Understanding results

Individual expert responses

Each expert's answer in your fields, with their profile, their own words and what the answer rests on.

Every entry in responses is one expert. Responses appear while the request is still pending, as soon as each expert confirms their structured answer.

What is verbatim and what is extracted

quote is the expert's own words. fields and comment are what the expert typed in a written answer, or what was extracted from an interview and then confirmed by the expert. Synquery does not change a confirmed answer.

Basis

first_hand: the expert reports what they have done or seen directly, such as their own hospital or their own deals.
estimate: they extend that experience to a wider claim, such as national adoption.
aggregate: they report figures they have seen from others.

basis_scope says, in the expert's words, how far their experience reaches.

Anonymity

respondent_id is anonymous and stable across all requests in your workspace, so you can see when the same expert answers again. Profiles show role and company type only, unless you asked for named experts.

responses[]

One entry per expert. Present while the request is pending, as each expert confirms.

respondent_idstring#

Anonymous ID, stable across all requests in your workspace.

sidestring#

The perspective, using the values you sent in sides or Synquery's default labels.

title / seniority / company_typestring#

The expert's profile.

last_in_rolestring#

A year, or current.

collectionstring#

written, ai_interview or human_interview.

basis / basis_scopestring#

What the answer rests on, and the scope of that experience in the expert's words.

fieldsobject#

The expert's confirmed values for each answer field; null where unanswered.

unansweredarray#

Names of fields the expert couldn't answer.

commentstring#

The expert's free comment.

quotestring#

The expert's own words, verbatim.

quote_start / quote_endstring#

Position in the interview transcript (hh:mm:ss); null for written answers.

agrees_with_consensusboolean#

Whether this expert sides with the combined answer.

is_past_answerboolean#

true if reused from an earlier request.

received_at / confirmed_atstring#

When the answer came in, and when the expert confirmed the structured version. For past answers, the original dates.

Sample responseGET /questions/{request_id}Fictional data

Question

What share of total knee replacements at US hospitals now use robotic assistance, and what is driving adoption?

answer

Four of five experts put robotic assistance at 20–30% of total knee replacements at the hospitals they know, higher at large systems and orthopedic-focused centers. These are practitioner estimates, not a measured national share.

agreement

4 of 5

on robotic_share

confidence

medium

Agreement within this panel, not factual accuracy

basis

First-hand

Most common basis across answers

experts

5 of 5

1 reused past answer

summary · one entry per answer field

robotic_share20–30%4 of 5 included · estimate

adoption_driversSurgeon training and recruitment · Patient demandtop answers · n 5

barriersCapital cost · OR time during learningtop answers · n 5

outlook_3yrincrease 5 · flat 0 · decrease 0counts · n 5

clusters · robotic_share

20–25%

2 · Surgeon, OR director

25–30%

2 · Surgeon, Seller

35–40%

1 · Seller

disagreement_summary

source: stated

The former device rep counts only hospitals that own a robot; the other four count all hospitals. His figure is reported separately and not blended into the range.

warnings: robotic_share: exp_2c7x1 used a different denominator (hospitals with a robot); excluded from the combined range.

Synthesis, agreement and confidence →