Building autonomous AI agents. Notes from the team building Gravity. AI workflows, the future of recurring work, and what we learn along the way.
Some jobs are too big for one agent. Producing a competitor analysis means researching several companies, summarising each, and assembling a comparison; doing all of that in a single agent stretches it thin and makes…
Read post →
Most useful agent work is not a single action. Chasing an overdue invoice means pulling the ledger, finding what is overdue, drafting a message for each client, sending it, and logging the result. That is a…
Read post →
The fastest way to lose trust in an agent is to let it do something irreversible that it got wrong. The fix is not to supervise everything, which would defeat the point of automating, but to design the agent so a…
Read post →
Ask the same agent to do the same thing twice. If it does exactly the same thing both times, it is deterministic. If it might take a slightly different path the second time, it is probabilistic. That single property,…
Read post →
Every agent has to answer two different questions. First, what should I do to reach this goal. Second, how do I actually do it. The first is planning. The second is execution. They look like one smooth motion from…
Read post →
An AI agent can only think about what fits in front of it. That "in front of it" is the context window: the span of text the model reads before deciding its next move. For a quick question it never fills up. For a…
Read post →
A useful AI agent is rarely one giant instruction. Underneath, the good ones are assembled from smaller parts: a tool that reads a calendar, a tool that sends an email, a packaged routine for drafting a reply, a…
Read post →
An AI agent swarm is several agents working in parallel toward a shared goal, coordinating through a shared environment, messages, or a supervisor, with useful behavior emerging from their interaction rather than…
Read post →
The one-line distinction is this: a software robot replays a fixed script of clicks and keystrokes, while an AI agent reasons about a goal and decides its own steps at run time. The robot follows a recording. The…
Read post →
Here is the one-line distinction. A digital worker is a vendor's marketing package: a named, human-shaped persona, say an accounts-payable clerk, that bundles automation, often RPA bots, with some AI on top. An AI…
Read post →
An AI agent is not one thing. Under the surface, the agent follows a control structure that decides how it reasons, when it calls tools, whether it checks its own work, and how it splits a job into smaller jobs. That…
Read post →
Comments are the part of a WordPress site that never sleeps. They arrive overnight, on weekends, and in bursts after a post does well, and a chunk of them are spam, a smaller chunk are abuse, and the rest are the…
Read post →
On X (Twitter), the gap between a mention and a reply is where reputations are made or lost. A frustrated customer tweets, a journalist quotes you, a prospect asks how you compare to a rival, and a bot tags you to…
Read post →
By the time a customer clicks cancel, the decision was made weeks ago. The card that failed three times, the plan that got downgraded, the seats that stopped logging in, the support ticket that never quite got…
Read post →
A new product review lands on your Shopify store. Now the clock starts. A happy five-star note deserves a warm thank-you while the buyer still feels good. A two-star complaint about a torn seam needs a calm reply…
Read post →
Sourcing eats a recruiter's day. You read a role brief, search for people who fit it, read profile after profile, write a first message that does not sound like a template, wait for replies, chase the silent ones,…
Read post →
A spreadsheet is honest about almost everything except its own quality. The rows look fine until a date is stored as text, an email is missing the @ sign, a price has a stray currency symbol, or the same customer…
Read post →
Bank reconciliation is the chore that eats a bookkeeper's week and rewards none of the effort. Most lines match an invoice cleanly: same amount, the invoice number sitting right there in the bank narration. The work…
Read post →
A Webflow form is the easy part. The hard part is what happens in the thirty seconds after someone hits submit: is this a sales lead or a support question, has this person contacted you before, which channel should…
Read post →
The daily live standup is a tax on a distributed team. It interrupts deep work, forces people across timezones into one awkward slot, and most of what gets said is status that could have been read in thirty seconds.…
Read post →
A Notion projects database is only as useful as the moment someone last looked at it. Status fields drift out of date, due dates pass quietly, and the one project that is actually on fire looks identical to the forty…
Read post →
Cold email is unforgiving. A campaign that looks fine on Monday can be burning sender reputation by Friday, and you only notice when reply rates fall off a cliff. The work of catching that early is pure monitoring:…
Read post →
Deals do not usually die from a hard no. They die quietly, sitting in a stage while the rep gets pulled onto something louder, until the close date passes and everyone pretends it was never real. The fix is…
Read post →
The issue tracker is where a project's first impression lives, and an untriaged tracker reads as neglect. New issues arrive with no labels, half of them missing the version or the steps to reproduce, some of them…
Read post →
A no-show is a small wound that bleeds quietly. The prospect who missed your call was interested enough to book, and if nobody follows up in the next day, that intent cools to nothing. The follow-up is simple and…
Read post →
A curated newsletter is mostly grunt work wrapped around a few minutes of taste. Somebody has to read a week of feeds, save the good links, write a tidy sentence about each one, put them in a sensible order, and…
Read post →
Taskade is a polished product, and that is worth saying plainly before drawing any line between it and Gravity. It folds projects, tasks, docs, and AI into one collaborative workspace, and in 2026 it leans hard into…
Read post →
Superagent and Gravity both have the word "agent" in their pitch, and that is roughly where the overlap ends. Superagent in 2026 is an open-source framework for AI agent safety: it blocks prompt injections, redacts…
Read post →
Of all the products Gravity is compared against, Spell.so is one of the closest in spirit. Both are built on the same instinct: stop doing repetitive work yourself and delegate it to AI. Spell.so leans into that with…
Read post →
HyperWrite, from OthersideAI, started as an AI writing assistant and grew into something broader: it still suggests and drafts text as you type, but it now also ships a Personal Assistant that can use your browser to…
Read post →