Notes on getting work done by agents
Comparisons, prices as of this month, and what actually works when you hand a task to an AI agent. Written by the people who build and test them.
How to Give an AI Agent Access to Your Email Safely
Email is the master credential. Most accounts route password resets through it; many financial accounts treat email-confirmed-this as proof of identity. Granting an AI agent access to email is the most consequential…
How to Debug an AI Agent That Did the Wrong Thing
Agent failures look like bugs but behave differently. A traditional code bug is deterministic; the same input always produces the same wrong output. An agent failure is a decision the agent made on an input where…
AI Agent vs Copilot: Active Autonomous vs Passive Assistive
"Copilot" and "agent" are now used interchangeably in marketing copy, which makes the buyer's job harder. The two categories are different. A copilot helps a person do their work; an agent does the work and reports…
AI Agent vs Chatbot vs Assistant: The Structural Differences (2026 Guide)
The terms "AI agent", "chatbot", and "assistant" are used interchangeably by vendors and inconsistently by buyers. The result is that procurement decisions get made on the basis of marketing copy rather than on the…
Why Bootstrapping, Not VC: A Founder's Decision Rationale After Three Shutdowns
The most common question I have been asked since Gravity went public is some version of: why are you not raising? After three shutdowns and a clean fourth bet, the assumption is that VC capital is the next move. The…
What I Learned From Killing a $100K Product (The Hardest Shutdown)
The hardest shutdown across all three startups was the one with revenue attached. Specifically, the $100K-annual-run-rate slice of Super AI that was working in 2025 even as the surrounding product was structurally…
The 3X-Bigger-Than-the-Feature-X Rule (And Why 1.3X Always Loses)
The 10x rule from Zero to One applies at the product level: the whole product needs to be 10x better than the closest alternative for users to switch (Volt Equity, Thiel 10x rule). It is well-known and widely cited.…
The Mistakes I Made With Super AI: A Founder's Decision Postmortem
The public version of the Super AI postmortem is on this site already (read it here). It explains the structural failure: an all-in-one AI router built in 2024, killed in March 2025, in a category that was getting…
Building in Bangalore, Not SF: Geography and Cost After Three Shutdowns
Aryan Agarwal, building Gravity, from Bangalore. The default assumption when a 3x founder builds an AI agent platform is San Francisco. The default assumption is wrong for this company; it is also probably wrong for…
Why I'm Betting Against Workflow Platforms in 2026 (Timing Argument)
This is a timing post, not a thesis post. The thesis lives in describe outcome, not workflow,workflow editors are the wrong abstraction once intelligence has moved into the system. This post is the narrower question:…
Vibe AI Postmortem: Lessons from Building an "AI Friend"
Vibe AI was an AI friend. From March 2025 to February 2026, I built it, ran it, watched it work in week one, watched it stop working by week three, and then watched the unit economics confirm what week three had…
Super AI Postmortem: Why an All-in-One AI App Didn't Work in 2024
Super AI ran from March 2024 to March 2025. Twelve months. The pitch fit on a sticker: describe what you want, we'll pick the model. An all-in-one AI app that auto-routed each prompt to the best foundation model, GPT…
Month 1: Building Gravity in Public, What Shipped, What Didn't
This is month 1 of Gravity, in public. Public means: I write the retro before I have all the answers, name what shipped and what didn't, and let the kill thresholds I set at month start judge themselves. The point is…
Mental Health Platform Postmortem: Why MindWave Shut Down After 13 Months
From October 2022 to October 2023 I ran a mental health startup out of Pune called MindWave. Thirteen months. The core product, private sharing, journaling, and venting, shipped. Real users came. Real users came…
How We Run 80+ Tests Per AI Agent Capability (and Why)
Every Gravity capability ships through 80+ tests across 8 failure categories before it goes near a real user. Not because we love testing, because AI agents are non-deterministic, and "it worked once" is not a…
The Economics of Bootstrapped AI Agent Companies (Unit-Level Math)
The economics of an AI agent company come down to one equation: per-active-agent revenue minus per-active-agent cost-of-inference. If the result is positive, the company can self-fund. If it's negative, no amount of…
Describe Outcome, Not Workflow: The Case Against Zapier-Style Automation
Zapier was the right abstraction for the 2010s. Trigger, step, action, condition, branch. A multi-billion-dollar business on the premise that the user could design the path. The premise is no longer right. The…
Bootstrapping an AI Agent Platform in 2026: A Founder's Playbook
Three shutdowns ago, I'd have raised a seed round to build Gravity. After three shutdowns, the framework I came back to is bootstrap. Not because raising is wrong, it's the right move for plenty of founders, but…
Three Startups, Three Shutdowns: What I Learned Before Building Gravity AI
In early 2026, 40% of AI startups launched in 2024 had already shut down (TechStartups, AI shutdowns roundup, December 2025). I'd already been in three of those statistics, just a year or two earlier than the cohort.…