AWS Bedrock Is an Estate, Not an API: FinOps for GenAI
AWS Bedrock cost is not token spend. It is an estate of agents, models, provisioned throughput, and jobs, each billed differently and easy to miss.
zopdev writing tagged ai-ops. Engineering and FinOps notes, post-mortems, and benchmarks.
AWS Bedrock cost is not token spend. It is an estate of agents, models, provisioned throughput, and jobs, each billed differently and easy to miss.
Vertex AI cost sprawls across endpoints, notebooks, feature stores, and jobs. The worst offenders have no off switch. FinOps starts with finding them all.
A team ships a generative-AI summarisation feature. The first month it costs $400 in Bedrock invocations. The second month it costs $1,200 as adoption grows. The third month it costs $9,200 because…
A developer asks Claude Code at 2 AM: "this terraform plan is failing admission, fix the bucket so it deploys." Claude reads the error, generates a slightly different bucket config, runs the plan…
The first ninety days of an MCP server in production are about correctness, not abuse. The team is busy proving the agents do the right thing: the policy lookups return what they should, the audit…
An alert fires at 2:47 AM. A pod in the namespace is in CrashLoopBackOff. The on-call engineer reads the alert, opens Slack to find the team that owns , opens the wiki to find what policies apply to…
The read-only MCP server work shipped clean. AI agents could read tags, search logs, query costs, walk topology. Operators saved hours per incident. The next question was obvious: which writes can…
The 47th agent is when finance shows up. Below 30 agents in production, the Anthropic invoice is one tolerable line item somewhere south of $25,000 a month, and nobody asks who is spending what. Past…
A single Claude API call is predictable. An agent with tool access is not.
The trust ceiling on AI in cloud automation is not capability. It is write access.
One post a week. Sundays. No "10 ways to think about cloud" listicles, just the engineering and FinOps notes we'd want to read.
See. Find. Fix. Automatic.
Connect your first cloud account in under 5 minutes. See your first remediation in under 7. No credit card required.