00Founder, Efficient Earners · Bengaluru

Anubhav Sood

I run a company on a fleet of AI agents I designed. Before that I carried an enterprise sales quota for five years.

A computer science engineer who worked as a developer before my MBA, based in Bengaluru. Open to Delhi and relocation.

anubhav.sood.1701@gmail.com  ·  +91 63669 77533

AS
Founder · Operator · Engineer
0Agents
0Lines of code
0Months
01The fifteen months

Jun 2025 to now

Jun 2025 to Feb 2026

I started building on the side, with earlier AI tools, and shipped the first version of the market-data engine by hand.

Mar 2026 onward

I moved to agentic coding tools for everything: engineering, marketing and operations. I designed the agent fleet that still runs the company.

Aug 2026

Payments went live on both platforms. The business stopped being a plan and became something people could actually buy from.

02What I built

Eight systems, one operator

Each card names one real, measured number. Nothing below is invented.

The Desk sign-in screen, as far as any visitor without an account can go. 9,014-line pre-deploy gate

The Desk platform

The paid member commerce platform: Cloudflare Pages Functions, KV and Durable Objects, Google OAuth and Razorpay. Signature check, idempotency, then corroboration against the provider before any entitlement opens.

The Desk sign-in screen, as far as any visitor without an account can go.

The My Little Lore storefront homepage, my own build. ~60 defects fixed, one launch day

mylittlelore.com

A second live storefront I built and deployed on my own: a PayPal checkout Worker, R2 signed delivery links and a KV ledger for the record. Earlier, a one-day launch audit for a family venture, Flippy Tales.

The My Little Lore storefront homepage, my own build.

The five-phase pipeline behind the market-data engine: ingest, structure, generate, verify, publish. Boxes and arrows only, no formulas. 15,117 Pine Script files

The market-data engine

An NSE data engine over 87 symbol trees, a five-phase contract-driven pipeline with sha-pinned computation, run daily and weekly.

The five-phase pipeline behind the market-data engine: ingest, structure, generate, verify, publish. Boxes and arrows only, no formulas.

Illustrative render of the core idea: the same instrument shown across five time horizons at once, each with its own shaded balance zone. Synthetic data. 212 instruments, 17 sectors

Blocks

A market-structure tool over 212 NSE instruments across 17 sectors, refreshed every morning. A fail-closed gate: if the check does not pass, nothing publishes.

Illustrative render of the core idea: the same instrument shown across five time horizons at once, each with its own shaded balance zone. Synthetic data.

The marketing operations dashboard, captured with placeholder figures, not live numbers. 12 named agents

The marketing organisation

Twelve named agents under one front door, a judgment and mechanics split, a twelve-platform distribution map with UTM attribution.

The marketing operations dashboard, captured with placeholder figures, not live numbers.

Title card from Module One of "The Read," the 72-chapter flagship video course. 31 agents, two studios

Two video studios

Two multi-agent studios, one for shorts and one for long-form: script gates, scene maps, voice-over, subtitle burn-in, film QA before any render.

Title card from Module One of "The Read," the 72-chapter flagship video course.

Cover of "Trade Less," the Global edition. 72 chapters, 3h16m

The courses and the book

A 72-chapter video course built on a written teaching method, plus a 150-page book across five channels and an India edition.

Cover of "Trade Less," the Global edition.

2,581 founder hours reconciled

The costing system

A single self-contained app that reconciles founder hours and tracks AI-tool spend as a real, dated cost line, not background overhead.

A self-contained hour and spend reconciliation tool, shown here by its icon rather than a screenshot.

03Every project

The full portfolio, filterable by status

Every product and system from my own evidence inventory, in one grid. Completion figures are my own honest estimate, not an audited number, and I say so on every card.

Trade Less, Global book

Live

A 150-page trading-psychology book, published on five channels.

100% (estimate)
gear.efficientearners.com

Trade Less, India Edition

Built, never listed

A 152-page NIFTY and MCX localisation of the book, built but never listed for sale.

70% (estimate)
gear.efficientearners.com

Trade Less, Audiobook

Script only

A roughly three-hour twenty-five-minute narration script plus a companion PDF. No narrator recorded yet.

40% (estimate)

"The Read" video course

Built, undeployed

The 72-chapter flagship video course behind the book. Built and QA-passed, no hosting decision made yet.

85% (estimate)

Micro-Apps course

Scripts done, unfilmed

A 36-unit course on building small apps. All 36 scripts are written, none filmed.

40% (estimate)

F&O Calculator

Live and selling

A standalone trading-cost calculator app, published and selling.

100% (estimate)

Waypoint Year

Built, blocked

An Etsy-style digital life planner, built and blocked on an OAuth issue with its listing images incomplete.

70% (estimate)

Market Basics

Blueprint only

A free entry-level trading course. Blueprint only, scripts not started.

15% (estimate)

Take-Home Tax app

Built, unpriced

A line-by-line tax calculator, built and verified to the rupee. No price set yet.

85% (estimate)

"The Crowd Map"

1 of 36 chapters

A volume-profile companion course. One of 36 chapters finished.

15% (estimate)

Business Costing calculator

Built twice

A standalone costing tool, built twice as two working versions. No ship decision made.

70% (estimate)

Business Pulse

Built, unnamed

A "pocket CFO" business-health app, built as version three. Not yet named or priced.

70% (estimate)

Desk course SKU

Live

"The Read" course, sold as a one-time purchase inside the Desk platform.

100% (estimate)
desk.efficientearners.com

Desk India Book SKU

Live

The India edition of Trade Less, sold as a one-time purchase inside the Desk.

100% (estimate)
desk.efficientearners.com

Desk Combo SKU

Live

Book and course bundled together, one flat price, no pro-rating.

100% (estimate)
desk.efficientearners.com

Desk F&O Calculator SKU

Live

The F&O calculator, sold as a one-time purchase inside the Desk.

100% (estimate)
desk.efficientearners.com

Blocks 10K course

Built, unlaunched

A four-module course teaching market structure by hand, never the engine math. Built, unsigned and not launched.

70% (estimate)

Blocks (the tool)

Data live, payment off

A five-horizon market-structure charting surface inside the Desk. The data engine runs live and automated daily. Membership payment is not switched on yet.

70% (estimate)
desk.efficientearners.com

My Little Lore shop

Live

A 22-bundle printable wall-art storefront, live and taking real payments.

100% (estimate)
mylittlelore.com

Trade Less, legacy Global edition

Out of scope

An older listing on a different storefront, explicitly ruled out of scope by my own decision.

Not applicable (estimate)

EE-Engines

Live

The NSE market-data and charting-script engine behind Blocks, automated daily and weekly, unattended.

100% (estimate)

EE Desk platform

Live

The member commerce platform: Cloudflare Pages Functions, KV, Durable Objects, Google OAuth, Razorpay.

100% (estimate)
desk.efficientearners.com

Public website

Live

The marketing and sales site for Efficient Earners.

100% (estimate)
efficientearners.com

EE Terminal

Paused

A retail and institutional charting terminal, paused for the current quarter with a defined re-launch checkpoint.

70% at pause (estimate)

EE Backtest

Active

The research workbench for trading hypotheses, active and running pre-registered studies.

100% (estimate)

Business Costing OS

Shipped

A self-built bookkeeping application, shipped and in active personal use.

100% (estimate)

Marketing operations system

Active

The dashboard, protocol and agent fleet behind every marketing decision.

100% (estimate)

Micro-project factory

Mixed

A portfolio of ten smaller ventures. One lane is active, nine are paused or blocked.

Mixed by lane (estimate)

My Little Lore stack

Live

The storefront, checkout worker and delivery system behind My Little Lore.

100% (estimate)
mylittlelore.com

Commercial Build

Archived

An earlier script-licensing factory, archived and superseded by a later decision.

Not applicable, superseded (estimate)

Showing all 30 projects.

04The agent operating system

Ninety agents, one router, two vetoes

The agent fleet org chart, grouped by lane

The ninety-agent fleet, grouped into its command, engineering, growth and media lanes, by name only.

The router and model law

M1the fast tier handles file work by default.
M2the frontier-tier model fires only on eight named triggers, then hands back to the fast tier.
M3The frontier-tier model stays capped: a short packet, about fifteen verification reads, no exploration, no writes.
M4Never the smallest tier, not even for a simple search.
M5A risky task gets a second fast-tier pass or a read-only frontier-tier review, never a frontier-tier implementer.
M6Escalations carry a one-page findings map. The frontier tier never re-reads what the fast tier already read.

Single-writer and veto agents

  • Every gate or money-touching file has exactly one owning agent. Two agents never share a file.
  • Two read-only veto agents, compliance and red team, review every release phase.
  • They hold no other job and cannot edit anything.
  • A phase with only agent sign-off is not counted as closed.

The fleet-learning loop

  • One skill is the only sanctioned path from a run-time lesson to a change in an agent or skill definition.
  • Agents themselves never hold that pen.
  • It runs once a day, so the fleet gets slightly better every day rather than drifting.
MCP: I am a heavy operator of connectors day to day, but not yet an author. I am building my first MCP server now.
05Evaluation, cost and safety

Checked in code, not asserted in a slide

3.6M

Pre-registered backtests

3.6 million setups tested against 8 pre-registered cells. Zero of eight passed, and I kept that negative result rather than re-cutting the study.

9,014

The pre-deploy gate

A 9,014-line pre-deploy assertion script, plus live probes after every deploy with automatic rollback if something breaks.

$/token

The token-cost auditor

A tool I wrote that prices every session against published per-token rates, so I see the real cost of the AI work, not just a usage bar.

7 of 7

The SEBI firewall, as build assertions

Vocabulary and data-recency rules written as build-gate assertions, not a style guide. They rejected 7 of 7 draft captions in one real pass. The 30-day data floor I set later matched a July 2026 regulatory circular almost exactly: a cost accepted deliberately, not a margin I got for free.

06Numbers
0
files in the estate
0
lines of code
0
agents
0
skills
0
Pine Script files
0
logged founder hours
0
chapter course
0
dated decisions
07Selling technical products

Five years carrying an enterprise quota

I sell technical products the same way I build them: discovery first. I sit with the engineering or operations side of a deal before I talk price, so the business case I bring back is built on what the buyer's team actually needs, not on a generic deck.

That order, technical discovery then the business case, is why deals that were stuck on objections moved once I was in the room.

  • 01120% of annual quota in FY2023, 180% on the primary line.
  • 02Among the first in the region to sell AI-driven analytics and cloud subscriptions as they launched.
  • 03Closed a stalled ₹3 Cr deal, eight months stuck on technical objections, in 45 days with a custom proof of concept.
  • 04Rescued a ₹1.5 Cr deal the customer had moved to cancel, and grew it 40%.
09Honest gaps and in progress

The story is the system, not the traction

My traction is small today. The honest story is the operating system I built and the discipline behind it, not inflated numbers. Payments have been live since August 2026, and I say that plainly rather than dress it up.

This page is a portfolio of outputs, not construction. It shows what each system does or produces, not how the underlying engines compute their results. Where a system is still being built, I say so plainly, and the completion figures in section 03 are my own honest estimate, confirmed by nobody but me.

In progress, all due September 2026: a small application built on the LLM API with its own evaluation set, an MCP server, and a public reference architecture of the Desk platform.