Building autonomous AI agents. Notes from the team building Gravity. AI workflows, the future of recurring work, and what we learn along the way.
Personal training is a coaching job, but most independent trainers spend a surprising share of their week on tasks that have nothing to do with coaching. Scheduling, reminder texts, weekly check-in emails, program…
Read post →
Nonprofit fundraising runs on relationships, but it gets buried in admin. Development directors at small and mid-size organizations spend a disproportionate share of their week writing acknowledgement letters,…
Read post →
Music production is a creative job buried under a mountain of admin. For every hour you spend in a session, you spend more time managing releases, chasing distributors, reconciling royalty statements, and keeping…
Read post →
Inventory management is one of the most number-heavy, repetitive jobs in any product business. You track hundreds or thousands of SKUs, watch stock levels against reorder thresholds, chase suppliers for delivery…
Read post →
Interior design is a creative profession buried under a mountain of admin. For every hour spent on concepts, material palettes, or site visits, there are several more hours spent chasing vendor quotes, processing…
Read post →
Customer onboarding is one of the highest-stakes workflows in any SaaS or service business. A new customer who reaches first value quickly stays and expands. One who stalls in a slow, manual onboarding process churns…
Read post →
Coze is one of the most capable no-code bot builders shipping in 2026. The canvas is clean, the plugin library is deep, and the free tier is genuinely generous, which is rare in this category. It is backed by…
Read post →
To set spending limits on an AI agent, give it three controls that work together: a per-run cap so one task cannot run away, a budget cap so total spend stays inside a window, and an auto-pause that stops the agent…
Read post →
To schedule an AI agent with cron, you write a five-field expression that says when the run should fire, attach it to the agent, and set the time zone explicitly. A cron schedule turns a one-off agent into a…
Read post →
An agent that never fails does not exist. APIs time out, tools return garbage, a model invents a step that was never asked for, and a permission check blocks an action halfway through a task. The question that…
Read post →
A team workspace for AI agents is a shared space where everyone buys, runs, and governs the same agents under one set of rules, instead of each person quietly building their own. The short answer to "how do I create…
Read post →
Connecting an AI agent to a private API is what turns a chatbot into something that does real work. The agent stops describing what could happen and starts reading your inventory, creating tickets, or pulling a…
Read post →
A data pipeline moves data from where it lives to where it is useful, cleaning and checking it on the way. The hard part is rarely the happy path. Sources change a column name overnight, a feed sends half its usual…
Read post →
To audit an AI agent's decision history, you reconstruct a single run from its log: the input it received, the plan it formed, every tool it called with the arguments and results, the final output, who triggered it,…
Read post →
A travel advisor's real product is judgment: knowing which resort suits a honeymoon, which layover is worth the savings, which supplier answers the phone when a flight cancels. Yet most of an advisor's day disappears…
Read post →
Insurance broking is an admin-heavy trade. An independent broker juggles multiple carriers, chases documents that never arrive on time, and tracks renewal dates across hundreds of clients. The job is advice and…
Read post →
Event planning is a high-volume coordination job dressed up as a creative one. For every hour you spend on design or guest experience, you spend several more chasing vendors, updating spreadsheets, and answering the…
Read post →
A prompt is not documentation; it is the logic of the agent. Change a line and you change how the agent behaves, sometimes for the better, sometimes in ways you only notice three days later when results quietly…
Read post →
An agent that passes every test in the lab can still fail on its first real day. Test data is tidy; the real world is not. Going live is its own discipline, separate from proving the agent works on known cases, and…
Read post →
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 →