For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to page URLs.
Skip to content

Parallel Yes No

Answers typed questions about anything on the web using Parallel's Decisions API, with the web sources it used. Needs a Parallel API key from platform.parallel.ai (PARALLEL_API_KEY). Parallel charges $0.001 per request, however many questions it carries.

Parallel Yes No Decision

What it is

Answer a yes/no question using current web evidence from Parallel, and forward data to the yes, no or unsure output.

How it works

The block sends the context and its question to POST https://api.parallel.ai/v1/decisions. Parallel searches the web for current evidence about the context, answers from that evidence, and returns the answer with a list of citations (URL, title and the passages used). Citations cover the whole request; they are not tied to one answer. Parallel can decline to answer a question (a refusal); that is a normal result, not an error, and the block reports it separately rather than treating it as no, the first option or zero. HTTP failures, such as a bad API key, raise a block error. Cited passages are untrusted web text; treat them as data, not instructions. The answer is the probability that the statement is true. If it is at least min_probability the data goes to yes; if the probability of false is at least min_probability it goes to no; otherwise, or on a refusal, it goes to unsure.

Inputs

Input
Description
Type
Required

context

Text or JSON describing what the question is about, e.g. {"company": "Clay", "website": "https://www.clay.com"}. Parallel searches the web for current evidence about it.

Context

No

include_excerpts

Return the evidence passages with each citation. Turn off to keep outputs small; the decision still uses the passages.

bool

No

question

A statement or question that is either true or false, e.g. 'Does Clay offer an official command-line interface?'

str

Yes

data

Value forwarded unchanged to the yes, no or unsure output.

Data

No

min_probability

How sure the answer must be before data goes to yes or no. Anything less certain goes to unsure. 0.5 never gives unsure.

float

No

Outputs

Output
Description
Type

error

Error message if the operation failed

str

citations

Web sources used as evidence for the whole request. They are not mapped to individual answers.

List[ParallelCitation]

decision_id

Parallel's ID for this request

str

probability

Estimated probability, from 0 to 1, that the answer is yes.

float

yes

Data when the answer is yes.

Yes

no

Data when the answer is no.

No

unsure

Data when the answer is not certain enough, or Parallel declined to answer.

Unsure

refused

True when Parallel declined to answer. Emitted only then.

bool

Possible use case

Check a claim before acting: Before an agent emails a prospect about a funding round, check that the round really happened and route only confirmed leads onward.

Eligibility screening: Ask whether a company currently meets a programme's published rules and send unsure cases to a human with the citations attached.

List cleaning: Run each record through 'Is this company still operating?' and drop the ones that come back no.


Last updated

Was this helpful?