Extract decisions from notes
Use OpenAI model [model ID] to summarize these meeting notes: [notes]. List confirmed decisions, next steps with stated owners, and unanswered questions. Do not fill in missing details.
Leina connects to OpenAI to help you summarize source text, rewrite drafts, and generate speech or images. Ask in your team chat. Leina does the work and brings back the result.
Connect OpenAI, choose what to share, and hand off your first task.
You
Use my chosen OpenAI text model to rewrite this customer update plainly: “Deployment is delayed. Revised delivery: October 18. Existing accounts still work. We will send another update tomorrow.” Keep every date and commitment, and add no promises.
Leina
Here is the revised update: “Deployment is delayed until October 18. Your existing account continues to work. We’ll send another update tomorrow.”
OpenAI · Text response
Customer delivery update
A clearer draft using only the supplied delivery details.
An AI integration with OpenAI sends the input you provide to a model available through your API account. Use it for a focused summary, rewrite, or media request with clear instructions and source material.
You specify the source and the destination. Leina uses the content available to your connection and returns the result for you to review.
OpenAI provides model APIs for text and media tasks. This connection uses an OpenAI API key.
Provide the customer draft and select an available text model.
Keeps the date, account status, and promised follow-up in scope.
Sends the draft and rewrite instructions to the selected model.
Review the returned wording before sharing it with customers.
Copy a prompt, add your details, and send it to Leina in your connected team chat.
Use OpenAI model [model ID] to summarize these meeting notes: [notes]. List confirmed decisions, next steps with stated owners, and unanswered questions. Do not fill in missing details.
Use OpenAI speech model [model ID] and voice [voice] to generate MP3 audio from this script: [script]. Keep the wording unchanged.
Use OpenAI model [model ID] to rewrite this customer update in plain language: [draft]. Keep every date and commitment, and do not add new promises.
Use OpenAI image model [model ID] to generate an image for this brief: [subject, setting, and visual style]. Include no text in the image.
Your next OpenAI task can start with a message.
Tell Leina what you need in your team chat. Include the source, destination, and expected result.
Connect the tools involved and give Leina access to the content it needs.
Share the source material, say where the result belongs, and describe what you need.
Review the result and any changes in the connected app.
Hand off these everyday tasks to your AI employee.
List the OpenAI models available to the current API key.
Retrieve the metadata for a single OpenAI model by ID.
Create a non-streaming OpenAI response through the Responses API.
Retrieve one stored OpenAI response by its identifier.
List the stored input items for one OpenAI response.
Count how many input tokens a Responses-style OpenAI request would consume.
Create embeddings with an OpenAI embedding model.
Classify text or image inputs with the OpenAI Moderations API.
Generate images with the OpenAI image generation API.
Synthesize speech audio from text with the OpenAI audio speech API.
Transcribe one uploaded audio file with the OpenAI audio transcription API.
Translate one uploaded audio file into English with the OpenAI audio translation API.
Create an OpenAI batch job from an uploaded input file.
Fetch one OpenAI batch job by its identifier.
Cancel one OpenAI batch job by its identifier.
Connect the Apps your work depends on, and give Leina the context to carry the task forward.
Hand off a task while your team is discussing it. Leina uses your connected tools and brings the result back to the conversation.
See How Leina Works in SlackHere is the revised update: “Deployment is delayed until October 18. Your existing account continues to work. We’ll send another update tomorrow.”
For a text task, provide the source text, the result you want, and a model available to your API account. This connection sends that input to OpenAI; it does not automatically read your email or project files.
The speech action returns audio data and its media type, not a hosted playback link. Choose the model, voice, and format; saving or playing the audio depends on the AI product using the connection.
The connection can list models available to your API key. Choose a model suited to the task; access to a listed model does not mean it supports every text or media operation.
Start with one task you already need to do. Tell Leina what a finished result should look like.
Connect OpenAI, choose what to share, and hand off your first task.