Lab — Lavi Sahu

07Lab — build log

I build this site the way I'd want an AI vendor to build a planning system: show the diff, not the pitch.

Lab — open source

Eight repos, not a mockup

Public, working code, not a portfolio slide: supply-chain planning tools, an AI-config system, an offline voice-dictation app, and the design system this page itself is built from. Pick a card to see what it actually does.

Explore GitHub @LaviSahu

Resilience Radar — Python (stdlib only) — self-contained HTML dashboard

View on GitHub →

Supply chain resilience control tower — risk radar, what-if simulation (time-to-recover / time-to-survive), and mitigation ranking. No dependencies to install; the dashboard is one self-contained HTML file.

git clone https://github.com/LaviSahu/resilience-radar.git

What the code actually does

# risk_score = likelihood(1-5) * impact(1-5), range 1-25.
TIER_THRESHOLDS: list[tuple[int, RiskTier]] = [
    (20, RiskTier.CRITICAL),
    (12, RiskTier.HIGH),
    (6, RiskTier.MEDIUM),
    (1, RiskTier.LOW),
]

def likelihood_score(event: Event, classification: Classification) -> int:
    """1-5, from event confidence (0-1) plus a source-reliability adjustment."""
    base = event.confidence * 5
    adjustment = SOURCE_RELIABILITY_ADJUSTMENT.get(classification.source_category, 0)
    return _clamp(base + adjustment, 1, 5)

src/resilience_radar/scoring.py — classic likelihood × impact risk scoring, plus a per-source reliability adjustment (geopolitical/regulatory signals score noisier than, say, a supplier or logistics event).

Lab — build log

Verification ledger — what's above, and how each piece was actually checked

Seen by human eyes

Every animation on the rebuilt pages

The merge-conflict resolutions of 2026-09-19

Read, not run

The twin's system prompt

Each repo description (2 of 8 carry verbatim code excerpts)

Nobody has checked

Everything the twin tells you

Whether anyone has ever used these repos

The third column is the honest one. It empties only when the gap does — not before.

Lab — build log

Don't take my word for it — move the levers.

Three live tools — scenario simulator, inventory calculator, bullwhip chart. No slides, no hand-waving: every figure is computed in your browser as you move the levers.

Lab — build log

An actual AI feature, not a mockup

This isn't a chatbot embed. It's a Cloudflare Pages Function calling Workers AI directly — origin-locked to this domain, rate-limited per IP, with a system prompt that tells it to say 'I don't know' rather than invent a client name or a number. Ask it something about S&OP or inventory planning.

Ask my AI twin

unverified

A demo: a language model with a short prompt in my voice. It can be confidently wrong — don't act on what it says. Ask it about S&OP, IBP, o9, inventory.

Ask anything about planning. The twin answers in my voice.

Twin self-grade — Tone: close. Facts: unverified by anyone, including me. Model: @cf/meta/llama-3.3-70b-instruct-fp8-fast, capped at 512 tokens, prompted to say "I don't know" rather than invent a client name or a number. A guardrail, not a guarantee.

AI-generated · not a substitute for the real Lavi

Lab — build logMerged, not shipped.

Build log — 2026-09-19

Lab — build logrefkit

Refkit — 28 ports, 1 in production

Every card below is a real VengeanceUI port — working code, not a screenshot. Exactly one of them, VeCreepy, is actually load-bearing right now: it's the Connect link in this site's own footer. The other twenty-seven are verified to render, not yet asked to carry a real page's weight. Same rule as the build log above — a component only counts as shipped once it's doing a job, not once it looks good in a gallery.

Lab — essays

Five frameworks, worked through properly

Not case studies from my own client work — original, research-driven essays on real named frameworks and formulas (bullwhip ratio, TTR/TTS resilience, the Kraljic matrix, Theory of Constraints, digital twins), each grounded in a cited real source, not invented. Pick a card for the summary, or read the full essay.

For the fuller story behind the bullwhip math — two 2000s-era factory fires and what they cost — see Buffer Shock, on the Blog →

# risk_score = likelihood(1-5) * impact(1-5), range 1-25. TIER_THRESHOLDS: list[tuple[int, RiskTier]] = [ (20, RiskTier.CRITICAL), (12, RiskTier.HIGH), (6, RiskTier.MEDIUM), (1, RiskTier.LOW), ] def likelihood_score(event: Event, classification: Classification) -> int: """1-5, from event confidence (0-1) plus a source-reliability adjustment.""" base = event.confidence * 5 adjustment = SOURCE_RELIABILITY_ADJUSTMENT.get(classification.source_category, 0) return _clamp(base + adjustment, 1, 5)

Refkit — 28 ports, 1 in production

Five frameworks, worked through properly