Expected Parrot
@expectedparrot.bsky.social
Tools for AI-powered research
https://www.expectedparrot.com
Docs: https://docs.expectedparrot.com
GitHub: http://github.com/expectedparrot/edsl
Discord: https://discord.com/invite/mxAYkjfy9m
Blog: https://blog.expectedparrot.com
https://www.expectedparrot.com
Docs: https://docs.expectedparrot.com
GitHub: http://github.com/expectedparrot/edsl
Discord: https://discord.com/invite/mxAYkjfy9m
Blog: https://blog.expectedparrot.com
Pinned
We've been adding collaboration features that let teams work on AI+human surveys in code and interactively at once.
Eg, you can create a survey with our open-source package EDSL or using our no-code builder, and invite collaborators to contribute using whichever approach works for them:
Eg, you can create a survey with our open-source package EDSL or using our no-code builder, and invite collaborators to contribute using whichever approach works for them:
We've been adding collaboration features that let teams work on AI+human surveys in code and interactively at once.
Eg, you can create a survey with our open-source package EDSL or using our no-code builder, and invite collaborators to contribute using whichever approach works for them:
Eg, you can create a survey with our open-source package EDSL or using our no-code builder, and invite collaborators to contribute using whichever approach works for them:
July 21, 2025 at 2:39 PM
We've been adding collaboration features that let teams work on AI+human surveys in code and interactively at once.
Eg, you can create a survey with our open-source package EDSL or using our no-code builder, and invite collaborators to contribute using whichever approach works for them:
Eg, you can create a survey with our open-source package EDSL or using our no-code builder, and invite collaborators to contribute using whichever approach works for them:
A key feature of our platform is that you can choose whether to use your own API keys for LLMs and human participant platforms, use an Expected Parrot key for unified access, or mix and match keys as desired:
blog.expectedparrot.com/p/bring-your...
blog.expectedparrot.com/p/bring-your...
Bring your own keys or mix and match
A key feature of Expected Parrot is that you can always use your own keys for LLMs and human participant platforms, or you can use your Expected Parrot key for unified access.
blog.expectedparrot.com
July 21, 2025 at 2:36 PM
A key feature of our platform is that you can choose whether to use your own API keys for LLMs and human participant platforms, use an Expected Parrot key for unified access, or mix and match keys as desired:
blog.expectedparrot.com/p/bring-your...
blog.expectedparrot.com/p/bring-your...
We've made some big improvements for running LLM experiments and hybrid AI + human surveys on our platform! Update your EDSL version to get all the latest features:
June 28, 2025 at 12:23 PM
We've made some big improvements for running LLM experiments and hybrid AI + human surveys on our platform! Update your EDSL version to get all the latest features:
Sometimes you need to check your LLM answers with real respondents. Our tools make it easy to launch a web-based version your LLM survey, combine human and LLM results, and analyze them at your dashboard or workspace. Here's a quick example: blog.expectedparrot.com/p/validate-y...
Validate your LLM answers with real respondents
Here's a quick example of methods for generating a web-based version of your LLM survey and analyzing human and LLM responses together at your workspace.
blog.expectedparrot.com
May 25, 2025 at 11:54 AM
Sometimes you need to check your LLM answers with real respondents. Our tools make it easy to launch a web-based version your LLM survey, combine human and LLM results, and analyze them at your dashboard or workspace. Here's a quick example: blog.expectedparrot.com/p/validate-y...
When you conduct LLM experiments at Expected Parrot 🦜 your prompts and responses are automatically cached, so you--and everyone you share your research with 🌎--can retrieve them for free 💸 and verify that you ran them ✅.
May 23, 2025 at 10:21 AM
When you conduct LLM experiments at Expected Parrot 🦜 your prompts and responses are automatically cached, so you--and everyone you share your research with 🌎--can retrieve them for free 💸 and verify that you ran them ✅.
New blog post: Quick methods for retrieving, combining & analyzing results
blog.expectedparrot.com/p/how-to-ret...
blog.expectedparrot.com/p/how-to-ret...
How to retrieve, combine & query your saved results with SQL
Quick methods for accessing and analyzing your automatically stored results from anywhere.
blog.expectedparrot.com
May 12, 2025 at 5:21 PM
New blog post: Quick methods for retrieving, combining & analyzing results
blog.expectedparrot.com/p/how-to-ret...
blog.expectedparrot.com/p/how-to-ret...
🚀 Over 1 million Q&A cached and counting!
The Universal Remote Cache now contains over a million unique LLM prompts and responses. You can retrieve them at no cost whenever you replicate research at Expected Parrot.
blog.expectedparrot.com/p/over-1-mil...
The Universal Remote Cache now contains over a million unique LLM prompts and responses. You can retrieve them at no cost whenever you replicate research at Expected Parrot.
blog.expectedparrot.com/p/over-1-mil...
🚀 Over 1 million Q&A cached and counting
The Universal Remote Cache now has over a million unique LLM prompts and responses. You can retrieve them at no cost whenever you replicate research at Expected Parrot.
blog.expectedparrot.com
May 1, 2025 at 2:38 PM
🚀 Over 1 million Q&A cached and counting!
The Universal Remote Cache now contains over a million unique LLM prompts and responses. You can retrieve them at no cost whenever you replicate research at Expected Parrot.
blog.expectedparrot.com/p/over-1-mil...
The Universal Remote Cache now contains over a million unique LLM prompts and responses. You can retrieve them at no cost whenever you replicate research at Expected Parrot.
blog.expectedparrot.com/p/over-1-mil...
📢📢📢 New features for monitoring your AI research costs
Our tools are designed to make it easy to understand and monitor your LLM usage. Learn more about our latest features for precisely tracking your costs: blog.expectedparrot.com/p/new-featur...
Our tools are designed to make it easy to understand and monitor your LLM usage. Learn more about our latest features for precisely tracking your costs: blog.expectedparrot.com/p/new-featur...
New features for monitoring your AI research costs
Our tools are designed to make it easy to understand and monitor your LLM usage. Learn more about our latest features for precisely tracking your costs.
blog.expectedparrot.com
April 28, 2025 at 7:02 PM
📢📢📢 New features for monitoring your AI research costs
Our tools are designed to make it easy to understand and monitor your LLM usage. Learn more about our latest features for precisely tracking your costs: blog.expectedparrot.com/p/new-featur...
Our tools are designed to make it easy to understand and monitor your LLM usage. Learn more about our latest features for precisely tracking your costs: blog.expectedparrot.com/p/new-featur...
Several key features of EDSL make it a convenient tool for comparing the performance of language models:
blog.expectedparrot.com/p/i-want-to-...
blog.expectedparrot.com/p/i-want-to-...
I want to see how OpenAI's o3 compares to...
EDSL is an open-source tool that lets you readily compare performance for many language models at once.
blog.expectedparrot.com
April 22, 2025 at 10:00 PM
Several key features of EDSL make it a convenient tool for comparing the performance of language models:
blog.expectedparrot.com/p/i-want-to-...
blog.expectedparrot.com/p/i-want-to-...
Have an idea for an LLM experiment?
Here are some reasons to run it at Expected Parrot, and easy ways to get started.
blog.expectedparrot.com/p/have-an-id...
Here are some reasons to run it at Expected Parrot, and easy ways to get started.
blog.expectedparrot.com/p/have-an-id...
Have an idea for an LLM experiment?
Here are some reasons to run it at Expected Parrot, and easy ways to get started.
blog.expectedparrot.com
April 15, 2025 at 12:44 PM
Have an idea for an LLM experiment?
Here are some reasons to run it at Expected Parrot, and easy ways to get started.
blog.expectedparrot.com/p/have-an-id...
Here are some reasons to run it at Expected Parrot, and easy ways to get started.
blog.expectedparrot.com/p/have-an-id...
What are my options for running EDSL surveys?
Here's a quick recap of features for specifying where and how to run your LLM-based surveys in EDSL. You can bring your own API keys for LLMs or use an Expected Parrot key to access all available models at once.
blog.expectedparrot.com/p/what-are-m...
Here's a quick recap of features for specifying where and how to run your LLM-based surveys in EDSL. You can bring your own API keys for LLMs or use an Expected Parrot key to access all available models at once.
blog.expectedparrot.com/p/what-are-m...
What are my options for running EDSL surveys?
Here's a quick recap of features for specifying where and how to run your LLM-based surveys in EDSL.
blog.expectedparrot.com
April 9, 2025 at 1:39 PM
What are my options for running EDSL surveys?
Here's a quick recap of features for specifying where and how to run your LLM-based surveys in EDSL. You can bring your own API keys for LLMs or use an Expected Parrot key to access all available models at once.
blog.expectedparrot.com/p/what-are-m...
Here's a quick recap of features for specifying where and how to run your LLM-based surveys in EDSL. You can bring your own API keys for LLMs or use an Expected Parrot key to access all available models at once.
blog.expectedparrot.com/p/what-are-m...
Show prompts, please!
EDSL makes it easy to tinker with prompts, compare responses from different language models, and replicate experiments by automatically storing all your prompts, responses and code to reproduce them.
blog.expectedparrot.com/p/show-promp...
EDSL makes it easy to tinker with prompts, compare responses from different language models, and replicate experiments by automatically storing all your prompts, responses and code to reproduce them.
blog.expectedparrot.com/p/show-promp...
Show prompts, please!
EDSL makes it easy to tinker with prompts, compare responses from different language models, and replicate experiments by automatically storing all your prompts, responses and code to reproduce them.
blog.expectedparrot.com
April 7, 2025 at 8:22 PM
Show prompts, please!
EDSL makes it easy to tinker with prompts, compare responses from different language models, and replicate experiments by automatically storing all your prompts, responses and code to reproduce them.
blog.expectedparrot.com/p/show-promp...
EDSL makes it easy to tinker with prompts, compare responses from different language models, and replicate experiments by automatically storing all your prompts, responses and code to reproduce them.
blog.expectedparrot.com/p/show-promp...
We launched a GPT for generating EDSL survey code - please give it a spin and let us know what you think!
chatgpt.com/g/g-67d17648...
chatgpt.com/g/g-67d17648...
April 7, 2025 at 1:34 PM
We launched a GPT for generating EDSL survey code - please give it a spin and let us know what you think!
chatgpt.com/g/g-67d17648...
chatgpt.com/g/g-67d17648...
How do I control AI agent memory when answering my questions?
EDSL provides a variety of features for controlling the context of information presented at each step of your experiment.
blog.expectedparrot.com/p/how-do-i-c...
EDSL provides a variety of features for controlling the context of information presented at each step of your experiment.
blog.expectedparrot.com/p/how-do-i-c...
How do I control AI agent memory when answering my questions?
EDSL provides a variety of features for adding context of prior questions to new questions, piping answers into other questions, and asking multiple questions at once in a structured way.
blog.expectedparrot.com
April 4, 2025 at 5:08 PM
How do I control AI agent memory when answering my questions?
EDSL provides a variety of features for controlling the context of information presented at each step of your experiment.
blog.expectedparrot.com/p/how-do-i-c...
EDSL provides a variety of features for controlling the context of information presented at each step of your experiment.
blog.expectedparrot.com/p/how-do-i-c...
"'Surveys' sounds niche and not what I need"
Totally fair! But many research tasks and experiments can be designed as survey-like interactions. Please let us try to convince you: blog.expectedparrot.com/p/surveys-so...
Totally fair! But many research tasks and experiments can be designed as survey-like interactions. Please let us try to convince you: blog.expectedparrot.com/p/surveys-so...
"Surveys" sounds niche and not what I need
Totally fair, but many research tasks and experiments can be designed as survey-like interactions.
blog.expectedparrot.com
April 2, 2025 at 4:39 PM
"'Surveys' sounds niche and not what I need"
Totally fair! But many research tasks and experiments can be designed as survey-like interactions. Please let us try to convince you: blog.expectedparrot.com/p/surveys-so...
Totally fair! But many research tasks and experiments can be designed as survey-like interactions. Please let us try to convince you: blog.expectedparrot.com/p/surveys-so...
Whether or not your ultimate research goal has anything to do with language models, using a model to perform data labeling tasks can be very helpful to your process. Here's a quick example of how to do it in EDSL: open.substack.com/pub/expected...
How to use a language model to label your data
I have a large collection of [texts, images, PDFs, CSVs, tables, transcripts ... ] that I need to [sort, tag, extract, clean, analyze, synthesize, summarize ... ].
open.substack.com
March 27, 2025 at 4:20 PM
Whether or not your ultimate research goal has anything to do with language models, using a model to perform data labeling tasks can be very helpful to your process. Here's a quick example of how to do it in EDSL: open.substack.com/pub/expected...
Do you owe someone an expense report?
Here's a notebook for reading a statement, identifying reimburseables, and drafting a memo, easily modified for your own content and purposes: www.expectedparrot.com/content/Robi...
Here's a notebook for reading a statement, identifying reimburseables, and drafting a memo, easily modified for your own content and purposes: www.expectedparrot.com/content/Robi...
Expected Parrot
www.expectedparrot.com
March 26, 2025 at 4:50 PM
Do you owe someone an expense report?
Here's a notebook for reading a statement, identifying reimburseables, and drafting a memo, easily modified for your own content and purposes: www.expectedparrot.com/content/Robi...
Here's a notebook for reading a statement, identifying reimburseables, and drafting a memo, easily modified for your own content and purposes: www.expectedparrot.com/content/Robi...
[1/6] "How do I use EDSL for data labeling?" Really, this is a grab bag of things you might want to do, such as analyze texts, categorize images, identify and quantify themes, spot issues in your data, etc.
March 19, 2025 at 12:21 PM
[1/6] "How do I use EDSL for data labeling?" Really, this is a grab bag of things you might want to do, such as analyze texts, categorize images, identify and quantify themes, spot issues in your data, etc.
With E[P] you can run jobs locally using your own API keys for LLMs, or use our key which comes with $25 in credits. Toggle on "help me" and we'll dig into any issues with your surveys and experiments and help you fix them!
March 8, 2025 at 6:51 PM
With E[P] you can run jobs locally using your own API keys for LLMs, or use our key which comes with $25 in credits. Toggle on "help me" and we'll dig into any issues with your surveys and experiments and help you fix them!
Reposted by Expected Parrot
Distracting myself by fiddling with something neat...using Expected Parrot's edsl library in-stream in an R data analysis to pass data to ChatGPT (in this case for classification) and then merging the answers back into R (w/ the reticulate package in RStudio).
@johnjhorton.bsky.social
@johnjhorton.bsky.social
November 6, 2024 at 6:18 PM
Distracting myself by fiddling with something neat...using Expected Parrot's edsl library in-stream in an R data analysis to pass data to ChatGPT (in this case for classification) and then merging the answers back into R (w/ the reticulate package in RStudio).
@johnjhorton.bsky.social
@johnjhorton.bsky.social
Hello, Non-Programmer! Build & run LLM surveys w/o knowing Python: app.arcade.software/share/MbB0C3...
Survey Builder
app.arcade.software
March 6, 2025 at 5:10 PM
Hello, Non-Programmer! Build & run LLM surveys w/o knowing Python: app.arcade.software/share/MbB0C3...
Reposted by Expected Parrot
March 6, 2025 at 1:58 PM