More from the team

quota.tokens = 50_000
# per-tenant ceiling
burst.limit = 1.2x
Architecture

Quota Design Patterns for Multi-Tenant AI Agent Deployments

How do you prevent one tenant's agent from starving another? This post covers CPU, memory, token, and network quota strategies that hold under concurrent load.

Marcus Pellegrino

sha256(prev_block)
-> block[n].hash
# tamper-evident chain
Audit Trail

Tamper-Evident Audit Logs: What Makes an AI Agent Action Trail Actually Immutable

Appending to a database is not immutability. This post explains hash-chaining, write-once semantics, and what a real tamper-evident audit trail requires at the storage layer.

Yuki Tanaka

ns.isolate(pid, net=deny)
fs.overlay(ro, /tmp/rw)
# least-privilege sandbox
Security

Sandbox Isolation Strategies When Your AI Agent Calls Sensitive APIs

Process isolation, namespace separation, and filesystem overlays each offer different tradeoff profiles. A practical comparison for teams deploying agents that touch production data.

Marcus Pellegrino

layer: runtime # outside trust
layer: app # inside trust
# not the same boundary
Architecture

Runtime Governance vs Application-Level Guardrails: Two Different Problems

Prompt filters and content policies run inside the trust boundary. Runtime governance enforces from outside. Why this distinction matters when your agent has credentials.

Guanlan Dai

policy: hipaa-tier-1
allow: ["hl7.fhir.org"]
phi.egress: BLOCK
Policy

Designing Egress Allowlist Policies for AI Agents in Healthcare Environments

Healthcare platforms face strict controls on where patient-adjacent data can go. We walk through a layered egress policy approach that satisfies technical security reviews without blocking legitimate agent workflows.

Yuki Tanaka

cpu: 250m mem: 512Mi
net: 10MB tok: 80k
# 4-axis quota floor
Operations

The Four Resource Dimensions That Matter for AI Agent Quotas

CPU and memory are table stakes. Network bytes and LLM token consumption are where modern agents actually blow their budgets. A framework for setting and enforcing all four.

Marcus Pellegrino

# threat: prompt-injection
# -> credential exfil
mitigate: isolate + audit
Security

Threat Model for AI Agent Code Execution: What Can Go Wrong and Where

A structured threat model for platform teams: prompt injection paths, credential leakage vectors, side-channel resource abuse, and the runtime controls that address each.

Yuki Tanaka

log.fields: [who, what,
when, why, outcome]
# SOC 2 CC7.2 mapping
Compliance

What Audit Trail Completeness Looks Like for AI Agents in SOC 2 Environments

SOC 2 auditors ask specific questions about what got accessed, by what, and when. This post maps those questions to the runtime log fields an AI agent runtime must produce.

Guanlan Dai

govern(agent) =
limit + observe
+ enforce + audit
Architecture

Building an AI Agent Governance Framework from First Principles

Before reaching for a product, it helps to understand what governance actually means at the runtime layer. A first-principles breakdown of what you are trying to enforce and why.

Guanlan Dai

prompt_filter: WARN only
runtime.enforce: BLOCK
# finserv/healthcare req
Compliance

Regulated Industries Need Runtime AI Controls, Not Just Prompt Filters

Why financial services and healthcare platform teams are finding that LLM-level safety layers alone cannot satisfy their security reviews, and what a runtime enforcement model adds.

Marcus Pellegrino

cap_drop: ALL
cap_add: NET_BIND
# minCap from OS research
Security

Lessons from OS Security for Agentic AI Sandbox Isolation

Process containment, capability-based security, and least-privilege access were solved problems in OS research. This post examines which solutions translate cleanly to AI agent runtimes and where the analogy breaks.

Marcus Pellegrino

Ready to put governance into practice?

The runtime layer that lets your agents operate with credentials, egress controls, and an immutable audit trail in place from the first run.