How an FDE maps business processes for AI deployment using three sources
vasuman · x · 2026-10-02
A practitioner thread from startupideaspod explains how a Forward Deployed Engineer maps real business processes before deploying AI, using three sources:
- People: the "20-year veterans who just handle it" — in finance, interview heads of AP, AR, reconciliations, billing, banking, and FP&A to build a "human API."
- Systems of record: 3-4 weeks of real-time Salesforce access to see what data comes in and how often it gets corrected.
- Documents across SharePoint, Drive, Notion, Slack, Teams, and Gmail.
Key takeaways: system data without interviews misses half the picture, and the mix varies — large companies may have 10 years of Salesforce data while SMBs keep most knowledge in people's heads. Choose your angle per company before you build.
More from coding & agent
- Muse agent files $2k flight disruption claim a user procrastinated on for months — armand_ruiz · 2026-10-02
- IBM's Torch Spyre team: an agentic CI pipeline to keep pace with PyTorch — lmoroney · 2026-10-02
- Open-Source Coding Agent Z-Engine Delegates Micro-Decisions to a System 1 Model — arshadbarves · 2026-10-02
- Don't Use Agents to Book Flights: Aim for Tasks That Save Months, Not Minutes — jesselyu · 2026-10-02
- Multi-Step Agents on Mobile: Latency, State, and Context Are the Bottlenecks — QuantumQuillQuester · 2026-10-02
- Tencent's AutoGUIWorld Uses Image Generators as World Models, Synthesizing 79K GUI Trajectories Without Running Software — Tencent-Hunyuan · 2026-10-02