AI & Agents
Articles about AI & Agents, with practical notes on AI-written enterprise software, governed data, application development, and agent workflows.
-
PublishedWhat Tools Do Forward-Deployed Engineers Use? An Ontology-First Open Stack
Five pains define forward-deployed work: plumbing eats week one, demos die in security review, requirements outrun code, patterns never compound, and the handover poisons trust. An ontology-first open stack removes each one.
AI & Agents Developers Forward-Deployed EngineerOntologyPalantirMCPObjectStack -
PublishedHow Many Tokens Is a Business App? A Complete CRM in 16k
Measured in the unit AI works in, a complete CRM is ~16k tokens of typed metadata — 8% of one context window. Software that fits whole in an agent's context is maintained differently. We call it context-sized software.
AI & Agents Developers CRM Context WindowContext-Sized SoftwareAI AgentsMetadataObjectStack -
PublishedWhen an AI Agent Deletes Production Data: Runtime Guardrails Beat Prompts
The Replit database incident shows a structural lesson: an agent's blast radius must be controlled by runtime permissions, approvals, and audit logs, not only by a prompt.
AI & Agents IT Leaders ReplitAI AgentsRuntime GuardrailsGovernanceAudit -
PublishedHow to Write Agent Rules That Generate Governable Apps
Most agent rule files police style, not governance. Use AGENTS.md, .cursor/rules, and an open declarative target so AI-generated apps are reviewable from day one.
AI & Agents Developers Agent RulesAI-written codeMCPOpen ProtocolGovernancePerspective -
PublishedMCP Security for Enterprise Agents: Why Protocols Need Governed Tools
MCP can connect agents to tools quickly, but enterprise systems need identity, permissions, approvals, and audit behind every tool call.
AI & Agents IT Leaders MCPA2AAgent InteroperabilityTool LayerAI GovernancePerspective -
PublishedWhy AI Agent Pilots Fail Before Production: The Four Missing Layers
A project drew applause on demo day, then was killed four months later by one question from legal. The problem was not the model; it was missing semantics, permissions, approvals, and audit.
AI & Agents Business Leaders AI AgentAdoptionROIGovernanceRuntimePerspective -
PublishedAgentforce vs. an Open Self-Hosted Runtime: When to Choose Each
A company nearly signed with Agentforce until it found that half its data lived outside the suite. Here is when to choose a closed suite, when to choose open self-hosting, and when to use both.
AI & Agents IT Leaders AgentforceCopilot StudioServiceNowOpen PlatformSelf-hostedPerspective