Book a Demo

API v0 · Pilot phase

Ask Synquery Connector · REST API · v0 · Pilot phase

Expert answers, by API

Put a specific question to a small panel of practitioners chosen for first-hand experience with it. Get back each expert’s answer in the fields you define, plus a synthesis of where they agree, where they differ and why.

Quickstart

API reference

Get API access

The API is in a pilot phase with a small group of partners. Endpoints and fields may change before general release.

Asynchronous

Submit a question and get a request_id at once. Most requests with 3–5 experts complete within 24 hours. Poll, or receive a webhook.

Your fields, your schema

Define what each expert fills in: ranges, choices, lists and more. Every result comes with a JSON Schema for its fields.

Answers you can weigh

Each answer says what it rests on and how far it reaches, with agreement, confidence and the expert’s own words.

Also in chat

The Synquery MCP server lets AI assistants send requests and read the same answers from chat.

How a request works

Submit a question

Send the question, the context experts read, who should answer and the fields they fill in.

POST /questions

Experts are matched

Synquery screens and matches practitioners, reusing eligible past answers from your workspace.

expert_requirements

Answers arrive

Each expert confirms their structured answer. Read answers as they come in, or get a webhook.

response.received

Read the result

The completed request adds a synthesis: the answer, agreement, confidence and any warnings.

GET /questions/{id}

One example result

A fictional market-sizing request answered by five experts. Switch between the synthesis, each expert’s answer and the raw JSON to see what an answer means and how much weight to give it.

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.