Building autonomous AI agents. Notes from the team building Gravity. AI workflows, the future of recurring work, and what we learn along the way.
Medical billing teams spend a significant portion of every day on work that is structured, repetitive, and rule-driven: scrubbing claims before submission, sorting denial codes, looking up modifier rules, and chasing…
Read post →
Law firm intake is where potential clients either become clients or leave for the next firm on their list. The quality of the intake experience, specifically how quickly the firm responds, how clearly it…
Read post →
Insurance agents spend a significant portion of their working week on tasks that are structured and repeatable: sending renewal notices, following up with new leads, collecting application documents, and updating…
Read post →
Architecture firms run on two parallel tracks: design work and coordination work. The design track is where principals earn their fees. The coordination track, proposals, spec updates, submittal logs, RFI chains,…
Read post →
Function calling and tool calling describe the same core behavior: a language model emits a structured request for an external capability, and the runtime executes it. The terms are often used interchangeably, but…
Read post →
Agent reflection is the process by which an AI agent evaluates its own output, identifies problems, and revises the result before returning it. It is how agents catch their own mistakes without requiring a human in…
Read post →
Long-term memory in an AI agent is any mechanism that stores information outside the active context window so it can be retrieved in a future session. Without it, an agent starts fresh on every run: no record of…
Read post →
LLM-based AI agents are probabilistic by default: the same input can produce different outputs on different runs. This guide explains where that variability comes from and the practical techniques teams use to…
Read post →
Staffing agencies win or lose on speed and throughput. The agency that sources a strong shortlist first, screens accurately, and moves candidates through the process without losing them to slow communication gets the…
Read post →
SEO agencies spend a large portion of each month on work that is structured and repeatable: running audits, pulling rank data, building client reports, researching keywords, and monitoring competitors. AI agents…
Read post →
SaaS customer success teams are expected to do more with fewer touches: protect net revenue retention, accelerate time-to-value for new accounts, and surface expansion opportunities, all while the book of business…
Read post →
PR agency work is 60 percent research and tracking, 40 percent relationship and strategy. Every pitch requires finding the right journalist, reading their recent coverage, personalizing the hook, and then monitoring…
Read post →
Running an Etsy shop means doing the creative work and the shop operations yourself, usually at the same time. Every order needs a confirmation message, every shipped package needs a tracking update, every listing…
Read post →
AI agents for dropshippers handle the operational work that scales badly with humans: routing orders to suppliers, syncing tracking numbers, sending customer updates, and monitoring supplier stock and prices. You…
Read post →
Solo digital marketing freelancers carry an unusually wide operational load: they do the client work, generate the reports, write the proposals, chase the invoices, manage the content calendar, and keep tabs on three…
Read post →
AI agents do not write your copy for you. They handle everything that has to happen before you write and after you submit, so you can spend more of your day doing the work that only you can do. Research, intake,…
Read post →
Running an Amazon business means managing a constant stream of operational tasks: listings that drift out of rank, inventory levels that creep toward zero, buyer messages that need a reply within 24 hours, and Seller…
Read post →
Three open protocols are competing to become the connective tissue of agentic AI systems: MCP, A2A, and ACP. Each solves a different interoperability problem, and understanding the distinction determines whether you…
Read post →
The short answer: LangSmith is LangChain's developer observability, tracing, and evaluation platform for LLM applications that engineers build and maintain in code. Gravity is an AI agent platform where…
Read post →
OpenAI and Anthropic are the two labs most cited when people argue about where AI agents are heading. They share a lot. Both build frontier models, both let those models call tools, and both have moved toward agents…
Read post →
Most people who ask how accurate their AI agent is are really asking the wrong question. They reach for a model benchmark number, a leaderboard score, a percentage from a vendor deck. None of that tells you whether…
Read post →
Your agent worked yesterday. Then someone tightened a prompt, the model provider shipped an update, or a tool changed its output format, and now it quietly fails one in five of the cases it used to handle. Nobody saw…
Read post →
You can score AI agent output quality four main ways, and most teams end up using a blend. Rubric-based scoring rates each output against named dimensions on a fixed scale. LLM-as-judge uses a strong model to apply…
Read post →
The big shift in AI agent pricing for 2026 is this: the per-seat subscription, the model that built modern SaaS, is losing its grip. When software was a tool a person operated, charging per login made sense. Agents…
Read post →
You just got off a good sales call. The prospect leaned in, raised one real objection, and agreed to a next step. Then the next call starts, the day fills up, and by evening the follow-up is a vague intention instead…
Read post →
Recurring client check-ins are the work that keeps relationships warm and accounts from quietly slipping away. The problem is rarely the message itself. It is the prep behind it: pulling up what the client has been…
Read post →
Most teams decide an agent is "ready" by trying it a few times and getting a good feeling. That is how a demo passes and production fails. An evaluation framework replaces the gut call with a repeatable process: you…
Read post →
If you want citable numbers on AI agent adoption, the honest starting point is this: the curve is steep, but the figures depend heavily on how each survey defines an "agent." The baseline is now near-universal.…
Read post →
You changed the prompt, swapped the model, or added a tool, and now you want to know if the new agent is actually better. The honest answer is that you cannot know from a few hand-checked examples. Agent behavior…
Read post →
The weekly team meeting, the biweekly project sync, the monthly leadership review: these standing meetings are where a lot of work is steered, and where the record is usually worst. Someone takes notes one week,…
Read post →