Skip to main content

​
State machine

PENDING
  │
  ├─ no active campaign ──► PASS_NO_BUDGET
  │                         (user admitted, no payout)
  ▼
ACTIVE
  │
  ├─ no response within 5 min ──► TIMED_OUT (user denied)
  │
  ▼
AWAITING_SCORE
  │
  ├─ Kimi unavailable (4 retries exhausted) ──► SCORING_UNAVAILABLE
  │                                             (user admitted, no payout, no cooldown)
  ├─ score < threshold ──► REPROMPT
  │     │
  │     ├─ second failure ──► COOLDOWN_REJECTED
  │     │                     (user denied, 24h cooldown)
  │     └─ second pass ──► PASSED
  │
  └─ score ≥ threshold ──► PASSED
          │
          ▼
       PAID_OUT

​
Conversation sub-states

Within ACTIVE, the conversation moves through:
  1. GREETING — agent sends opening message from brief
  2. AWAITING_RESPONSE — waiting for user reply
  3. PROBING (conditional) — agent sends follow-up if response was thin; returns to AWAITING_RESPONSE
  4. CLOSING — agent sends final turn; transcript queued for Kimi
Maximum 3 agent turns. The conversational LLM decides whether to probe based on response length and whether the brief’s target signal was collected.

​
Timing

StageTarget
Join detected → DM sent< 2s
Each LLM turn< 1s
Kimi scoring< 3s
logCompletion contract call< 5s
releasePayout contract call< 5s
User admitted< 1s after payout confirmed
Typical total: under 30 seconds for an engaged user.

​
Timeouts

Verification timeout: User does not respond to the initial DM within 5 minutes → TIMED_OUT → user denied. They can rejoin and start a new verification. Rejection cooldown: Two consecutive failures (including re-prompt) → COOLDOWN_REJECTED → 24-hour cooldown on that user/group combination. The cooldown key is tg_user_id + group_id. Kimi outage: Scoring request queued with up to 4 retries and exponential backoff. If all 4 fail → SCORING_UNAVAILABLE → user admitted, no payout released, no cooldown applied. Kimi infrastructure failures do not penalize users.

​
Rate limits

ScopeLimit
Per user per group3 verification attempts per 24 hours
Per group globallySequential processing (no concurrent verifications per group)
Sequential processing per group prevents simultaneous join floods from exhausting campaign budgets faster than intended.

​
Re-prompt

On first failure, the agent sends a single re-prompt using a different angle from the same brief:
“Let’s give it another shot — [rephrased question or different question from the brief].”
If the second attempt also fails, the user is denied and the 24-hour cooldown begins. Failed verifications are not billed to the advertiser.