Hermes Agent · data analysis operating system

From raw business problem to shipped analytics product.

I use Hermes Agent as an AI automation layer across the full data-analysis lifecycle: scoping, data QA, SQL/Python analysis, evidence validation, dashboard design, documentation, GitHub PRs, and Vercel deployment.

Standard team workflow, compressed by automation.

Modern data teams win by shortening the path between stakeholder question and trusted decision artifact. My portfolio shows how Hermes Agent makes each stage faster without removing human judgment.

01

Frame

Turn vague stakeholder pain into a decision question, success metric, and caveat list.

02

Ingest

Load public data, define schema, inspect fields, document missing operational signals.

03

QA

Use Hermes to generate data tests, anomaly checks, null checks, and reproducible audit notes.

04

Analyze

Build SQL/Python metrics, compare baselines, segment risk, and keep assumptions explicit.

05

Validate

Stress-test interpretation: association vs causality, proxy vs direct proof, signal vs action.

06

Package

Convert analysis into recruiter-readable dashboard, case narrative, and proof trail.

07

Ship

Push GitHub PR, preview on Vercel, merge to production domain, document next iteration.

Case studies that show the system working.

Each case demonstrates different analytics muscle: forecasting/planning logic and operations-risk triage.

Demand planning

Favorita Planner Exception Queue

Forecast baselines become planner-review candidates using WAPE, MAE, Bias %, Forecast Score, FVA framing, ABC/XYZ segmentation, and replenishment assumptions.

Forecast QAPlanner queueAssumption control

Open case

Delivery operations

Olist Delivery SLA Risk

Late-delivery exposure, review-score association, and seller/category/region investigation candidates framed without unsupported root-cause claims.

SLA riskCustomer impactCandidate triage

Open case

Automation stack

Human-owned logic. Agent-accelerated execution.

Hermes Agent does not replace analyst judgment. It orchestrates repetitive work: code generation, file ops, browser checks, GitHub PRs, site deployment, and documentation discipline.

H

Hermes Agent

Task-executing AI assistant for analysis planning, code iteration, documentation, browser QA, GitHub workflows, and deployment automation.

OD

Open Design

Generates recruiter-facing layout artifacts and case-study pages, then hands accepted HTML into a publish pipeline.

GH

GitHub PR workflow

Every published change has a branch, commit message, reviewable diff, and deployment preview.

V

Vercel production

PR previews for review, main branch deploys to im-khang.com.

Recruiter readout

What this website proves.

I can operate like a lean AI-augmented analytics team: discover the business question, build the evidence model, document limitations, create a decision artifact, and ship it publicly with a modern PR/deploy workflow.

Read end-to-end documentation