Chord AI Context

chord ai is in beta! for more information about chord ai please reach out to your account manager introduction chord ai’s context helps you capture and manage verified insights in the form of instructions and sql pairs instructions offer two levels of guidance global instructions , which apply to all queries (e g , applying business rules like filtering out canceled orders, enforcing rounding conventions or naming standards across the board), and question‑matching instructions , which apply only when a question matches a defined pattern (e g , how to calculate “late delivery rate” based on specific date logic) together, these ensure more precise, standardized sql generation aligned with your organization’s metrics and logic additionally, sql pairs allow you to map natural language questions—like “what is our average customer lifetime value?”—to pre‑verified sql queries, so that when similar questions are asked in the future, chord ai can generate accurate and consistent results using those saved queries question types that are best served by sql pairs include complex business or computation logic that requires precise sql formulation frequently asked business questions with established calculation methods custom kpis and metrics specific to your brand combined, instructions and sql pairs give chord ai the ability to answer domain specific questions with high consistency and accuracy—capturing organizational knowledge, reducing sql errors, and improving trust in ai generated outputs read on for additional information about these features within chord context instructions the instructions feature in chord context lets your team embed business logic and formatting rules directly into how the system generates sql queries and answers by using instructions, organizations can standardize how metrics are calculated, ensure consistent sql structure, and provide data context in a way that aligns closely with internal definitions it helps chord copilot produce accurate, reliable, and predictable answers by capturing domain specific business rules and metrics logic in advance there are two types of instructions that organizations can customize global instructions and question matching instructions global instructions you can set global instructions that apply to all questions—perfect for enforcing naming conventions, consistent rounding, data filters (e g excluding canceled orders), and join behaviors to add a global instruction navigate to the context navigation link click the "add instruction" button select "global" under "apply instruction to" enter your instruction details in the text field click "submit" to save and apply the instruction question matching instructions you can also define question matching instructions , which only apply when user queries match specific patterns or topics—such as calculating “late delivery rate” using your exact definition to add a question matching instruction navigate to the context navigation link click on the instructions tab click the "add instruction" button select "matched to specific questions" under "apply instruction to" enter your instruction details in the text field add questions that should trigger the instruction click "submit" to save and apply the instruction sql pairs chord ai's sql pairs capability allows you to capture and map natural‑language questions to their exact sql queries, building a trusted knowledge base of verified answers whenever a team member asks a similar question—such as "what is our average order value?"—chord ai can pull the saved sql and respond with the exact computation each time, ensuring consistency across the organization to set up a sql pair , you can manually add a sql pair to chord context if you know certain questions that your team will ask in advance to manually add a sql pair navigate to the context navigation link click on the question sql pairs tab click the "add question sql pair" button add a question and the corresponding sql statement that answers the quesiton click "create" to create and save the sql pair once a sql pair is created, you can view, edit, or delete a specific sql pair at any time