orgoca

What an agent can do with the CompileML corpus

orgoca/CompileML: Compile tree-ensemble models into deterministic, auditable decision artifacts: score, calibrated PD, risk bands, and adverse-action reason

• Look up how CompileML implements cobol, credit-risk, credit-scoring, with answers cited to file and line.
• Reuse a worked example: the commit “Refuse missing values instead of compiling a model the artifact canno…” (6 files · Python).
• Answer from CompileML's real Python source instead of memory (AI, prompts and agents).

• How does CompileML implement cobol?
• What does tests do in CompileML?

Search the GitHub repository orgoca/CompileML with XERJ (https://hub.xerj.org/corpus/orgoca--compileml).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/orgoca/CompileML CompileML && git -C CompileML checkout 9eda1f9500f9261268fdaea5d3aa90d69204efd3
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./CompileML --url http://127.0.0.1:9200 --prefix compileml --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: Apache-2.0. Keep the copyright notice and credit the authors.

corpus orgoca--compileml · AI, prompts and agents
Related corpora: cognita, adalflow, AmaLS367/InferWeave, Aarivg/soccer-transfer-valuation
AI search and retrieval with XERJ · Case study: reference coding for agents