Chinh (lelouvincx) lelouvincx

Note

• https://spiess.dev/blog/how-i-use-claude-code

  • One inline prompt to directly get the result: claude -p "your question".
    • Can create alias to auto-generated git commit message like: claude -p "Look at the staged git changes and create a summarizing git commit title following conventional commits. Only respond with the title and no affirmation.".
  • When I see something go wrong, press Escape immediately and edit the prompt.
  • Hidden command: /terminal-setup.
  • Can paste an image directly by copy paste.
  • Press escape twice and edit the previous prompt.

• Done

  • DONE Write review for Hieu and Dong

• DONE Find out how Zoho billing calculates 315 active customers

Note

• Tagging system:

  • Check lai trong code search còn track không.
  • Track at tenant-wise only.
  • Chia priority of tracked metrics.

• Supervisor Agent: Orchestrates workflow and escalates edge cases.

• Specialized Sub-agents: Sourcing, screening, engagement, compliance.

• Human-in-the-Loop Triggers: Strategic intervention points for quality control.

• Focus on augmenting human recruiters by automating top-of-funnel screening while ensuring viable candidates reach human review.

• Done

  • DONE Check SQL queries generated from the AI

• DONE Coi màn hình mua cho Linh

Note

• https://lucumr.pocoo.org/2025/7/3/tools/

  • Before thinking of automating some task with software/AI, ensure that the task works correctly as scale.

• Goals (the tests should be):

  • P1 Cover enough capabilities of our Explore Data AI.
    • From this, we have a sense of:
      • What are advantages.
      • What are disadvantages.
      • What are capabilities that our AI can outperform competitors'.

• Done

  • DONE Tagging system event tracking

• DONE Review PR for Hieu

• DONE Handle the schedule issue

• Done

  • DONE Push first 5 tests

• DONE Review the compiled SQL to see if any errors

• Note

  • Building an eval, which includes a dataset and a choice of evaluation methods.
  • Goal:
    • Structure a process of building evals for Holistics AI.
    • Should be composable with:
      • Multiple datasets.
      • Multiple evaluation methods.
      • Multiple system prompts.
      • Multiple LLMs.

• Done

  • DONE Check for anh Tien

Done

• DONE Review Tram’s doc and make clear understanding with her

• DONE percent_rank for hometime

• DONE Tính tiền dạy python

• Note

  • https://www.john-rush.com/posts/ai-20250701.html
    • Fix inputs, not outputs.
  • Investigate problems:
    • Mismatch in number of customers.
    • Discrepancy in MRR.
  • Problems with current Zoho pipeline:
    • Internal tenants: Vincent Woon + Holistics + Vincent Test + Holistics1 + Test Staging 2 + Holistics Software + Holistics (Vincent) + Holistics - Test - SGD + US Holistics Test + Huy Vu EU Test.
    • Using static exchange rate (e.g exchange rate from SGD to USD is 1.4 while actually 1.27) => more tax.
    • Exchange rate of some invoices EURO -> SGD is 1.25, while the global config is 1.4.

• Done

  • DONE Finalize the test suite approach

• Note

  • Goal creating the benchmark:
    • Build trust - show the transparency of AI accuracy.
    • Have a sense of capacity (?).
    • Use this to informally evaluate Holistics AI vs. other tools.
  • https://www.sigmacomputing.com/blog/text-to-sql-data-chat
  • Current common benchmarks like Spider or BIRD is benchmarking for text-to-SQL problem, not the business-question-to-insight problem.
  • Idea: sync common AMQL questions from Zendesk.

• Done

  • DONE Finalize the test suite approach

• Read Holistics’s AI Philosophy.

• Research common/standard GenBI benchmarking methods.

Note

• Hôm nay Linh mắng mình, như mọi lần. Đều là về mình. Cách ứng xử, lối sống, phân chia thời gian, và quan trọng nhất là cách nói năng. Mình nghĩ sẽ tốt hơn nếu viết ra đây để mình phải nhớ tới nó mà sửa. Vì lần này đã là lặp lại của rất nhiều lần trước rồi. Mình chưa biết phải nói rõ ràng là sửa cái gì, nhưng mình cũng có hình dung mang máng. Sẽ quay lại update sau.

Done

• DONE Fix and review progressed PRs

• DONE Update progress in squad AI