KeenRaven
The author has 8 years of experience building and shipping software. She has a general software engineering background, with experience in finance earlier in her career and big tech more recently. She focuses on Infrastructure, Security, DX, Policy, and Risk.
8 articles
-
GuidesMCP Servers in Production: Start Narrow, Stay Auditable
MCP works when you treat servers as trust boundaries, not generic adapters. Narrow resource scope, explicit consent, and auditability matter more than broad connectivity.
-
OpinionWhat Belongs in the System Prompt vs the App Layer
System prompts are for steering behavior. Authorization, state changes, retries, and data access belong in the app and server layers where they can be enforced.
-
GuidesHuman Approvals for Agents: Where to Put the Breakpoints
A concrete guide to approval boundaries for agents: side effects, trust boundaries, ambiguous decisions, and the audit trail that makes the approval real.
-
OpinionWhy Internal AI Assistants Fail at Authentication Boundaries
Internal assistants usually fail where identity, permissions, and retrieval meet. Here is why broad access feels productive at first, and why scoped identity design matters more than another prompt tweak.
-
GuidesHow Does OpenClaw Work? A Guided Tour of the Lobster Assistant
OpenClaw (formerly Clawdbot, then Moltbot) is a personal AI assistant that runs on your devices. Here is the architecture: the Gateway control plane, channels, sessions, tools, skills, and the agent loop.
-
GuidesShipping Safe Tooling: Schemas, Validation, and Failure Modes in Tool Calling
A production guide to tool calling safety: designing tight tool contracts, validating outputs, limiting agency, and handling retries, idempotency, and audit logs for tool-using agents.
-
OpinionWhy Frontier Models Are Getting More Restrictive
Moderation is no longer a thin filter on top of a chatbot. For frontier labs, it is becoming an end-to-end product and risk system shaped by capability jumps, regulation, and enterprise expectations.
-
GuidesOpenAI Codex CLI vs Claude Code: A Practical Harness Comparison for Real Repos
Claude Code is the safe bet. Codex CLI came in strong and is already close in UX. Here is the harness-level comparison: approvals, sandboxing, context, and extensibility.