writing
Series · 8 posts published · 8 planned

FinAI Build Building a Financial AI in Four Months

Building a financial recommendation system with Claude Code, on consumer hardware, as a three-person team.

한국어 ↗
Episodes
8 / 8

No episodes published yet.

2026
EP 1 04 · 18 EN

[FinAI Build] Ep 1 — The Premise

What three people with one desktop GPU set out to replace — an 80-DAG ALS recommender that could not explain itself and could not scale past one task — and how that starting constraint shaped every later architectural choice.

#finai-build#architecture#claude-code#financial-ai#ple
read
EP 2 04 · 21 EN

[FinAI Build] Ep 2 — Organizing the AI Agents

Five phases, four tools — how Gemini, Claude Opus, Cursor, and Claude Code each took a specific slot (ideation / technical validation / scaffolding / implementation / paper writing). Why tool separation beat tool uniformity on both speed and quality.

#finai-build#claude-code#architecture#financial-ai
read
EP 3 04 · 24 EN

[FinAI Build] Ep 3 — How We Adapted: Guardrails, Memory Bank, Contract Verification

The mechanisms that kept three parallel AI-agent teams from breaking at integration — the CLAUDE.md constitution, the migration from a manual memory bank to Claude Code auto-memory, and the interface-key diff check run after every parallel session.

#finai-build#claude-code#architecture#financial-ai
read
EP 4 04 · 28 EN

[FinAI Build] Ep 4 — The Seven Experts: Importing Structural Isomorphism Across Eleven Disciplines

Why seven experts, why these seven. The cross-disciplinary scan with Gemini surfaced eleven fields; the feasibility review with Opus narrowed to DeepFM, Temporal Ensemble, HGCN, PersLay, Causal, LightGCN, and Optimal Transport.

#finai-build#architecture#ple#expert-pool#financial-ai
read
EP 5 05 · 01 EN

[FinAI Build] Ep 5 — The Data Integrity Hunt

Before any architecture debate — three chained label-leakage detections, the deterministic-leakage rationale behind the 18→13 task reduction, and the self-replicating features that surfaced across synthetic-data iterations v2→v3→v4.

#finai-build#data-integrity#leakage#financial-ai
read
EP 6 05 · 05 EN

[FinAI Build] Ep 6 — The Bug That Overwhelmed All Architectural Decisions

For weeks sigmoid gating seemed to beat softmax. Fixing an uncertainty-weighting implementation bug flipped the result. A case study in how a training-environment bug contaminates architectural conclusions.

#finai-build#debugging#methodology#financial-ai
read
EP 7 05 · 08 EN

[FinAI Build] Ep 7 — Distillation and Serving: PLE → LightGBM → Lambda + 5 Bedrock Agents

Teacher is PLE, student is per-task LightGBM, serving is AWS Lambda. Why this combination, what happens when teacher-student fidelity fails, and the role division across the 5-agent Bedrock pipeline.

#finai-build#distillation#serving#lambda#bedrock
read
EP 8 05 · 12 EN

[FinAI Build] Ep 8 — Honest Negative Results and What Comes Next

Record from four months — how adaTT converged to a null effect at 13-task scale, why GradSurgery was rejected on VRAM overhead, Paper 3 WIP status, and real-data metrics pending after 2026-04-30. Why what did not work matters as much as what did.

#finai-build#adatt#gradsurgery#negative-results#financial-ai
read