Convert meeting minutes written in natural language into data structures (Mermaid ERD), build a standard project terminology dictionary, and master key information for the entire collaborative design pipeline preserving decision-making and impact analysis of design changes.
Errors in understanding between planning, design, and development at the project site directly lead to database omission and loss of consistency. Find out why ensuring consistency at the design stage is important.
When looking at the same service screen plan, the data model and relationship settings that planners, designers, and developers associate with each other are misaligned, ultimately leading to omissions or data inconsistencies (runtime errors).
When naming variables using different names for the same entity, such as 'Member, Customer, User, Member', unnecessary translation and communication rework costs are greatly incurred.
By modifying the DB schema and not updating the API or screen plan in line with the rapidly increasing service policy, system inconsistencies snowball and cause system paralysis.
Unlike ChatGPT, which is limited to a single conversation context, we compare the characteristics of Codex Client, which recognizes the entire folder structure and dependency relationships between multiple files.
| Compare items | ChatGPT (General Conversational AI) | Codex Client (Workspace-based AI) |
|---|---|---|
| Context awareness | Only locally understand the contents of a single file/text pasted by the user | Intelligently recognizes multiple dependencies of DDL schema, plan, and API specifications within a folder at the same time |
| Terminology standardization | Remaining at the level of a one-off English work, it is impossible to maintain consistency in variable names throughout the entire project. | Self-recommendation of consistent standard naming and DB column names based on project standard terminology dictionary |
| Scope of Impact Analysis | Level of suggestions for fragmentary schema errors or hypothetical table modifications | Reverse inference on list of API specifications and screen modification areas according to subtle changes in schema (e.g. column addition) |
A list of the final products the learner produces during the Day 6 session and the purpose of those products.
Entities and relationships are extracted and rendered from the natural language plan. Mermaid ERD scripts and statements (Output: erd-schema.md)
Fragmented Korean/English planning terms defined in standard English column format Project Standards Glossary (Output: project-glossary.md)
API and screen modification list according to addition of reservation approval system (WAIT_APPROVE) Change impact analysis report (Output: change-impact-report.md)
Archives the reasons for normalization and data design decisions and rejected alternatives. Design Decision Log (DDL) (Output: design-decision-log.md)
Contains DB improvement measures for concurrent payment errors, referential integrity loss of withdrawal, and transaction rollback. Edge Case Analysis Report (Output: edge-case-analysis.md)
This is a mapping between the input values used in the practice stage and the results generated through Codex Workspace inference.
Enter meeting scenario lines to derive precise normalization relationships (1:N, 1:1) and Mermaid codes.
Please analyze the provided meeting minutes from a data structure perspective to derive key entities and relationships, and write a data structure definition and Mermaid ERD code.
We build a master dictionary of domain terms by comparing and analyzing the gap between Figma planning terms and DB development specifications.
Please analyze terms such as 'Member/User/Customer/Member' and 'Counselor/Expert/Teacher/Counselor' that are used interchangeably throughout the project and create a dictionary of standard project terms in the form of a Markdown table.
Understand the scope of API and table impact when a release plan change adds an 'Approval' step to the scheduling process.
Please fill out the API specifications, DB schema, screens, and change sharing reports that are affected as the reservation confirmation process has been changed to 'Awaiting Approval' status and 'Payment after expert approval'.
Log rejection reasons and agreements regarding normalization decisions, physical separation decisions for reservation history, etc.
Please extract normalization and database structure design decisions from the meeting and create a Design Decision Log that includes decision items, background reasons, alternatives reviewed, approvers, and possible future changes.
We audit system vulnerabilities to prevent referential integrity violations (withdrawals) and transaction collapses.
Please derive edge case exception scenarios for data consistency violations that may occur in the currently defined User, Expert, Reservation, and Payment table structures and suggest improvement measures.
Beyond simple text matching, it identifies the referential integrity (FK) relationships and transaction life cycle of entities and automatically deduces natural language proposals into Data Definition Language (DDL) queries and state machine rules.
We derive a master dictionary of enterprise terms by semantically clustering differently written terms (customer name vs. nickname), and synchronize the consistency of the data dictionary based on this.
We check how the data and analysis information derived from each step goes through the technical design loop to maximize quality.
This five-step collaboration loop blocks exceptions from the planning and design stage, providing an absolute advantage in gaining productivity and eliminating human errors for developers who begin actual coding work.
This is a list of topics that are great for discussion during training or to use as interview questions.
“What are the performance shortcomings of selecting Soft Delete (logical deletion) instead of Hard Delete when processing membership withdrawal, and what is the index/DB partitioning strategy that can compensate for this?”
“When a project progresses to the halfway point without creating a terminology standardization dictionary, how does the ‘terminology debt’ cost incurred within the development team affect the actual schedule?”
This is a diagram of the overall practice tasks and missions covered on Day 6.
| Task | topic | How to use AI |
|---|---|---|
| Task 01 | Addressing gaps in understanding data structures | Convert meeting content into data structures and organize entities and relationships |
| Task 02 | Terminology standardization | Create a standard terminology dictionary by analyzing terms throughout the project |
| Task 03 | Share the impact of change | Analyze the impact of design changes and track related documents and functions |
| Mission 01 | Design decision history | Create a decision log to manage design basis and change history |
| Mission 02 | Excavating Exception Scenarios | Analyze missing edge cases and derive risk factors and improvement plans |