GAIP Climate Risk Insurance RAG Engine with LlamaIndex & Cognition Devin
Insurers must dynamically underwrite regional climate risks based on technical policies and historical flood data. Construct an advanced RAG parametric underwriting pipeline using LlamaIndex and Cognition Devin automation to generate validated climate policy decisions.
What you are building
The core problem, expected build, and operating context for this challenge.
Build a climate insurance policy underwriting index with LlamaIndex and automated engineering with Cognition Devin.
How work is evaluated
Evaluates policy decision accuracy and document retrieval correctness.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
citation_present
Checks if clause citation exists
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
retrieval_accuracy
Correct policy clause retrieval rate • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Implement hierarchical RAG indexing using LlamaIndex
Automate code refinement using Cognition Devin environment execution
Extract structured underwriting recommendations from climate policy documents
Reference links and supporting material
Synthetic policy guidelines and flood historical records for Southeast Asia.
How this agent runs
Evaluates policy decision accuracy and document retrieval correctness.
Challenge input
JSON query containing location and flood millimeter level
LlamaIndex
Document parsing and vector search
Cognition Devin
Automated pipeline engineering
Evaluated output
JSON containing payout_approved, payout_amount, citation
- Checks if clause citation exists
- Correct policy clause retrieval rate • target: 0.95 • range: 0-1
- Benchmark: ClimateRAG-Bench
- Retrieval Accuracy target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
View technical recipe
Configured tools
- Llama Index · Required
- Cognition Devin · Optional
- Exa · Optional
- Cognition Devin · Optional
- Cognition Devin · Optional
Evaluation contract
- citation_present · Weight 1
- retrieval_accuracy · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.