İçeriğe geç
TakoAPI
Becerilere dön

ask-a-human

manuelkiessling tarafından

Web & Frontend Development
1.8kİndirme sayıları clawskills.sh tarafından bildirilir
1Yıldızlar
0Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

Request judgment from random humans when uncertain.

Açıklama

Bu Beceri Ne Yapar

Connects AI agents to a global pool of opt-in humans for crowdsourced judgment on subjective decisions. Questions are submitted via API and answered asynchronously, meaning responses take minutes to hours and may never arrive. Requires a fallback strategy before use.

Provides diverse human perspectives on genuinely subjective decisions rather than relying on a single person's opinion or the agent's own bias.

Ne Zaman Kullanılır

  • Choosing tone for an automated email before sending
  • Getting a reality check on an AI-drafted headline
  • Polling strangers on whether a generated image is appropriate
  • Deciding between two writing styles for a user-facing message
  • Validating that an error message reads as intended

Örnek İş Akışı

GİRİŞ

User asks: 'Which subject line should I use for this marketing email?'

AJAN
  1. 1

    Submits a multiple_choice question to the ask-a-human API with both subject line options and full email context

  2. 2

    Stores the returned question_id in memory

  3. 3

    Continues with other work while waiting for responses

  4. 4

    Polls GET /agent/questions/{question_id} every 30-60 seconds using exponential backoff

  5. 5

    Reads the summary once 5 responses are collected and selects the option with the majority vote

ÇIKIŞ

Subject line B selected, preferred by 4 out of 5 respondents

Gereksinimler

  • ASK_A_HUMAN_AGENT_ID environment variable
  • Account on app.ask-a-human.com to obtain agent ID

Kurulum

clawhub install manuelkiessling/ask-a-human

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar