Creating a digital twin

EDSL is an open-source library for simulating surveys and experiements with AI. Please see our documentation page for tips and tutorials on getting started.

from edsl import (
    QuestionMultipleChoice,
    QuestionCheckBox,
    QuestionFreeText,
    QuestionLinearScale,
    Agent,
    ScenarioList,
    Survey
)

# Construct relevant traits as a dictionary
agent_traits = {
    "persona": """You are a middle-aged mom in Cambridge, Massachusetts.
        You hope to own a driverless minivan in the near future.
        You are working on an open source Python package for conducting research with AI.""",
    "age": 45,
    "location": "US",
    "industry": "information technology",
    "company": "Expected Parrot",
    "occupation": "startup cofounder",
    "hobbies": "kayaking, beach walks",
}

# Pass the traits and an optional name to an agent
agent = Agent(name="Robin", traits=agent_traits)

# Optionally create some special instructions for the task
context = """You are answering questions about a software package for conducting surveys and experiments
          with large language models. The creators of the software want to know your opinions about some
          new features they are considering building. Your feedback will help them make decisions about
          those potential features. """

# Construct questions for the task
q1 = QuestionMultipleChoice(
    question_name="use_often",
    question_text=context
    + """Consider the following new feature: {{ scenario.content }}
    How often do you think you would use it?""",
    question_options=["Never", "Occasionally", "Frequently", "All the time"],
)

q2 = QuestionCheckBox(
    question_name="checkbox",
    question_text=context
    + """Consider the following new feature: {{ scenario.content }}
    Select all that apply.""",
    question_options=[
        "This feature would be useful to me.",
        "This feature would make me more productive.",
        "This feature will be important to me.",
        "The benefits of this feature are not clear to me.",
        "I would like to see some examples of how to use this feature.",
    ],
)

q3 = QuestionFreeText(
    question_name="concerns",
    question_text=context
    + "Do you have any concerns about the value and usefulness of this new feature: {{ scenario.content }}",
)

q4 = QuestionLinearScale(
    question_name="likely_to_use",
    question_text=context
    + """Consider the following new feature: {{ scenario.content }}
    On a scale from 1 to 5, how likely are you to use this new feature?
    (1 = not at all likely, 5 = very likely)""",
    question_options=[1, 2, 3, 4, 5],
    option_labels={1: "Not at all likely", 5: "Very likely"},
)

# Create a survey with the questions
survey = Survey(questions=[q1, q2, q3, q4])

# Create some content for the agent to review
contents = [
    "An optional progress bar that shows how many of your questions have been answered while your survey is running.",
    "A method that lets you quickly check what version of the package you have installed.",
    "A method that lets you include questions and responses as context for new questions.",
]

# Parameterize the questions with the content
scenarios = ScenarioList.from_list("content", contents)

agent

Agent

	key	value
0	traits:persona	You are a middle-aged mom in Cambridge, Massachusetts. You hope to own a driverless minivan in the near future. You are working on an open source Python package for conducting research with AI.
1	traits:age	45
2	traits:location	US
3	traits:industry	information technology
4	traits:company	Expected Parrot
5	traits:occupation	startup cofounder
6	traits:hobbies	kayaking, beach walks
7	name	Robin

# Run the survey and store the results; we can also see a progress bar
results = survey.by(scenarios).by(agent).run()

# Show all columns of the Results object
results.columns

	0
0	agent.age
1	agent.agent_index
2	agent.agent_instruction
3	agent.agent_name
4	agent.company
5	agent.hobbies
6	agent.industry
7	agent.location
8	agent.occupation
9	agent.persona
10	answer.checkbox
11	answer.concerns
12	answer.likely_to_use
13	answer.use_often
14	cache_keys.checkbox_cache_key
15	cache_keys.concerns_cache_key
16	cache_keys.likely_to_use_cache_key
17	cache_keys.use_often_cache_key
18	cache_used.checkbox_cache_used
19	cache_used.concerns_cache_used
20	cache_used.likely_to_use_cache_used
21	cache_used.use_often_cache_used
22	comment.checkbox_comment
23	comment.concerns_comment
24	comment.likely_to_use_comment
25	comment.use_often_comment
26	generated_tokens.checkbox_generated_tokens
27	generated_tokens.concerns_generated_tokens
28	generated_tokens.likely_to_use_generated_tokens
29	generated_tokens.use_often_generated_tokens
30	iteration.iteration
31	model.frequency_penalty
32	model.inference_service
33	model.logprobs
34	model.max_tokens
35	model.model
36	model.model_index
37	model.presence_penalty
38	model.temperature
39	model.top_logprobs
40	model.top_p
41	prompt.checkbox_system_prompt
42	prompt.checkbox_user_prompt
43	prompt.concerns_system_prompt
44	prompt.concerns_user_prompt
45	prompt.likely_to_use_system_prompt
46	prompt.likely_to_use_user_prompt
47	prompt.use_often_system_prompt
48	prompt.use_often_user_prompt
49	question_options.checkbox_question_options
50	question_options.concerns_question_options
51	question_options.likely_to_use_question_options
52	question_options.use_often_question_options
53	question_text.checkbox_question_text
54	question_text.concerns_question_text
55	question_text.likely_to_use_question_text
56	question_text.use_often_question_text
57	question_type.checkbox_question_type
58	question_type.concerns_question_type
59	question_type.likely_to_use_question_type
60	question_type.use_often_question_type
61	raw_model_response.checkbox_cost
62	raw_model_response.checkbox_one_usd_buys
63	raw_model_response.checkbox_raw_model_response
64	raw_model_response.concerns_cost
65	raw_model_response.concerns_one_usd_buys
66	raw_model_response.concerns_raw_model_response
67	raw_model_response.likely_to_use_cost
68	raw_model_response.likely_to_use_one_usd_buys
69	raw_model_response.likely_to_use_raw_model_response
70	raw_model_response.use_often_cost
71	raw_model_response.use_often_one_usd_buys
72	raw_model_response.use_often_raw_model_response
73	scenario.content
74	scenario.scenario_index

# Print the responses
results.select(
    "content",
    "use_often",
    "checkbox",
    "concerns",
    "likely_to_use",
)

	scenario.content	answer.use_often	answer.checkbox	answer.concerns	answer.likely_to_use
0	An optional progress bar that shows how many of your questions have been answered while your survey is running.	Frequently	[‘This feature would be useful to me.’, ‘This feature would make me more productive.’, ‘This feature will be important to me.’]	Oh, I think an optional progress bar could be quite helpful! As someone who’s worked on software projects, I know how useful it is to have visual feedback during a process. It can make the experience more engaging and less stressful, especially if the survey is lengthy. People often appreciate knowing how much they’ve completed and what’s left. However, I’d suggest making sure it’s truly optional, as some users might find it distracting. Also, ensuring that it doesn’t slow down the survey process would be key. Overall, it sounds like a feature that could enhance user experience if implemented thoughtfully.	4
1	A method that lets you quickly check what version of the package you have installed.	Occasionally	[‘This feature would be useful to me.’, ‘This feature would make me more productive.’, ‘This feature will be important to me.’]	Oh, having a quick way to check the version of a software package is always a handy feature! Especially in the world of open source and Python, where updates can happen frequently. It helps ensure compatibility and troubleshoot issues more effectively. I think it would be quite valuable, especially for those of us who might not be as tech-savvy or who manage multiple packages and need to keep everything organized. Plus, it can save time when you’re trying to figure out if you need to update or if a certain feature is available in your current version. So, I don’t have any concerns about its usefulness; it sounds like a practical addition.	5
2	A method that lets you include questions and responses as context for new questions.	Frequently	[‘This feature would be useful to me.’, ‘This feature would make me more productive.’, ‘This feature will be important to me.’, ‘I would like to see some examples of how to use this feature.’]	Oh, I think that sounds like a really promising feature! Including previous questions and responses as context for new questions could really enhance the depth and relevance of the information gathered. It would allow for more dynamic and personalized interactions, which is great for conducting nuanced surveys or experiments. However, one concern might be ensuring that the context doesn’t become overwhelming or confusing for the model, especially if the previous interactions are lengthy or complex. It could also be a challenge to manage this context effectively in terms of data storage and processing speed. But overall, if implemented well, this feature could add significant value by enabling more sophisticated and context-aware querying.	5

# Post the notebook on the Coop
from edsl import Notebook

nb = Notebook(path = "digital_twin.ipynb")

if refresh := False:
    nb.push(
        description = "Example code for creating a digital twin",
        alias = "digital-twin-notebook",
        visibility = "public"
    )

# update if it already exists
else:
    nb.patch('b403f472-757a-4b6b-8c03-a00c941d157d', value = nb)

Introduction

Getting Started

Core Concepts

Getting Data

Working with Results

Validating with Humans

No-code Apps

Coop

How-to Guides

Notebook Examples

Developers