Chinh (lelouvincx) lelouvincx

• Note

  • Options for providing data to AI:
    • Metadata: titles, labels, descriptions, text blocks, data types, model relationships, formulas, chart settings, AMQL codes, git commit messages.
    • Sample data: Few sampled values of the source database columns.
    • Result data: result data (in form of csv or images) of the generated chart.

• Done

  • DONE Fix wrong tests

• Done

  • DONE Fix wrong AQL in tests

• Note

  • https://openai.com/index/introducing-swe-bench-verified/
  • Revise the goals of benchmarking:
    • P1 Internal: Track our AI’s improvement.
    • P1 External: Communicate (firstly with internal Holistics stakeholders: Sales team, Product team; then with prospects & customers).
  • This is divided into many tasks:
    • Creating test cases - I’m working on this.
    • Evaluation method.
    • Evaluation pipeline.
    • Presenting evaluation result.
  • Goal of creating test suite for benchmarking:
    • Make a gold standard for evaluating agents’ ability to work with data-related business problems, rather than generating SQL/AQL snippets (like text-to-sql models do).
    • Have a measurable way to indicate how good our AI is (in aspect of better support analytics techniques - running total, percent of total, trend analysis; reduce lines of code) that correlate with real data analyst productivity.
    • Ease of comparing Holistics’s AI with chatgpt, text-to-SQL models, or competitors (?).
    • Identify capability gaps (where all agents fail).
  • Expected one-line pitch:

    • Our latest AI agent can now successfully handle 95% of common analytical patterns like Period-over-Period comparisons and 85% of complex multi-step Cohort analyses, representing a 20% quarterly improvement in advanced analytical support, according to our benchmark dataset.

Done

• DONE Tìm bằng tốt nghiệp cấp 3

• DONE Test for window functions (50%)

• DONE Fill 10 AQL in existing tests

• DONE Review https://github.com/holistics/dbt/pull/794

• Note

  • eliot-jones.com
    • Beautiful because it’s simple, light, and focus on the content.
    • Love it.
    • Also https://bytemash.net/posts/i-went-down-the-linear-rabbit-hole

Done

• DONE Window funcs (moving calculation) (50%)

• DONE Review PR DAT-232 https://github.com/holistics/prefect/pull/342

• DONE Re-prioritize metrics + tell Hien

Done

• DONE Sửa nốt và đưa cho Nhân, hoàn thiện trong ngày

• DONE Build dataset

• DONE Support superbexperience on a custom waterfall chart

Done

• DONE Data modeling - Tracking Request

  • Re-model to factless table.
  • Fix key conflict by adding new intermediate model dim_as_code_objects.

• DONE Update SQL queries to Postgres dialect

• DONE Reply clark at hometime

Done

• DONE Data modeling - Tracking Request

  • Test all models.
  • Complete PR.

• DONE Update SQL queries to Postgres dialect

• DONE Review PR break down tracking for Hieu

Done

• DONE Build model dim_as_code_objects

• DONE Review running_total issue

• DONE Reply Sasha

• DONE Review Hieu’s event tracking for break down

• DONE Cập nhật địa chỉ mới