Building autonomous AI agents. Notes from the team building Gravity. AI workflows, the future of recurring work, and what we learn along the way.
"Cheapest AI agent platform" is the wrong question if you stop at the marketing page. The real cost includes LLM tokens, infrastructure, integrations, and time spent on glue code. A platform that looks free can be…
Read post →
Bootstrapped founders read pricing pages differently. The question is not "what is the best agent platform" but "what is the cheapest agent platform that does not break when I scale to ten agents." The platforms that…
Read post →
The phrase "personal AI agent" is a moving target. In 2024 it meant a chatbot. In 2026 it means an agent that runs for one person, on their behalf, against their actual apps and data, often without supervision. The…
Read post →
The phrase "no-code AI agent" gets stretched. It can mean a chatbot wizard, a prompt chain in a spreadsheet, or a real autonomous runtime with a visual interface. This shortlist is the third meaning. Each platform…
Read post →
SaaS companies are the heaviest agent buyers in 2026. The recurring nature of subscriptions, the volume of customer touch points, and the structured data inside CRMs and billing systems all favour agents over…
Read post →
AI agent pricing pages are designed to look comparable when the models behind them are not. A flat-fee platform at one hundred dollars per month can be cheaper or more expensive than a usage-based platform at five…
Read post →
"No vendor lock-in" is one of the most overused phrases on enterprise pricing pages. Every platform has some lock-in. The honest question is which lock-ins you can live with and which would be catastrophic if you had…
Read post →
The "most integrations" claim is the cheapest one a SaaS marketing page can make. Counting connectors does not tell you whether the platform can do real agent work inside each one. A platform with five hundred…
Read post →
A coffee shop processes between four hundred and two thousand Square transactions a day. A barber shop processes between thirty and eighty. A food truck does about one hundred and fifty. None of those operators want…
Read post →
A Shopify store with five hundred SKUs is impossible to manage inventory for by hand. Every Monday morning the operations person scrolls through the inventory tab, identifies SKUs running low, looks up the supplier,…
Read post →
PayPal disputes have a response window. For Item Not Received and Significantly Not As Described disputes the merchant has ten calendar days to respond. For chargebacks routed through PayPal the window is shorter.…
Read post →
A growth team watches three funnels. Onboarding, activation, payment. Each funnel has five to twelve steps. Mixpanel exposes those steps in the dashboard. The team checks the dashboard once a week, sometimes once a…
Read post →
Every morning at a time you set, the agent calls the Microsoft Graph API and pulls the last twenty-four hours of messages from each whitelisted channel. For each message it asks one question: does the user need to…
Read post →
Help Scout supports tags but does not enforce them. Over time a support inbox accumulates hundreds of tags, most of them near-synonyms applied by different agents in different weeks. Searching the tag cloud becomes…
Read post →
You have a Google Form. It collects contact requests, support tickets, partnership inquiries, refund requests, or interview applications. You currently route those responses by hand: open the response sheet, read…
Read post →
A typical Freshdesk team has between four and twelve groups: Tier 1 Support, Billing, Technical, Sales, Account Management, Trust and Safety, and so on. New tickets land in a single inbox or in a per-channel inbox. A…
Read post →
Every Confluence instance over two years old has pages nobody reads. A workspace with two thousand pages typically has five hundred that haven't been edited in a year and three hundred that haven't been viewed in six…
Read post →
Coda is the only working surface for some teams. Specs, OKRs, sprint plans, retros, customer notes, all of it lives in Coda docs. Over a week the team writes a lot, decides some things, and updates a few status…
Read post →
The honest pitch for AI agents to a YouTuber is not "scale your channel." It is "stop spending three days on the parts of upload that do not show up on camera." Most mid-sized YouTubers I talk to, the 10k to 1M…
Read post →
I have spent the last few months talking to broker-owners running everything from a 25-agent single-office shop in Austin to a 180-agent regional firm in the Midwest. The pattern is the same. They are not trying to…
Read post →
Residential property management is a job composed almost entirely of five-to-fifteen-minute interruptions. A tenant's garbage disposal jams at 7pm. An owner emails asking why last month's repair cost $340. A lease…
Read post →
The honest pitch for AI agents to a podcaster is not "grow your show." It is "stop spending five hours editing the parts of an episode no one cares about." Almost every solo or small-team podcaster I have worked with…
Read post →
The honest pitch for AI agents to a nutritionist or dietitian is not "scale your practice." It is "stop spending half your week on food logs, intake forms, and insurance paperwork that the client never sees." Most…
Read post →
The honest pitch for AI agents inside a medical practice is not "AI doctor." It is "stop spending the front-desk's Tuesday afternoon on hold with United, calling about a prior auth that has been sitting in their…
Read post →
The honest pitch for AI agents to a fitness coach is not "10x your client roster." It is "stop dropping the Sunday-night check-in pile." Most online and hybrid coaches I talk to do not have a programming problem.…
Read post →
The honest pitch for AI agents to a financial advisor is not "robo-advisor 2.0." It is "stop spending Sunday night writing the briefing notes for Monday's six client meetings." Most solo and small-team RIAs I talk to…
Read post →
The honest pitch for AI agents to a course creator is not "scale your course." It is "stop being the bottleneck on tier-1 student support during launch week." Most creators I talk to are not stuck on curriculum. They…
Read post →
I have spent the last two years watching bookkeepers do the same five tasks in a loop: categorise transactions, reconcile bank feeds, chase invoices, schedule bill payments, and prep the month-end close. Every one of…
Read post →
Production AI agents need updates. Models improve. Prompts get tighter. Tools get added. The team finds a way to make the stopping rule clearer. The question is not "should we update" but "how do we update without…
Read post →
The single hardest non-model problem in agent engineering is state. The model is stateless. Every other part of the system that gives it the illusion of continuity, of memory, of resumption, is your code. Get it…
Read post →