Observed Signal · May 15, 2026 · Product Usage · Source: t3n · Impact: 2/5 · Sentiment: Positive
Claude Code Creator Runs Thousands of AI Agents Overnight
Boris Cherny, the developer behind Claude Code, told Sequoia Capital in an interview that he runs large numbers of AI agents using Anthropic’s Claude. While five to ten active Claude sessions during the interview produced a few hundred subagents, Cherny said he typically schedules "a few thousand" agents overnight. He manages most tasks via the Claude mobile app and uses Anthropic features called Loop (client-driven, cron-scheduled tasks) and server-side Claude Routines to run agents even when his devices are offline. Cherny described Loops that monitor CI, fetch social-media feedback every 30 minutes, and perform recurring coding tasks. The piece illustrates a power-user setup for orchestrating many agentic workflows across device-driven and server-hosted execution.
Illustrates practical, large-scale use of agentic workflows and server-side agent execution (Loops and Routines) that signal how power users orchestrate LLM-based automation—relevant to operational patterns and tooling but not a platform policy or major release.
Track Anthropic Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Boris Cherny (Claude Code developer) uses Anthropic’s Claude extensively.
- During an interview Cherny had about five to ten active Claude sessions that spawned a few hundred AI subagents.
- Cherny said he normally runs "a few thousand" AI agents overnight to perform deeper work.
- He manages most agent workflows via the Claude smartphone app and uses Loops (cron-scheduled tasks) plus server-side Claude Routines.
- Examples of Loops include CI monitoring and aggregating social-media feedback every 30 minutes.
Connected Companies & Entities
6 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Boris Cherny Explains Building Anthropic's Claude Code
Boris Cherny, creator and Head of Claude Code at Anthropic, discusses how Claude Code evolved from a side project into a core internal developer tool and the engineering practices that enable agent-driven development. He describes a high-velocity workflow (running multiple parallel Claude instances to produce many PRs per day), retrieval strategies (simple glob/grep driven by the model outperformed more complex RAG/indexing approaches), and deterministic review and sandboxing patterns used to manage safety. The episode also covers Claude Cowork — a VM-based desktop agent built rapidly to serve non-engineers — and organizational shifts: prototypes replacing PRDs, automation of repetitive code-review comments, and a changing skills profile for engineers as agentic tools handle more of the implementation work.
Claude Code Marks Agentic AI Inflection Point
SemiAnalysis argues that Anthropic’s Claude Code — a terminal-native, agentic CLI that reads codebases, plans multi-step tasks, and executes them — represents an inflection point for AI agents and could rapidly displace human coding work. The newsletter reports Claude Code currently authors ~4% of public GitHub commits and projects >20% by end of 2026, powered by Anthropic’s Opus 4.5. SemiAnalysis built a Tokenomics model quantifying revenue and capex impacts for cloud providers (AWS, Google Cloud, Azure) and their supply chains (Trainium, TPUs, GPUs). Anthropic also launched Cowork (desktop agent) on Jan 12, 2026. The piece highlights enterprise adoption (e.g., Accenture training 30,000 people on Claude), potential disruption to seat-based SaaS (Microsoft/Office 365), and wider automation risk across information work.
Treat Claude Code as Teams — Subagents Tripled Speed
A developer recounts six months of production patterns for using Claude Code subagents to speed engineering workflows, arguing that treating the assistant as multiple specialist processes — not a single agent — preserves context and attention. The post defines a subagent as a Claude process with its own context window that performs a scoped task and returns a final summary. The author describes five patterns (parallel independent subagents, independent reviewers, long-form code explorers, specialist subagents, and cautious autonomous runs), gives verification caveats (subagents hallucinate confidently), and recommends small, version-controlled subagent configurations. The author also notes building end-to-end agentic workflows using Claude Code with tools like Cursor and Supabase and running hands-on sessions at Intelligence Academy in Paris.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.