metabase/metabase
Mar 2026 – Jul 2026
5 Months active
Languages Used
ClojureSelmerJSONMarkdown
Technical Skills
AI integrationClojureSQLfull stack developmentAPI developmentbackend development
Mihael Konjević
PROFILE
Mihael Konjević
Worked on the metabase/metabase repository to deliver advanced AI-driven automation and data discovery features, focusing on Metabot’s evolution from an external Python service to a native Clojure agent. Leveraged Clojure and SQL to build robust prompt systems, context enrichment pipelines, and dynamic query tooling, enabling low-latency, in-process LLM interactions and safer, more reliable query construction. Enhanced backend architecture with structured MBQL processing, unified resource navigation, and on-demand skills for task-specific guidance. Addressed critical bugs in query construction and foreign key resolution, while improving test coverage, observability, and integration with Slack-GitHub notifications to streamline analytics workflows and developer experience.
Overall Statistics
Feature vs Bugs
71%Features
Repository Contributions
16Total
Bugs
4
Commits
16
Features
10
Lines of code
54,324
Activity Months5
Work History
July 2026
2 Commits • 1 Features
Jul 1, 2026July 2026 monthly summary for metabase/metabase: Delivered targeted improvements to data-source discovery and query construction guidance, and fixed a date-related SQL reliability issue. These efforts enhanced user guidance, reduced ambiguity in data sourcing, and prevented SQL errors during date computations, contributing to faster insight generation and more trustworthy analytics across data workflows.
2 Commits • 1 Features
Jul 1, 2026July 2026 monthly summary for metabase/metabase: Delivered targeted improvements to data-source discovery and query construction guidance, and fixed a date-related SQL reliability issue. These efforts enhanced user guidance, reduced ambiguity in data sourcing, and prevented SQL errors during date computations, contributing to faster insight generation and more trustworthy analytics across data workflows.
July 2026
June 2026
5 Commits • 2 Features
Jun 1, 2026June 2026 monthly summary for metabase/metabase: Delivered significant Metabot-related enhancements that improve automation reliability, task-specific guidance, and prompt efficiency, along with critical fixes and cross-system improvements. Key features delivered: - Metabot Enhancements: on-demand skills system enabling dynamic task-specific instructions; SQL guardrail skills configured as always-on for robust query safety; per-profile skill inlining to keep prompts lean; improved termination and load behavior to minimize unnecessary tool calls. - Slack-GitHub Integration: added Slack ID mapping for user '@retro' to ensure notifications reach the correct recipient. Major bugs fixed: - Metabot Construct-Query fixes: resolved trailing options in string-filter handling, clarified distinct aggregations guidance, and improved explicit-join behavior with comprehensive tests. - Portable Foreign Key resolution reliability: fixed ambiguity when identical table names exist across schemas by querying the database directly to bypass metadata provider when needed. Overall impact and accomplishments: - Increased automation reliability and speed for Metabot-driven tasks, reduced erroneous tool calls, and improved query construction accuracy. - Improved operator visibility and notification routing through Slack-GitHub integration. Technologies/skills demonstrated: - Prompt engineering and LLM-driven agent design (on-demand vs always-on skills, per-profile manifests, terminal-tools model termination). - Advanced SQL tooling and guardrails integration, catalog-management, and profile-based capability partitioning. - Database metadata handling and cross-system integration (Slack/GitHub notifications). Business value: - Faster, more reliable data-query automation with better governance and incident response, reducing manual intervention and accelerating data insights.
June 2026
5 Commits • 2 Features
Jun 1, 2026June 2026 monthly summary for metabase/metabase: Delivered significant Metabot-related enhancements that improve automation reliability, task-specific guidance, and prompt efficiency, along with critical fixes and cross-system improvements. Key features delivered: - Metabot Enhancements: on-demand skills system enabling dynamic task-specific instructions; SQL guardrail skills configured as always-on for robust query safety; per-profile skill inlining to keep prompts lean; improved termination and load behavior to minimize unnecessary tool calls. - Slack-GitHub Integration: added Slack ID mapping for user '@retro' to ensure notifications reach the correct recipient. Major bugs fixed: - Metabot Construct-Query fixes: resolved trailing options in string-filter handling, clarified distinct aggregations guidance, and improved explicit-join behavior with comprehensive tests. - Portable Foreign Key resolution reliability: fixed ambiguity when identical table names exist across schemas by querying the database directly to bypass metadata provider when needed. Overall impact and accomplishments: - Increased automation reliability and speed for Metabot-driven tasks, reduced erroneous tool calls, and improved query construction accuracy. - Improved operator visibility and notification routing through Slack-GitHub integration. Technologies/skills demonstrated: - Prompt engineering and LLM-driven agent design (on-demand vs always-on skills, per-profile manifests, terminal-tools model termination). - Advanced SQL tooling and guardrails integration, catalog-management, and profile-based capability partitioning. - Database metadata handling and cross-system integration (Slack/GitHub notifications). Business value: - Faster, more reliable data-query automation with better governance and incident response, reducing manual intervention and accelerating data insights.
May 2026
6 Commits • 4 Features
May 1, 2026May 2026 performance summary for metabase/metabase: Delivered high-impact features across Metabot NLQ enhancements, unified resource navigation, and data-discovery ranking, while fixing critical query construction robustness issues. The month focused on improving user-facing experience, reliability, and scalability of data discovery and query composition, with strong emphasis on business value and maintainable architecture. Key outcomes include improved NLQ prompt handling, safer and more discoverable resource navigation, refined search ranking for curated content, streamlined SQL/profile prompts, and robust fixes to MBQL clause handling.
6 Commits • 4 Features
May 1, 2026May 2026 performance summary for metabase/metabase: Delivered high-impact features across Metabot NLQ enhancements, unified resource navigation, and data-discovery ranking, while fixing critical query construction robustness issues. The month focused on improving user-facing experience, reliability, and scalability of data discovery and query composition, with strong emphasis on business value and maintainable architecture. Key outcomes include improved NLQ prompt handling, safer and more discoverable resource navigation, refined search ranking for curated content, streamlined SQL/profile prompts, and robust fixes to MBQL clause handling.
May 2026
April 2026
2 Commits • 2 Features
Apr 1, 2026April 2026 (2026-04) monthly summary for Metabot work: Key features delivered: - NLQ Metabot profile alignment and testing: aligned embedding profile with NLQ profile (same system prompt and tool set), removed obsolete test, and added a new test to verify alignment, ensuring consistent NLQ/metabot user-facing behavior. - Structured MBQL processing with agent-lib: introduced a full agent-lib module for structured MBQL program repair, validation, and evaluation; provides idempotent normalization, schema validation, and safe evaluation; replaces old query construction with a unified program format and enhances querying capabilities. Major bugs fixed: - Fixed evaluation context and time-interval keyword coercion; aligned source type mappings and IDs to enable correct evaluation; addressed test failures and updated to the new program schema. - Stabilized tests and build tooling: fixed tests, addressed Eastwood warnings, updated cljfmt indentation, and refined prompt guidance to reflect new tool schema and field IDs. Overall impact and accomplishments: - Significantly improved NLQ/metabot consistency and user experience, reducing edge-case behavior and support needs. - Enabled richer, safer MBQL queries via agent-lib, improving reliability, maintainability, and future extensibility of Metabase’s AI-assisted querying. - API and tooling improvements (v2 endpoints, MCP-friendly schemas) open path for broader client adoption and automation with fewer integration issues. Technologies/skills demonstrated: - Clojure, CLJ tooling (clj-kondo, Eastwood), and codebase modernization - MBQL domain knowledge and agent-lib architecture (repair, validate, eval, runtime) - Sandboxed evaluation, runtime scoping optimizations, and schema evolution - API design, tool prompts engineering, and test-driven development
April 2026
2 Commits • 2 Features
Apr 1, 2026April 2026 (2026-04) monthly summary for Metabot work: Key features delivered: - NLQ Metabot profile alignment and testing: aligned embedding profile with NLQ profile (same system prompt and tool set), removed obsolete test, and added a new test to verify alignment, ensuring consistent NLQ/metabot user-facing behavior. - Structured MBQL processing with agent-lib: introduced a full agent-lib module for structured MBQL program repair, validation, and evaluation; provides idempotent normalization, schema validation, and safe evaluation; replaces old query construction with a unified program format and enhances querying capabilities. Major bugs fixed: - Fixed evaluation context and time-interval keyword coercion; aligned source type mappings and IDs to enable correct evaluation; addressed test failures and updated to the new program schema. - Stabilized tests and build tooling: fixed tests, addressed Eastwood warnings, updated cljfmt indentation, and refined prompt guidance to reflect new tool schema and field IDs. Overall impact and accomplishments: - Significantly improved NLQ/metabot consistency and user experience, reducing edge-case behavior and support needs. - Enabled richer, safer MBQL queries via agent-lib, improving reliability, maintainability, and future extensibility of Metabase’s AI-assisted querying. - API and tooling improvements (v2 endpoints, MCP-friendly schemas) open path for broader client adoption and automation with fewer integration issues. Technologies/skills demonstrated: - Clojure, CLJ tooling (clj-kondo, Eastwood), and codebase modernization - MBQL domain knowledge and agent-lib architecture (repair, validate, eval, runtime) - Sandboxed evaluation, runtime scoping optimizations, and schema evolution - API design, tool prompts engineering, and test-driven development
March 2026
1 Commits • 1 Features
Mar 1, 2026March 2026 monthly summary for metabase/metabase: Delivered MetaBot v3 as an in-process native Clojure agent, replacing the external Python AI service with a production-ready, low-latency in-process implementation. Introduced a robust prompt system, context enrichment, and SQL query tooling, enabling faster, more reliable LLM interactions within a single JVM and direct Toucan2 access. Implemented feature-flag controlled rollout (use-native-agent) for gradual validation and minimized risk. Expanded capabilities with 13 wrapped tools and a comprehensive memory/state pipeline to support richer conversations and tool orchestration. Phase-based progress across prompts/context (Phase 2A), SQL tooling (Phase 2B), resource/link tooling (Phase 2C), chart tooling and profiles (2F), plus read_resource tool integration for resource discovery. Achieved high-quality test coverage (210 assertions across 15 tests; all passing) and improved observability via Prometheus metrics and Snowplow events. Business value includes lower latency, reduced HTTP round-trips, improved data access via Toucan2, and safer, structured SQL edits and query operations. The deliverables position MetaBot for scalable, enterprise-grade AI automation with richer analytics workflows.
1 Commits • 1 Features
Mar 1, 2026March 2026 monthly summary for metabase/metabase: Delivered MetaBot v3 as an in-process native Clojure agent, replacing the external Python AI service with a production-ready, low-latency in-process implementation. Introduced a robust prompt system, context enrichment, and SQL query tooling, enabling faster, more reliable LLM interactions within a single JVM and direct Toucan2 access. Implemented feature-flag controlled rollout (use-native-agent) for gradual validation and minimized risk. Expanded capabilities with 13 wrapped tools and a comprehensive memory/state pipeline to support richer conversations and tool orchestration. Phase-based progress across prompts/context (Phase 2A), SQL tooling (Phase 2B), resource/link tooling (Phase 2C), chart tooling and profiles (2F), plus read_resource tool integration for resource discovery. Achieved high-quality test coverage (210 assertions across 15 tests; all passing) and improved observability via Prometheus metrics and Snowplow events. Business value includes lower latency, reduced HTTP round-trips, improved data access via Toucan2, and safer, structured SQL edits and query operations. The deliverables position MetaBot for scalable, enterprise-grade AI automation with richer analytics workflows.
March 2026
Activity
Loading activity data...
Quality Metrics
Correctness93.8%
Maintainability82.6%
Architecture91.2%
Performance82.6%
AI Usage55.0%
Skills & Technologies
Programming Languages
ClojureJSONMarkdownSelmer
Technical Skills
AI IntegrationAI integrationAPI developmentAPI integrationClojureClojure developmentSQLSoftware Developmentback end developmentbackend developmentdata aggregationdata analysisdata processingdata visualizationdatabase management
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline