An Anthropic Japan BDR runs his sales day with a fleet of six Claude agents
Claude (Anthropic) · rss · 2026-10-16
Shahboz Ibragimov, a BDR on Anthropic's Japan team, details how he automated most of his sales routine with a fleet of Claude agents (named Nakama), now running on Claude Managed Agents (beta).
Agent fleet
- Furiwake: routes the daily inbound lead queue across the team each morning, posting a Slack report.
- Sabaki: qualifies and categorizes his leads, executes the defined next step, updates Salesforce, drafts first-touch emails.
- Henji: scans his inbox hourly and drafts Japanese/English replies.
- Shoudan: pushes customer-interaction updates into Salesforce opportunities.
- Nokori: end-of-day calendar scan, meeting summaries, follow-up drafts.
- A coordinator agent checks a Slack channel every 15 minutes, applying plain-language change requests and versioning each agent's instructions.
Playbook and lessons
- Prototype in Claude first with "one skill + one scheduled task + one shared folder as knowledge base," then migrate to Managed Agents once agents exceed what you can track (skill → system prompt, task → deployment schedule, folder → memory store).
- Key benefits: background runs with no cron to maintain; a single shared memory store so a correction learned by one agent propagates fleet-wide; credentials in managed vaults with scoped permissions.
- He stresses non-developers can do this: describe each agent's job in plain language and let Claude write the short setup scripts.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23