Notes from the build
What we learn building company software with agents and running our own company on it, for the people who decide how their company runs.
- Agent sprawl: how to run a company on one AI agent instead of 3,000Companies are building AI agents by the thousand, each with its own instructions, its own keys and its own copy of the rules. Vercel went the other way and moved hundreds of internal agents behind one. Here is how a company runs on a single agent, and what has to sit behind it.11 min read
- MCP gateway vs raw MCP servers: how to run a company through any agentEvery tool your company uses now has an MCP server, and the usual way to give an agent access is to plug them all in. It demos well and breaks on permissions, rules, context and the next agent you try. An MCP gateway over your company's ontology gives every agent one door, with your own actions, roles and history behind it.15 min read
- Read this before you cancel HubSpot or SalesforceCompanies are cancelling CRM contracts and having AI agents write their own. Writing the CRM is now the easy part. What decides whether it survives is the layer underneath it: objects, permissions, actions, history and safe access for agents. That layer is called an ontology.10 min read
- AI agents can build your BI. Here's why they get the numbers wrong.Benchmarks keep finding that agents writing SQL against raw tables give confident wrong answers, while the same agents answering through a semantic layer get nearly everything right. What that means for how you build analytics now.4 min read
- SaaS becomes company contextAgents are now how people ask questions and get work done. The CRM, the BI tool and the warehouse stop being separate products and become one thing a company owns: its context. Here is what that is made of, and why we're building it.3 min read
- Semantic layer or ontology? Your agents need both.A semantic layer tells an agent how to count. An ontology tells it what exists and what it may do. One makes agents good analysts; the other lets them do the work. Here is the difference, and how the two fit together.3 min read
- How to leave GA4 without losing a single reportYou don't have to rip out gtag to own your web analytics. Change where it sends, keep GA4 running while you rebuild, and switch only when the numbers match.3 min read
- Lead scoring without a training pipelineGrade every demo request against standards written in plain language. The standards are drafted from your own CRM history, applied by a decision model, and changed by editing text instead of retraining.3 min read
- The future of ad traffic verification with SegmentStream and JevAd traffic verification is still sold as a black box for $60–100k a year. The next generation runs next to your conversions, is checked against real outcomes, and is decided by a model built for decisions.11 min read
Have us build it. Start a pilot.
Start a pilot
Our engineers build the first version on your data in two weeks, at a fixed price.
Or build it yourself with your coding agent:
curl -fsSL https://segmentstream.com/install.sh | sh