Automated GTM Funnel Metrics & Revenue Alignment Auditor for Fintech SaaS
Aligning product usage metrics with Go-To-Market (GTM) strategy is critical for B2B fintech SaaS providers scale sales pipelines without increasing churn. Misalignment between customer acquisition cost (CAC), net revenue retention (NRR), and platform API consumption leads to mispriced enterprise contracts. In this challenge, you will implement a GTM alignment auditor using LangChain. The agent will analyze product telemetry alongside customer billing records to detect pricing leakage, underutilized contract tiers, and churn risk indicators.
What you are building
The core problem, expected build, and operating context for this challenge.
Build a LangChain agent to analyze B2B fintech SaaS revenue metrics and identify GTM misalignment.
How work is evaluated
Evaluates calculation accuracy for SaaS metrics and alignment recommendations.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
nrr_calculation_exact
Verifies NRR calculation matches formula exactly
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
math_precision_error
Mean absolute percentage error on numerical metric estimations • target: 0 • range: 0-100
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Construct a LangChain agent with custom python analytical tools
Ingest customer API usage records and SaaS subscription terms
Calculate key metrics including NRR, LTV/CAC ratio, and usage-tier delta
Generate automated executive recommendations for pricing alignment
Reference links and supporting material
Synthetic B2B SaaS cohort telemetry data including monthly API call volumes and subscription billings.
Challenge setup
Evaluates calculation accuracy for SaaS metrics and alignment recommendations.
Challenge input
JSON containing customer cohorts, ARR start, expansions, and contractions
LangChain
Standard Python framework for language model agents and tool orchestration.
Evaluated output
JSON containing calculated_nrr_percentage, churn_risk_count, and strategy_recommendation
- Verifies NRR calculation matches formula exactly
- Mean absolute percentage error on numerical metric estimations • target: 0 • range: 0-100
- Benchmark: FinSaaS-Analytics-Bench
- Math Precision Error target: 0
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- Langchain · Required
- LangChain · Optional
- Langchain · Required
- LangChain · Optional
Evaluation contract
- nrr_calculation_exact · Weight 1
- math_precision_error · Weight 1
Metrics
- math_precision_error · Target 0
Benchmarks
- FinSaaS-Analytics-Bench
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing customer cohorts, ARR start, expansions, and contractions
Output: JSON containing calculated_nrr_percentage, churn_risk_count, and strategy_recommendation
Execution harness: Python
Evaluation tools
- LangChain · Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.