Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Launching EDSL surveys for real human respondents via humanize, including scenario methods, Prolific integration, and retrieving responses.
Humanize — Sending EDSL Surveys to Real Humans
Humanize converts an EDSL survey into a web-hosted survey on Expected Parrot (Coop) that real people can fill out in a browser. Results come back as standard EDSL Results objects.
Basic usage (no scenarios)
from edsl import Survey, QuestionFreeText, QuestionMultipleChoice
q1 = QuestionMultipleChoice(
question_name="preference",
question_text="Which do you prefer?",
question_options=["Option A", "Option B", "Option C"],
)
q2 = QuestionFreeText(
question_name="why",
question_text="Why did you choose that?",
)
survey = Survey([q1, q2])
info = survey.humanize(
human_survey_name="Preference Study",
survey_visibility="unlisted",
)
print(info["respondent_url"]) # share this link with respondentsprint(info["admin_url"]) # monitor responses here
survey.humanize() returns a Scenario (dict-like) with these keys:
Key
Description
uuid
Human survey UUID — needed to fetch responses later
respondent_url
Public link for respondents
admin_url
Admin dashboard link
name
Survey name
n_responses
Response count (0 at creation)
survey_uuid
UUID of the pushed survey object
scenario_list_uuid
UUID of the pushed scenario list (if any)
Save the uuid — you need it to retrieve responses.
With scenarios
When using scenarios, call .humanize() on a Jobs object (not directly on the survey). You must specify a scenario_list_method.
from edsl import Scenario, ScenarioList
scenarios = ScenarioList([
Scenario({"product": "Widget A", "price": "$10"}),
Scenario({"product": "Widget B", "price": "$25"}),
Scenario({"product": "Widget C", "price": "$50"}),
])
q = QuestionFreeText(
question_name="opinion",
question_text="What do you think of {{ product }} at {{ price }}?",
)
survey = Survey([q])
info = survey.by(scenarios).humanize(
human_survey_name="Product Feedback",
scenario_list_method="randomize",
)
Scenario list methods
Method
Behavior
"randomize"
Each respondent gets a random scenario (with replacement)
"ordered"
Scenarios are assigned sequentially to respondents
"loop"
Survey is expanded — every question is repeated for every scenario (creates a longer survey)
"single_scenario"
Exactly one scenario is used for all respondents (scenario list must have length 1)
Rules:
If you attach scenarios, you must specify scenario_list_method.
If you specify a method, you must attach scenarios.
Agents and models are not supported with humanize — the survey goes to real humans.
Retrieving responses
from edsl import Coop
coop = Coop()
# Using the uuid from the humanize call
results = coop.get_human_survey_responses(info["uuid"])
# Results is a standard EDSL Results object
results.select("answer.preference", "answer.why").print()
If EDSL cannot construct a full Results object (e.g., schema mismatch), it falls back to returning a ScenarioList with the raw response data.
Checking status
status = coop.get_human_survey(info["uuid"])
print(f"Responses so far: {status['n_responses']}")
Prolific integration
For paid recruitment via Prolific:
coop = Coop()
# First, create the human survey
info = survey.humanize(human_survey_name="Paid Study")
# Then launch a Prolific study
study = coop.create_prolific_study(
human_survey_uuid=info["uuid"],
name="Product Preference Study",
description="5-minute survey about product preferences",
num_participants=100,
estimated_completion_time_minutes=5,
participant_payment_cents=150, # $1.50 per respondent
device_compatibility=["desktop", "tablet"],
)
Minimum pay: Prolific requires at least $8.00 USD/hour. EDSL validates this — if your payment / estimated time is below $8/hr, it raises a CoopValueError.
Prolific filters
filters = coop.list_prolific_filters()
# Inspect a filter
filters.find("age")
# Create filter dicts for the study
age_filter = filters.create_study_filter("age", min=25, max=45)
study = coop.create_prolific_study(
human_survey_uuid=info["uuid"],
name="Filtered Study",
description="...",
num_participants=50,
estimated_completion_time_minutes=5,
participant_payment_cents=200,
filters=[age_filter],
)
