Case studies
My focus: context layers for AI agents. The case study shows client work; supporting projects document further architecture and engineering experience.
0:50 · Governed context workflowCase study: a context layer for AI agents on a temporal knowledge graph. Sourced answers from chat, tickets, wiki and CRM, external actions authorized before execution.
September 5, 2026 · 17 min
HubSpot-native AI layer that scores every contact on ICP fit, ranks the pipeline by expected revenue, and prescribes a specific next action with a written reasoning trace — all as first-class HubSpot properties, no tool switching.
April 23, 2026 · 5 min
Transformation portfolio platform with AI-scored initiatives, capability-maturity radar, and investment recommendations. Replaces steering-committee spreadsheets with continuous prioritization across business value, complexity, maturity, and ROI.
April 22, 2026 · 4 minSupporting development work and technical validation. Each detail page states its project status and measurement limits.
Technical voice AI validation: local inference, a documented warm-path benchmark and the remaining integration steps.
Independent project · no client commissionIndependent PII-redaction project for SAP free text, with results from 16 test documents and clear evaluation limits.
Your agents answer from whatever the retriever finds, and too often that is last quarter's truth. I build the context layer they answer and act from: a temporal knowledge graph that keeps every fact with its source and the time it held, reads with each person's own permissions, and writes nothing without a person's approval. On your own tenant, billed by the hour, step by step.
With your consent I use PostHog (EU) for usage analytics and masked session recordings to find problems. Text and input values are hidden. See the privacy policy.