← Back to the wire

How we built Jarvis, our AI team member for every department

AnnouncementProductNov 16, 2026

Agora built Jarvis, an AI agent running on Claude, to automate daily search quality assurance for its product catalog. Jarvis operates from its own laptop and Slack account, coordinating dozens of sub-agents on scheduled tasks: search QA at 5 a.m., training-run checks, and a Slack responder every 30 minutes. It does not learn between runs; behavior is governed by editable plain-English instructions. Guardrails include limited permissions, request verification, and no irreversible actions without human approval.

Receipt № 29301 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01high
www.searchagora.comOfficialhttps://www.searchagora.com/blog/how-we-built-jarvis-our-ai-team-member-for-every-departmentThis first-person account from Agora explains the internal architecture and operating philosophy behind Jarvis, detailing its scheduled tasks, skills, connectors, and the decision to make its behavior fully editable in plain English.
PRIMARY
ClaudeModelSlackCompanyAgoraCompanyJarvisModel
Canonical: https://www.searchagora.com/blog/how-we-built-jarvis-our-ai-team-member-for-every-department