AI research system cuts 2-hour skip-tracing to 8 minutes, lands client a $41.5K deal
aryanXmahajan · x · 2026-11-14
The author built an AI research system for a claim-acquisition business client; the client's first deal closed at $41.5K net (screenshot included).
- Pain point: closing was never hard — manually digging county deeds and obituaries for one verified phone number took 2 hours.
- Approach: spent 3 afternoons encoding the client's exact research steps and wiring skip-tracing databases into his laptop; now he drops in a county file, describes the task in 60 seconds, and the AI finishes the 2-hour search in 8 minutes.
- Model: system runs locally on the client's machine; the client still closes deals himself.
A template for indie AI automation consultants: pick a high-ticket vertical with painful manual research, then productize the expert's workflow.
More from coding & agent
- Compacting at 500k tokens costs a third less than 1M: real usage data on context compression — EricBuess · 2026-11-14
- Context Vim idea: diffusion LLMs could edit full code pages with control tokens — ryunuck · 2026-11-14
- Agent drives Unreal Engine via MCP: auto lighting, rendering and self-critique loop — HankYeomans · 2026-11-14
- Running Claude agent sessions visualized as characters in an Oasis game world — LeviTurk · 2026-11-14
- Vibe-Coded Game Hits 35.7K Plays and 10.5K Players in First Week on Spawn — TAbrodi · 2026-11-14
- One dev shipped a Kunio-kun-style beach sports game with Claude in under 12 hours — Duvob90 · 2026-11-14