# Claude Certified Engineers > A software studio staffed by engineers certified through Anthropic's Claude Certification Program. We ship production Claude agents, MCP integrations, and eval harnesses. Fixed fee, your IP. ## Site - [Home](https://claudecertified.agency/): Studio overview, certifications, services, and pricing. - [Blog](https://claudecertified.agency/blog): Notes on production Claude systems. - [Services](https://claudecertified.agency/#services): Audit, production agent build, MCP integration, eval harness, enablement, embedded engineer. - [Pricing](https://claudecertified.agency/#pricing): Fixed-fee engagements. ## Production agents - [Guardrails and prompt injection for tool-using Claude agents](https://claudecertified.agency/blog/guardrails-prompt-injection-claude-agents): A tool-using Claude agent without guardrails will be helpful in the wrong direction. Here is the refusal, injection, and review path we install before live traffic. - [Prompt caching and token budgets in production Claude](https://claudecertified.agency/blog/prompt-caching-token-budgets-production): Prompt caching cuts Claude spend when the stable prefix is actually stable. Here is how we set cache breakpoints, ceilings, and evals so cost is a number, not a surprise. - [LLM-as-judge rubrics you can defend in CI](https://claudecertified.agency/blog/llm-as-judge-rubrics-in-ci): LLM-as-judge is fine when the rubric is boring, structured, and checked by a human. Here is how we score Claude agents without turning CI into a $12 hobby. - [Put an eval harness on Claude before the agent goes live](https://claudecertified.agency/blog/eval-harness-for-claude-agents): Most Claude pilots stall because nobody can tell if quality got better. Here is the eval harness we install in week one, wired into CI, before the agent sees real traffic. - [Golden datasets for Claude agents](https://claudecertified.agency/blog/golden-datasets-for-claude-agents): A golden dataset for Claude is a named, versioned set of real cases with invariants, not a folder of happy-path chats. Here is how we build one that CI can fail. ## MCP and tools - [Connecting Claude to Salesforce or SAP without a catch-all tool](https://claudecertified.agency/blog/claude-salesforce-sap-mcp): "We connected Claude to Salesforce" usually means one mega-tool and a security exception. Here is how we ship named MCP verbs that survive a CRM of record. - [Human-in-the-loop queues for irreversible MCP actions](https://claudecertified.agency/blog/human-in-the-loop-mcp-review-queues): If Claude can refund, post, or export, it needs a review queue, not a braver system prompt. Here is how we design human checkpoints that agents actually wait on. - [Claude tool use vs MCP: when each is the right contract](https://claudecertified.agency/blog/claude-tool-use-vs-mcp): Tool use on the Messages API and MCP servers are not the same design. Here is how we choose which contract Claude should use for a given job. - [MCP server security review that clears InfoSec](https://claudecertified.agency/blog/mcp-server-security-review): An MCP server is a permissioned adapter, not a chatbot plugin. Here is the security review we run before Claude gets hands on Salesforce, SAP, or your internal APIs. - [Tool schemas Claude actually calls](https://claudecertified.agency/blog/mcp-tool-schemas-claude-calls): Claude skips, mis-fills, or over-calls tools when the schema is written for OpenAPI completeness instead of for a model. Here is how we design MCP tools that get used correctly. ## Claude Code - [Claude Code enterprise rollout checklist: permissions, policy, and auditability](https://claudecertified.agency/blog/claude-code-enterprise-rollout-checklist): A staged Claude Code enterprise rollout checklist covering managed policy, tool permissions, MCP, gateways, auditability, evals, cost controls, and adoption. - [CI eval gates for Claude Code changes](https://claudecertified.agency/blog/ci-eval-gates-claude-code): If Claude Code can edit prompts and tools, CI must be able to fail those edits. Here is how we gate agentic coding the same way we gate application code. - [Certification enablement vs hiring another Claude engineer](https://claudecertified.agency/blog/certification-enablement-vs-hiring): Enablement trains your team on your repo. Hiring adds a headcount. Here is how we choose, and why the exams are the syllabus rather than trivia. - [CLAUDE.md that the team actually follows](https://claudecertified.agency/blog/claude-md-that-teams-follow): CLAUDE.md is repo policy for Claude Code, not a novel. Here is what we put in it so agentic coding stays inside your conventions after we leave. - [Repo conventions that keep Claude Code inside your architecture](https://claudecertified.agency/blog/agentic-coding-repo-conventions): Agentic coding fails when the repo has no rules the agent can follow. Here is the convention set we install so Claude Code PRs look like your team's, not like a weekend plugin. - [First PR in seven days with Claude Code in an existing repo](https://claudecertified.agency/blog/first-pr-claude-code-existing-repo): A certified engineer opens a pull request inside seven days because the repo is ready, not because the model is magic. Here is the week-one path we use in live codebases. ## Hiring certified engineers - [Six weeks to a production Claude agent](https://claudecertified.agency/blog/six-weeks-to-production-claude): Prototype by week two, live traffic by week six. Here is the path we run on a Production Agent Build, and what has to be true on day zero or the calendar is fiction. - [IP ownership when a vendor builds your Claude agent](https://claudecertified.agency/blog/ip-ownership-claude-vendor): If the prompts, evals, and MCP servers do not live in your git from day one, you are renting a demo. Here is the IP rule we sign before week one, and what to reject in a vendor contract. - [Architect vs Developer staffing on a Claude engagement](https://claudecertified.agency/blog/architect-vs-developer-staffing): Developer-certified engineers build the tools and agents. Architect-certified engineers decide what must not be built. Here is how we staff both so you do not get a clever system nobody can govern. - [Audit vs Build vs Embedded: which Claude engagement to buy](https://claudecertified.agency/blog/audit-vs-build-vs-embedded): A two-week audit, a six-week production build, and a quarterly embed solve different problems. Here is how we choose so you do not buy a rebuild when you needed a diagnosis. - [Why Claude certification is a hiring filter, not a badge](https://claudecertified.agency/blog/why-claude-certification-hiring-filter): Most failed Claude projects fail for the same four reasons. Anthropic's exams exist because those reasons are learnable. Here is how we hire and staff against them. ## Optional - [RSS](https://claudecertified.agency/blog/rss.xml): Full post index as RSS 2.0. - [Sitemap](https://claudecertified.agency/sitemap.xml): Canonical URL list for crawlers.