Skip to content
View gaddyh's full-sized avatar

Block or report gaddyh

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

Pinned Loading

  1. agent_feature_template_repo agent_feature_template_repo Public template

    A reusable template for building AI agents slowly and systematically: define the goal, map capabilities, design each feature in Markdown, implement in small steps, and evaluate behavior before conn…

    Python

  2. localize localize Public

    Don't just measure that your agent failed — localize why. A self-validating eval harness for tool-using agents, with per-layer failure attribution and an LLM-as-judge.

    Python

  3. tami_one tami_one Public

    WhatsApp-native commitment extraction for mortgage advisors: ingests real WhatsApp threads, detects who owes what by when, and evaluates extraction quality with DSPy, generated devsets, and rich fa…

    Python

  4. trajectory-analysis trajectory-analysis Public

    Trajectory analysis framework for agent evaluation — moving beyond reward scores to behavioral explanation.

    Python

  5. ai-software-delivery-pipeline ai-software-delivery-pipeline Public

    A small AI software-delivery lab: code generation, automated tests, task-level evaluation, and failure localization in one repeatable loop.

    Python

  6. cognitive-tool-agent cognitive-tool-agent Public

    Failure Driven Decomposing

    Python