Topic
AI agents
An AI agent is a language model that can call tools to act on real systems: search, read a record, place an order, open a ticket. These notes cover how we build agents that hold up in production, from grounding and tool design to memory, approval gates and observability.
Most of these notes are about the controls that make an AI agent safe to let act. Server-side grounding, the pattern we built for MayAI, has the agent return only identifiers and the server build everything the user sees from real tool results. DevGuardian AI runs three role-based review agents, an Architect, a QA reviewer and a Security reviewer, and the note on building both in .NET says when a multi-agent system earns its extra agents: only when the work has a genuinely different mandate.
Two notes look at agents from the other side. A website now has a second kind of visitor, an agent acting for a person, and who runs the site's MCP server decides what that agent can see and do. An AI-first CMS turns the content system round: the agent operates it, and people decide what it may publish.
The work behind these notes is our AI agents and multi-agent systems service: single tool-calling agents and role-based teams on Microsoft Agent Framework, with approval gates for anything irreversible and OpenTelemetry tracing from the first prototype.
October 8, 2026 · 4 min read
Your website has a new visitor: AI agents
An MCP server for a website lets AI agents search the site, ask it questions and act on it for a person, and who runs that server decides what agents see. A summary of founder Amir Pournasserian's October 2026 survey of 44 tools, and what it means for a business.
October 8, 2026 · 4 min read
Keeping AI agents honest: the server-side grounding pattern
Server-side grounding is a pattern in which an AI agent returns only identifiers and the server builds everything the user sees from real tool results, so the agent cannot show an invented item. How we built it for MayAI, the six rules around it, and where it applies.
October 8, 2026 · 4 min read
Multi-agent systems in .NET: what we learned building two of them
A multi-agent system is one in which several AI agents, each with its own role and tools, work on the same task. Seven lessons from building two agent systems on Microsoft Agent Framework in .NET: DevGuardian AI, with three review agents, and MayAI, with one agent and six tools.
October 8, 2026 · 4 min read
Why a CMS should let AI operate and people govern
An AI-first CMS is a content management system built for an AI agent to operate, with people deciding what it may publish. Founder Amir Pournasserian's October 2026 design: tools over MCP, rules that become checks, facts stored once and a review desk, and why we plan to prototype it in FluentCMS.
Working on one of these problems?
The patterns in these notes are the ones we use on client work. Tell us what you are building.
Book an AI consultation