Before You Scale the AI, Fix the Evaluation
Once an AI system makes measurable decisions in production, evaluation decides whether you can trust it. Five learning outcomes on metrics, operating points, and the handoffs between ML and generative AI.
Tag
Agentic
Whose Authority Reaches the Tools?
65 minutes
Deciding, server by server, whether an ADK agent on Agent Runtime calls its MCP tools as the employee or as itself: on-behalf-of tokens for …
What Your Agents Inherit From Your Data Engineering
25 minutes
An agent can only explain what your data platform can explain. How business rules, their history, and corrections are engineered from the …
From an Entra Sign-In to an Agent Session
43 minutes
How an employee's Microsoft Entra sign-in reaches an ADK agent on Agent Runtime: the token checks, the session binding, who else can call …
Mapping the Agent Before Anyone Attacks It
45 minutes
A reference operations agent on Google Cloud, threat-modelled against OWASP and MITRE ATLAS, with a first control: a deny-by-default policy …
The CTO Playbook for Agentic Systems
6 minutes
A 71-page operating manual for engineering leaders whose software has started to reason, decide, and write the software that carries out …
GATE v1.5 Roadmap
10 minutes
A preview of the next GATE release: a per-control ISO/IEC 42001 mapping with the asymmetry written down, streaming-aware output validation, …
Your System Prompt Is Not a Trust Boundary
16 minutes
A text-to-SQL agent's system prompt cannot enforce a data rule. sql-guard v0.2.0 puts the rule in a parser instead, and closes eight …
Arkhe: An Ontology Language for AI Systems
7 minutes
Two weeks ago I argued that your ontology is the asset and you should own it in a neutral, versioned form. Arguing is cheap. Arkhe v0.2 is …
Your Ontology Is the Asset. Stop Renting It Back.
10 minutes
Agentic AI post-mortems keep naming the same trio: determinism failures, hallucinations, and compliance gaps. An ontology retires all three, …
AI Safety Assurance Is Still Goodwill, Not Evidence
6 minutes
The UN's first scientific assessment of AI says safety assurance still runs on developer goodwill, not verification. Here is what …
Multi-Tenant Agentic AI on Google Cloud: A Production Walkthrough
25 minutes
A review of Google's multi-tenant agentic AI reference architecture stage by stage, naming trade-offs at each decision point and filling the …
Engineered Compliance: Beyond Templates
10 minutes
Regulators do not ask for documents. They ask for systems that behave a certain way and the ability to prove it. We introduce Sakura Sky's …