Claude
Anthropic's hosted models for reasoning, writing and code. Claude is a family of large language models from Anthropic, available through Anthropic's API and through major cloud platforms including Amazon Bedrock and Google Cloud Vertex AI. It supports long context, tool use, vision and structured output. Teams use Claude for coding agents, document analysis, customer-facing assistants and operational automation.
When it is the right choice
- You need careful reasoning over long documents or codebases
- You are building agents that call tools and work through multi-step tasks
- You want to buy through your existing AWS or Google Cloud account
- Not ideal when data must stay on hardware you own; choose a self-hosted model there
How we use it
- Build infrastructure and operations agents on Claude with narrow, audited tool permissions
- Reach Claude through Bedrock or Vertex AI to keep billing and access control in your cloud account
- Trace prompts, tool calls and token usage end to end and alert on cost or error spikes
- Run regression evaluations before moving to a new model version
Where it fits in our work
Related articles
From Idea to AI Feature in Six WeeksHow an AI project runs end to end in six weeks: discovery, design, prototype, infrastructure, rollout, then measuring and improving.
CI/CD for Models and PromptsEvaluation gates, model registries, canary releases and rollback: applying CI/CD discipline to prompts and models in LLM applications.
Fine-Tuning or Prompting? A Decision Guide for Small TeamsWhen prompting, RAG or fine-tuning is the right way to adapt a language model, and what each one costs a small engineering team.Claude: frequently asked
Can we use Claude through our AWS account?
Yes. Claude is available on Amazon Bedrock, so access, billing and regional settings go through AWS. It is also on Google Cloud Vertex AI.
Is Claude a good fit for agents that change infrastructure?
It is well suited to tool use, but any agent that changes real systems needs tight permissions, human approval for risky actions and a full audit trail. We design those controls first.
Running Claude, or deciding whether to? Tell us what you have; the first consultation is free.
Let's talk »

