Topic
Notes from our projects
Write-ups of how we built specific systems: the order we built them in, the decisions that held, and what we would tell a team starting today. Each one links to its case study.
MayAI, a consumer agent that turns one chat message into a food order, is where server-side grounding comes from: the model returns identifiers and the server renders every item from real tool results, so an invented dish cannot reach the screen. DevGuardian AI, a code review platform with three role-based agents, needed retrieval built for code: chunks parsed with Roslyn, dependencies in a Neo4j graph (GraphRAG) and re-indexing keyed to git commits. Valco AI, built for Valco Properties on Dubai's daily public property records, shows why the data model comes before any machine learning or chat. One more note draws MayAI and DevGuardian AI together into seven lessons for teams building agents in .NET.
The services behind this work are AI agents and multi-agent systems, RAG and knowledge systems and applied machine learning and forecasting. Every project, including those without a note yet, is on the case studies page.
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 · 3 min read
RAG for code and other structured material: why token-count chunking fails
Most retrieval-augmented generation (RAG) systems split documents by token count, which cuts code, contracts and catalogues into fragments that look right and miss the answer. What we built for DevGuardian AI instead, from code-aware chunks to a dependency graph and incremental refresh, and how it applies beyond code.
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 · 3 min read
From public data to market intelligence: how Valco AI was built
Valco AI is the platform we built for Valco Properties to turn Dubai's daily public property records into market intelligence and a conversational assistant for its staff. The pipeline, the data model, the forecasting models and the conversational layer, and the order we built them in.
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