prioritized findings with risk, evidence, and concrete remediation steps
target-state notes for boundaries, logs, rollback, and ownership
quick-win backlog for the first 30 days
plain-language summary that avoids false precision
Relevant evidence: Hands-on work around cloud networking, managed services, migrations, account structure, and security operations; biased toward evidence, blast-radius reduction, and systems a team can maintain.
bounded-agent-integration
Bounded agent integration
Design and build an MCP or agent-facing integration with read-only defaults, clear tool scope, authentication handling, pagination, rate limits, tests, and handoff notes.
working MCP server or integration with explicit tool schemas
authentication and token lifecycle handling
tests, linting, typing, and deployment notes
agent-facing documentation and example prompts
Relevant evidence: Released Cisco FMC MCP Server with token lifecycle handling, rate limiting, transparent pagination, read-only design, pytest, mypy, and ruff.
governed-ai-workflow-plan
Governed AI workflow plan
Turn a proposed AI workflow into an implementable design with identity, tool boundaries, review loops, evidence, fallback paths, and explicit non-goals.
LLM pilotsenterprise AI enablementrisk reviewsagentic workflows
Outputs:
workflow architecture with trust boundaries and tool permissions
control checklist mapped to operational risks
prototype or implementation plan where useful
acceptance tests for safe behavior and handoff
Relevant evidence: MÆI/Smactorio work applies control thinking, external review, and task-scoped tool use to real agent workflows.
security-automation-guardrails
Security automation and migration guardrails
Build or review automation that turns cloud-security decisions into repeatable checks, runbooks, scripts, Terraform patterns, or operational dashboards.
platform engineeringsecurity operationscloud migrationlean teams
Outputs:
automation backlog split by risk and execution cost
scripts or infrastructure patterns for high-value controls
operational runbook with validation steps
handoff notes for the owning team
Relevant evidence: Repeated work converting ambiguous constraints into scripts, runbooks, dashboards, migration notes, and operating patterns.
architecture-reality-check
Architecture reality check
A direct review of a cloud, security, AI, or infrastructure decision when the system is messy and the cost of being wrong is not theoretical.