AI Orchestration: From Custom Skills to Autonomous Hedge Fund Operations | S2E9

Mar 31, 2026

Jhanvi Virani, COO of Hedgineer and AI infrastructure builder for asset managers, explains translating investment workflows into custom AI skills. She discusses using Claude Code and Cowork for summaries and automation. They cover local schedulers, secure server-side automations, the Agent SDK, and running agentic systems 24/7 to scale institutional workflows.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Cowork Makes Nontechnical Automation Practical

Claude Cowork removes the need for a heavy developer layer by letting non-technical users create scheduled tasks and polished outputs in plain English.
Jhanvi used Cowork to stop attending >50% of meetings by having summarized, high-quality deliverables generated for her instead of live attendance.

ADVICE

Match Claude Interface To The Task

Use CloudCode if you need multiterminal developer workflows and Cowork for visual connectors and scheduled tasks; pick the tool to match the work style.
Michael prefers multiple terminal sessions and screen real estate in CloudCode, while Jhanvi starts net-new projects in Cowork then moves to CloudCode for tweaks.

INSIGHT

Cowork Attachment Limit Blocks Some Automations

Cowork schedule tasks run locally and currently cannot access email attachments, only HTML previews, which limits automating receipt or PDF ingestion.
Jhanvi tested automating expense receipts via email→SharePoint and found attachments cannot be pulled down by Cowork today.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

AI Orchestration: From Custom Skills to Autonomous Hedge Fund Operations

Most asset managers treat AI as just a chatbot, failing to bridge the gap between an LLM's general reasoning and the specific, high-stakes workflows of their actual day-to-day.

In this episode of The Hedgineer Podcast, Michael Watson sits down with Jhanvi Virani, COO of Hedgineer, to discuss the practical mechanics of deploying AI within hedge funds and asset managers. Jhanvi details her experience shadowing a CIO to translate their cognitive investment process into a digital skill—a structured framework that allows Claude to synthesize fragmented data from order management systems, SharePoint research, and consensus estimates into polished, institutional-grade outputs in a one-day turnaround. We move beyond simple prompting to explore the "Agentic Loop," discussing how local schedulers and the Claude Agent SDK are enabling systems to run autonomously 24/7.

The conversation also covers the technical nuances of the Claude Ecosystem, comparing developer-centric Claude Code with user-friendly Claude Cowork. Jhanvi shares her on-the-ground findings regarding the limitations of local vs. remote execution and why building a secure, server-side environment is the ultimate bottleneck for scaling AI intelligence across a firm.

Key Takeaways

The Skill-Based Unlock: How shadowing investment professionals allows engineers to map complex and manual research workflows into automated skills that produce consistent, high-polish one-pagers.
Claude Code vs. Cowork: A breakdown of why developers prefer terminal-based workflows for multitasking, while non-technical users leverage Cowork for scheduled tasks and visual connector management.
Building "AI Native" Infrastructure: The 0-to-1 process of auditing fund workflows, building custom MCP (Model Context Protocol) connectors for legacy data vendors, and establishing organizational agent management frameworks.
The Self-Healing Feedback Loop: Using usage analytics and "meta-agents" to observe behavior, evaluate performance, and automatically suggest system improvements, creating a self-sufficient AI framework.

Timestamps

00:00 - Introduction and the role of skills in unlocking automation

04:15 - Evolving daily workflows with Claude Code and Cowork

08:42 - UI vs. Terminal: Optimizing screen real estate and parallel sessions

14:30 - Testing the bounds: Automating expense reports and attachment limitations

17:45 - Windows vs. Linux runtimes and the "Local Scheduler" in Cowork

22:10 - The Agentic Loop: From Claude Agent SDK to OpenClaw deployments

29:40 - CIO Shadowing: Translating a day of research into a custom AI skill

36:50 - The future of autonomous analytics and observation agents

43:15 - Deliverables for becoming AI Native: Audits, MCP servers, and data warehouses

51:00 - AI Personification: Authenticity in communication and the risk of "AI slop."

64:20 - Team expansion in Bangalore and the tech-focus of South India

Guest Bio: Jhanvi Virani is the COO of Hedgineer, where she oversees the deployment of AI infrastructure and automation for institutional asset managers. She specializes in bridging the gap between technical LLM capabilities and high-level investment workflows.

Host Bio: Michael Watson is the founder of Hedgineer and host of the podcast, focusing on the intersection of data science, AI, and hedge fund technology.