Building autonomous AI agents. Notes from the team building Gravity. AI workflows, the future of recurring work, and what we learn along the way.
Founders love to publish waitlist numbers because they look like traction and demand nothing in return. I want to do the less satisfying thing: explain what an early, pre-launch waitlist genuinely tells you, what it…
Read post →
I have started over enough times to be suspicious of momentum that I cannot measure. So at the end of the first stretch of building Gravity in the open, I want to write down what is actually true rather than what…
Read post →
Publishing roughly ten posts a day for a month is an unusual thing to do, and I went in expecting to learn about SEO. I came out having learned more about the difference between producing a lot and saying something,…
Read post →
I have watched a hype cycle from the inside three times, and the first half of 2026 had the unmistakable texture of one turning. Not a crash, a sorting. The capital was still there, the demos were still dazzling, and…
Read post →
I have pitched ideas that were technically better than the thing that got approved, and lost. The lesson stuck: the quality of an agent project rarely decides whether it gets funded. The quality of the buy-in does. A…
Read post →
Most teams do not migrate to AI agents because a vendor sold them on it. They migrate because a Zap broke on an edge case for the third time, or because a Make scenario grew into a 22-step chain that nobody dares…
Read post →
"How long will this take?" is the first question every buyer asks and the one most vendors answer badly. The honest answer is that it depends on which of four very different things you are actually building. A…
Read post →
An executive does not read a business case to learn. They read it to decide whether to bet a slice of budget and reputation on you being right. Everything in the document either reduces their uncertainty or wastes…
Read post →
Choosing an AI agent platform looks easy until you have to defend the decision to a CFO, a security review, and a procurement officer simultaneously. The marketing pages are interchangeable. The pricing is opaque…
Read post →
Agent updates fail badly when they are in-place. A prompt edit lands mid-run and the second half of a conversation no longer matches the first. A new model lands and a tool-call signature shifts. An index rebuild…
Read post →
The vendor quote is rarely the cost. A platform that lists at $5K/month often has a real TCO of $12K to $20K/month once integration build, model usage, maintenance, governance, and change management are added. This…
Read post →
ROI calculations for AI agents fall into two categories: defensible numbers backed by measurement, and made-up numbers backed by vendor claims. The CFO can tell the difference. This guide is the defensible version:…
Read post →
An agent PoC succeeds when the go-no-go decision is obvious within 6 weeks. It fails when scope creeps, baseline is missing, or no one is responsible for the call. The 25-item checklist below covers what to confirm…
Read post →
This is the RFP template I send when buyers ask "give me the question list". Sixty questions across six sections, with a 1-to-5 scoring rubric and walk-away criteria. The template assumes enterprise procurement;…
Read post →
A PoC tells you the technology works. A pilot tells you the deployment works. Most teams skip the pilot because the PoC succeeded; then production hits real volume, real users, and real operational concerns, and the…
Read post →
The on-call runbook is the operational artifact that makes the platform survivable. A well-written runbook turns a 2 AM page into a 10-minute fix the on-call engineer can execute alone. A bad runbook forces a…
Read post →
Most agent platform outages I have seen were not catastrophic. A model provider had an incident; a region's vector store throttled; a deploy clobbered a prompt store; a tenant's run history was deleted by a buggy…
Read post →
Capacity planning for agent platforms looks like web-app capacity planning but with two big differences. The throughput unit is tokens-per-minute, not requests-per-second. The cost curve is steeper because each…
Read post →
Both Anthropic and OpenAI now ship enterprise chat surfaces that look almost identical in the screenshot: a chat thread, file uploads, custom instructions, connectors, and the ability to schedule or repeat work. The…
Read post →
The phrase "AI agent" now covers two products that look similar in a screenshot and behave very differently in production. The first is a chat-first workspace agent: ChatGPT with connectors, files, code interpreter,…
Read post →
SOC 2 is the buyer-facing artifact most enterprise prospects ask for before they let an AI agent platform near their data. It is also one of the most misunderstood. The report does not certify your AI; it attests…
Read post →
Most AI agent purchases go wrong at the sales-call stage, not after deployment. The team likes the demo, the vendor likes the deal, and a year later someone is paying for an unused seat tier with a 60-day notice…
Read post →
An AI agent dashboard does two jobs. It tells the on-call within a minute whether the platform is healthy. It tells a debugger within five minutes why a specific run went wrong. Most dashboards are good at one or the…
Read post →
The classic SaaS isolation problem is well understood: keep tenant data, queries, and identity separated through the request path. An agent platform adds two new surfaces that have to follow the same rules. The…
Read post →
Agent logs grow fast. A single run easily writes dozens of structured events: orchestrator steps, model calls with input and output bodies, tool calls with payloads, retrieval queries with chunk text. Multiply by…
Read post →
Most AI agent platforms first discover their real ceiling during a launch. The dashboard says everything is fine, the model provider's rate limiter starts throwing 429s, the retry loop multiplies the rate of incoming…
Read post →
The point of a canary is to learn things evals cannot. Evals run on a held-out set; production runs on whatever showed up today. Some regressions are visible only at production scale, on production traffic shapes,…
Read post →
Blue-green deployment is older than the cloud, and it still works. The twist for AI agents is that the unit of deploy is not "the binary"; it is the bundle of code, prompts, model version, retrieval index, and tool…
Read post →
Fuel accounts for roughly 24 percent of total fleet operating costs, according to the American Trucking Associations (ATA, 2024). That's the single largest controllable expense for most carriers. And yet the average…
Read post →
Construction is a $1.36 trillion industry in the United States alone (U.S. Census Bureau, 2025). Yet it remains one of the least digitized sectors on the planet. Projects run over budget 80% of the time. Rework eats…
Read post →