Skip to content
View danielgaskins's full-sized avatar

Block or report danielgaskins

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
danielgaskins/README.md

Daniel Gaskins

I build applied AI systems that have to survive messy documents, misleading tests, and real business rules.

Current work

SyncABill

An invoice workflow that uses Gemini to extract structured data, applies review rules chosen by the account controller, and sends approved bills to QuickBooks Online or Xero. I completed Google's CASA Tier 2 security assessment and brought the product to SOC 2 readiness.

Read the case study

Mendmark

A mutation-testing tool for agent evals. It plants controlled failures in passing traces, reruns the same evaluators, and shows teams which broken tool calls, repeated side effects, hidden errors, and damaged responses their tests miss.

View Mendmark · Read the field note

lgbm-to-code

A Python package that turns trained, one-output LightGBM models into dependency-free Python, C++17, or JavaScript. The test suite executes or compiles every target and compares its raw scores with LightGBM at 1e-12 tolerances.

View lgbm-to-code · View on PyPI

How I work

I start with the failure that would make a clean result misleading. Then I build the data, tests, workflow, and recovery path around it.

Portfolio · LinkedIn · Email

Pinned Loading

  1. mendmark mendmark Public

    Mutation testing for agent evals. Find the tool-use failures your tests miss before they reach production.

    Python 1

  2. lgbm-to-code lgbm-to-code Public

    Generate dependency-free Python, C++17, and JavaScript inference from trained LightGBM models, with executed cross-runtime parity tests.

    Python

  3. danielgaskins.github.io danielgaskins.github.io Public

    Applied AI portfolio covering SyncABill, Mendmark, computer vision, and production ML systems.

    HTML

  4. minc-ssl minc-ssl Public

    Implementation of MINC: Non-Contrastive Mutual Information for Self-Surpervised Leanring(SSL) in PyTorch

    Python 2