In the agentic era I got an idea on how to create portfolios, run interviews and apply to job positions in an agentic environment. The goal is to have a pretty objective portfolio where I list my competences and I ask a bot to judge its content.

The knowledge base is organized into these kind of documents:

• blog posts the collection of all articles written in this context: 100+ files
• source codes the code written all over my career: 3k3+
• images the images used for reports: 1k5
• resume the list of my experiences
• portfolio projects the project descriptions (roles, functions, scope)
• skills the list of skills
• personal profile a brief description on the personal profile

I created a library to interact with local models and file system model_local.py which is loaded by graph rag. The model is deployed using mcp server on docker.

The system is integrated within emacs and there is no need to exit the program. LLMs help to write the python code which is executed in-line in a separate buffer.

• kit created after mcphost
• opencode
• ellama
• gptel
• aider
• aideremacs

blogD = c_t.dir2tree(os.environ['HOME'] + '/lav/siti/spiega/markdown/')
llm = c_t.get_llm_mcp(model_id=model_id)
blogD = c_t.summarize_text(llm,blogD)
blogD.to_csv(baseDir + "graph/blog_desc_" + modelN + ".csv",index=False)

and a function to create graphs graph_rag.py