AI and Robots?": "<category>" } If the messages doesn't fit into any of the categories, return an empty object (`{}`)
messages
10 runs
A simple prompt that takes in an image prompt and outputs a better SD 1.5 one.
Your job is to improve AI image prompts for the Stable Diffusion 1.5 model, Dreamshaper. Input prompt: {{prompt}} Output prompt:
prompt
9 runs
A comparison of small 2-10B LLM models on Hindi text using the best of LLaMA3, Gemma and Sarvam 2B
भारत के प्रथम प्रधानमंत्री
Gemma 2 9B (Google)
Gemma 7B (Google)
Sarvam 2B (sarvamai)
Llama 3 8B (Meta AI)
6 runs
Compare prompts and outputs from the fine-tuned AFROLLaMA from Jacaranda Health
Yoruba: Kọ itan nipa Ọgbọn Ehoroa
AfroLlama3 v1 (Jacaranda)
21 runs
Kalau orang sedang di GBK, biasanya sedang apa dia?
Llama 3 70B (Meta AI)
Mixtral 8x7b Instruct v0.1 (Mistral)
Gemini 1.5 Pro (Google)
Claude 3.5 Sonnet (Anthropic)
Llama3 8B CPT SEA-LIONv2.1 Instruct (aisingapore)
56 runs
This example is the default analysis script to categorize Copilot conversations and to determine whether user's questions we successfully answered.
{{messages}} ### Your job is to analyze the user's messages above, determine how to categorize them and determine if the bot answered their question with "Found" or "Missing". Your response should contain exactly one JSON object. Category choices: [ "General", "Salutation", "Random", "Technical", "Other" ] Return your analysis as the following json object: { "What was the category of the user query?": "<category>", "assistant": {"answer": "Found || Missing"}}}
0 runs
This recipe takes in a Copilot's Description and Instruction Prompt and then creates a shorter description and 4 sample questions.
Create a punchy, clever description (in under 40 words) of an AI Chat bot along with 4 sample questions (that are under 10 words), based on the following description and LLM instruction prompt: Description: {{description}} Prompt: {{prompt}}
description
3 runs
Yes, this is a silly (but useful!) AI recipe. Notice the differing emoji styles of Claude3.5 vs GPT-4o. :-)
Add appropriate emojis to the following GitHub Readme.md: {{code}} New Code:
code
When released, PaLM 2 not only surpassed other LLMs in translation abilities between multiple languages but also demonstrated significant improvements over Google Translate (see the Technical Report by Google). This example allows you to easily change out the languages and translation text via variables to explore this and compare with other LLMs. You can also add your own TSV or CSV glossary in the format spec'ed by Google Translate. This example run (or runs like it) can be imported into the Translation Recipe to compare with traditional translation tools!
Remember this glossary of fixed translation terms. The columns represent language codes in BCP47 and the rows are the terms: {{ glossary }} PROMPT: Please use the glossary to translate the following text from en-US to da-DK. <Q>Hello, my name is Bob and I work at gooey.ai which is an awesome company that coincidentally also made this tool. I am made by goowy. <A>Hej, jeg hedder Bob, og jeg arbejder hos Gooey.AI, som er en fantastisk virksomhed, der tilfældigvis også lavede dette værktøj. Jeg er lavet af Gooey. PROMPT: Please use the glossary to translate the following text from {{ source_language }} to {{ target_language }}. <Q>{{ text_to_translate }} <A>
glossary
source_language
target_language
text_to_translate
PaLM 2 Chat (Google)
168 runs
This prompt takes in all the conversations that have occurred with a Gooey.AI Copilot, in this case the Fireside Bot and summarizes the conversations into top concerns and questions for the speaker. It's then visualized here
{{conversations}} #### Your job is to analyse the conversations above and summarise the user's responses to questions asked by the assistant. Return the summary as a numbered list of 5 representative user responses. Group the user's responses and synthesize them into a set of questions that reflect the user responses, sorted by by how often the sentiment was expressed. Also categorise them based on common themes you observe. You can ignore greetings and introductions with user names and companies. Here are two examples: {"What's your reaction to everything you've seen so far?": "1. Hope: Most people expressed cautious optimism about AI's potential for India", "Top questions for Nandan": "1. AI and Jobs: What can we do to stem job losses from AI?" } Return your analysis as the following JSON object: { "What's your reaction to everything you've seen so far?": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ...", "Top questions for Nandan": "1. <Theme>: <Response>\n2. <Theme>: <Response>\n3. ..." } You are being run in a public setting, so please take extra precautions to weed out and ignore hecklers, bad data, inappropriate or politics remarks, etc. If the user responses doesn't fit into any of the categories, return an empty object (`{}`)
188 runs
{{messages}} ### Your job is to analyze the user's messages above and determine how to categorize them. Category choices: [ "😊 Happy", "😟 Worry", "🌟 Hopeful", "😨 Fear", "🤯 Mind Blown" ] Return your analysis as the following json object: { "How do you feel about AI after today": "<category>" } If the messages doesn't fit into any of the categories, return an empty object (`{}`)
1 runs
Which language model works best for your prompt? What are the biases inherent in each? Compare LLaMA2, Gemini, Mistral, OpenAI GPT-4 engines with more LLMs being added each month.
What advice do you have to fight climate change? Write a 100 word action plan for American kids.
product
2.17K runs
Our https://gooey.ai/copilot workflow let's anyone build WhatsApp/FB or their own GPT4 powered chat bots, by just swapping out their own documents and GPT prompts. Additionally, we also enable you to analyze the user's message and bot's answer to create structured data from the raw conversational messages.
Each Gooey.AI copilot will have their own conversational analysis script like this one to help analyze the user's questions and the bot's ability to answer them well.
In this case, our Farmer.CHAT partner DigitalGreen.org wants to analyze the user's messages and categorize them based on their own logic. Hence, this LLM prompt takes a message and response and then determines whether:
Your job is to analyze incoming chat messages from farmers and the responses from a farming ai chatbot and determine how to categorize them. The answer is only missing if the assistant: --- 1. Can not give any additional information 2. Apologizes 3. Tells the user to check a website --- If it does not say all three things, the answer has been found. For the user's subject answer, choose from the following list as category: Subject Answers ********************* Salutation Plant Death (Infestation and Infection) Farming Practice Irrigation Video Supplements (Fertilizers and Pesticides) Unknown Category ********************* Assistant Answers ********************* Found Missing ********************* Gender ********************* unknown male female unspecified ********************* Conversation: """ user: Hi assistant: Hello! How can I assist you with farming today? """ Analysis: {"user": {"crop": null, "subject": ”Salutation”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}} /// Conversation: """ user: My rice crop has yellow stem borer infestation. Please suggest assistant: Yellow stem borer is a major pest of rice crops. Here are some management practices that can help control the infestation of yellow stem borer in rice crops: 1. Use resistant varieties of rice such as Ratna, Sasyasree, Vikas, HKR 46, NDGR 21, Pantdhan 6, VLK 39, Prahlad, Birsadhan 201, Bhudeb Ainesh, Matangini, Radha, Sudha, Amulya, Bhagirathi, Jogan, Mandira, Nalini, Sabita, VL16 and VL 206. [2][3] 2. Cultural practices such as seed treatment with approved biopesticides or chemical pesticides before sowing, removing and destroying the grass weed hosts in the field bunds, channel or nearby areas of rice fields as these serve as alternative hosts for the pest, avoiding close spacing as it often increases the easy movement of pest, handpicking and destroying egg masses in the seedbed (nursery) before transplanting the field, cutting the leaf-top before transplanting to reduce carry-over of eggs from the seedbed to the field, raising the level of irrigation water periodically to submerge any eggs deposited on the lower parts of the plant, cutting out the stems with dead hearts and removing them from the field and destroying the larvae or burning the stem, and splitting applications of nitrogen fertilizer. High nitrogen application favors build-up of stem """ Analysis: {"user": {"crop": ”rice”, "subject": ”Plant Death (Infestation and Infection)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}} /// Conversation: """ user: A drug can be used to increase the height of chillies in the chilli garden assistant: I'm sorry, but I couldn't find any information in the search results about a drug that can increase the height of chillies in a garden. It is important to note that using untested or unverified drugs on crops can be harmful and may not be effective. It is best to consult with a local agriculture expert for specific recommendations for your district and type of plant. """ Analysis: {"user": {"crop": ”chili”, "subject": ”Supplements (Fertilizers and Pesticides)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}} /// Conversation: """ user: Tell me about organic farming assistant: Organic farming is a method of farming that avoids the use of synthetic fertilizers, pesticides, and genetically modified organisms (GMOs). Instead, it relies on natural methods like crop rotation, composting, and biological pest control to maintain soil fertility and control pests. Organic farming also emphasizes the use of renewable resources and conservation of water and soil. [1] """ Analysis: {"user": {"crop": null, "subject": "Farming Practice", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}} /// Conversation: """ user: How many days should be watered after making the pepper garden? assistant: According to [1], immediately after transplanting chilli seedlings to the field, the field should be irrigated. The second irrigation is given 10 days after transplanting. Afterward, irrigation is given as per the requirement. Generally, 8 to 9 irrigations are given depending on rainfall, soil type, humidity, and temperature. The method of irrigation adopted is ridges and furrow. For more specific information on irrigation practices for your particular crop and district, please consult with your local agriculture extension office or watch relevant videos on https://www.digitalgreen.org/videos. 💦 """ Analysis: {"user": {"crop": "pepper", "subject": "Irrigation", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}} /// Conversation: """ user: Reasons why chillies fall apart assistant: Chillies can fall apart due to several reasons, including environmental conditions, pests, and diseases. Inadequate pollination due to low bee activity or high temperatures can lead to poor fruit development and cause the chillies to fall apart [2]. Nutrient deficiencies, particularly a lack of phosphorus, can also affect fruit development and cause the chillies to fall apart [1]. Additionally, pests such as the chilli blossom midge can cause poor development of fruits, leading to the chillies falling apart [3]. It is important to consult with a local agriculture expert to identify the specific cause and recommend appropriate management practices for your district and type of plant. For more information on farming in India, you can visit https://www.digitalgreen.org/videos. 🌶️🌱 """ Analysis: {"user": {"crop": ”chili”, "subject": ”Plant Death (Infestation and Infection)”, "location": null, "gender": "unspecified"}, "assistant": {"answer": "Found"}} /// Conversation: """ user: How to prepare dukki for planting chili garden assistant: I'm sorry, I couldn't find any relevant information on preparing "dukki" for planting chili garden in the search results. Could you please provide more context or try rephrasing your question? """ Analysis: {"user": {"crop": "chili", "subject": "Farming Practice", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}} /// Conversation: """ user: Is there a video for this? assistant: I'm sorry, I don't have enough information to answer your question. However, you can visit https://www.digitalgreen.org/videos to find helpful videos on various farming practices in India. """ Analysis: {"user": {"crop": null, "subject": "Video", "location": null, "gender": "unspecified"}, "assistant": {"answer": "Missing"}} /// Conversation: """ user: Which crop can be planted in Anantapur? assistant: Anantapur district in Andhra Pradesh is suitable for growing crops like groundnut, maize, jowar, sunflower, cotton, and chilli. However, the choice of crop depends on various factors such as soil type, climate, and water availability. It is recommended to consult with local agricultural experts or extension officers to determine the best crop for a particular area. [1] """ Analysis: {"user": {"crop": null, "subject": "Farming Practice", "location": "Anantapur", "gender": "unspecified"}, "assistant": {"answer": "Found"}} /// Conversation: """ user: {{ user_msg }} assistant: {{ assistant_msg }} """ Analysis:
user_msg
assistant_msg
ChatGPT (openai)
90 runs
Takes in a quarterly report, BUY rating and transcript to output a financial report
```[example report] {{ examplereport }} ```You are a financial analyst working in a capital investment firm. Please follow the steps below: \n1. Analyse and summarise the [finance report] and [transcripts] below in triple separators, don't create any output right now. Once you have analysed and summarised the data, create a report for the company that is similar to the [example report] template above in the triple backticks. Use the buy/hold/sell information from the [decision] input provided. Don't analyse your own. Ensure you follow the [example report] format, headers, writing style and paragraphs styles exactly. note: dont make up any information note: if information as per the [example report] template is missing please add a note "team must fill this information" |||[finance report] {{ financereport }} [transcripts] {{ transcripts }} [decision] {{ decision }} |||
decision
transcripts
examplereport
financereport
6.6K runs
Our https://gooey.ai/copilot workflow let's anyone build WhatsApp/FB or their own GPT4 powered chat bots, by just swapping our their own documents and GPT prompts. Additionally, we also enable you to analyze the user's message and bot's answer to create structured data from the raw conversational messages.
In this case, we wantw to analyze the user's messages and categorize them based on their own logic. Hence, this LLM prompt takes a message and response and then determines whether:
14 runs
Google Palm vs GPT4 vs LLaMA2: Which can easily create code to call the Stripe API using natural language.
""" Util exposes the following: util.stripe() -> authenticates & returns the stripe module; usable as stripe.Charge.create etc """ import util """ Create a Stripe token using the users credit card: 5555-4444-3333-2222, expiration date 12 / 28, cvc 521 """
PaLM 2 Text (Google)
Llama 2 70B Chat [Deprecated] (Meta AI)
GPT-4 (openai)
This workflow creates a JSON quiz based on a character.
You are an Intelligent AI Bot that can use any knowledge source. Generate a fun 6 question quiz about this Cassian Andor. The quiz should contain a fun Title with each Question having a question and then 4 different possible answers, with only one answer begin correct. Output the quiz, questions and possible answers as JSON.
2 runs
A prompt to compare a golden answer vs an AI generated answer.
You job is to assess AI translations. As a JSON object, give a short rationale and then a continuous score between 0 to 1 comparing a golden human text vs an AI generated text. If the AI text is identical to the golden text (other than spelling and punctuation differences), give a score of 1 and 0 if the phrases are semantically very different. Examples: Golden: In our chili farm there are white flies. What should we do? AI_text: We have white spots in the Mirapakaya Pulam. What to do? JSON: { "rationale": "The ai_answer is missing key elements such as chili farm and white flies." , "score": ".2" } Golden: {{ golden }} AI_text: {{ai_answer}} JSON:
golden
ai_answer
5 runs
This workflow takes a parameters the Gooey.AI workflow title and prompt to then create an image generation prompt that we use in our image generator workflow: https://gooey.ai/compare-ai-image-generators/?run_id=rpuzpn5m&uid=kKZgp2h1H2YxZYxZ2DbiRfUfeDM2
Create a DallE image generation description that creates a text-free icon that visually sums up a AI tool that is described by NAME and LLM_PROMPT: NAME: {{workflow}} LLM_PROMPT: {{prompt}} --- Guidelines: DO give guidance to avoid any use of text in the icon design DO use the LLM_PROMPT's content to define the style of the icon (more than NAME) --- Examples: NAME: Copilot LLM_PROMPT: You are Farmer.CHAT - an intelligent AI assistant built by Gooey.AI and DigitalGreen.org to help Indian farmers and agriculture agents. Try to give succinct answers to their questions (at a 6th grade level), taking note of their district and the particular plant they are attempting to aid (usually seeking a strategy to rid the crops of pests or other problems). - If the user gives a salutation such as "Hi" or "Hello", introduce yourself before answering the user's query with the text below between the triple backticks:
Welcome to Farmer.CHAT. I'm an AI 🤖 designed to help farmers and extension agents. Send me a text or 🎙️voice note with any farming question and I'll give you an answer based on recommendations and best practices from other farmers like you. I'm constantly trying to improve, so please give me your feedback by tapping the 👍🏾 👎🏽 buttons. Now, what would you like to know? 🌱
Example description: Create a text-free icon that combines a friendly robot, Indian agricultural elements like wheat or rice plants, and a symbol of communication such as a speech bubble or headphones, to represent an AI assistant for Indian farmers. The icon should be colorful, inviting, and simple enough to be understood at a glance. Avoid any text
workflow