Human judgment,
at API speed.

OpenGuilds is the human-in-the-loop layer for modern AI. Send tasks via REST, and verified guild workers — backed by AI fallback — guarantee every task completes. No null results. No stalled pipelines. Ever.

Live consensus protocol
t = 0.0s
01 · Request

POST /v1/tasks

task_type: "classification"

engineering
02 · Workers respond0/3 in
A
label: "bug"0.00
B
label: "bug"0.00
C
label: "bug"0.00
03 · Consensus

label: "bug"

confidence: 0.91

passed
04 · Webhook

200 OK

latency: 8.4s

delivered
$2.1MPaid to workers
12,400Active workers
99.1%Consensus accuracy
94msMedian queue

From REST request to verified result, in three moves

01

POST a task

Send a single JSON payload to /v1/tasks. Pick a guild, a task type (classification, annotation, judgment, RLHF), and a confidence threshold.

02

Workers reach consensus

Verified guild workers complete the task in parallel. Each answer carries a confidence score; we compute a weighted result and route low-confidence tasks for review.

03

Receive a webhook

Once consensus is reached — or AI fallback completes — we POST the result to your webhook with a signed payload and a completion_source field.

Three guarantees you can build on

Hybrid intelligence

Every task is guaranteed to complete. Verified humans answer first; AI agents step in if a task crosses your timeout. You never get a null result.

Consensus by design

Multiple workers complete each task in parallel. We return a result only when their agreement passes the confidence threshold you set.

Single REST endpoint

POST a task, get a webhook. No queues, no orchestration, no SDK gymnastics. Python and Node SDKs are optional.

Route tasks to verified workers in the right domain

Two guilds open today. Four more in development.

Live

General

Content moderation, data labeling, image classification, form extraction, opinion surveys.

Open to everyone$0.03 – $0.15
Live

Engineering

Code review, security triage, technical documentation QA, architectural judgment.

GitHub or LinkedIn verified$0.50 – $3.00
Coming soon

Medical

Clinical note review, ICD-10 coding, symptom classification, medical image annotation.

Medical license required$2.00 – $15.00
Coming soon

Legal

Contract review, case law analysis, compliance evaluation, legal document classification.

Bar admission required$3.00 – $20.00
Coming soon

Climate

Climate data labeling, carbon validation, environmental impact classification, policy QA.

Domain credential required$0.75 – $6.00
Coming soon

Multilingual

Translation QA, cross-lingual moderation, multilingual RLHF preference ranking.

Native fluency assessment$0.05 – $1.50

Ship what your users actually need:
a real human in the loop.

Free tier includes 100 tasks per month. No credit card. Set up your first task in five minutes.

  • 100 tasks free / month
  • No credit card required
  • AI fallback included