Skip to content
Paula Livingstone writing · projects · tools

Projects

The Frontier Engineer Project

Anthropic is investing $100 million to train 10,000 Frontier Deployed Engineers. This project asks whether an experienced industrial cybersecurity engineer can independently build the same underlying capabilities through targeted study, hands-on engineering and the delivery of a real agentic AI system.

ClaudeClaude CodePythonMCPRAGLLM AgentsLLMOpsCoursera

The Frontier Engineer Project › 03 — Tools & Retrieval

Building LLM Applications with Tools and Retrieval — Edureka

Learning how an LLM can work with external tools and retrieve evidence from controlled information sources rather than relying solely on model knowledge and prompt context.

Why this is in the programme

A useful enterprise system cannot depend upon the model already knowing the answer. It must be able to obtain relevant information from authoritative sources and preserve enough of that relationship for its output to be examined.

Course

Building LLM Applications with Tools and Retrieval — Edureka

The course covers tool calling, APIs, structured data, retrieval-augmented generation, embeddings, vector databases, chunking and retrieval techniques.

Role in the experiment

This stage addresses one of the central questions of the project: how a model can reason from evidence without losing the provenance that makes its conclusions defensible.

The eventual engineering work will examine not only whether relevant information can be retrieved, but whether the system can distinguish source evidence from its own inference.