Skip to content

[pull] master from Snowflake-Labs:master#615

Merged
pull[bot] merged 26 commits intosymopsio:masterfrom
Snowflake-Labs:master
Mar 13, 2026
Merged

[pull] master from Snowflake-Labs:master#615
pull[bot] merged 26 commits intosymopsio:masterfrom
Snowflake-Labs:master

Conversation

@pull
Copy link

@pull pull bot commented Mar 13, 2026

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

sfc-gh-jreini and others added 26 commits February 24, 2026 10:22
- Remove Private Preview banner and Tool Execution Accuracy references
- Add programmatic evaluation API (EXECUTE_AI_EVALUATION) as primary path
- Add custom metrics via YAML config section (groundedness, execution efficiency)
- Update agent improvement flow to use ALTER AGENT SQL
- Keep Snowsight UI instructions inline as secondary option
- Update schema references (AGENTS -> AGENTS_DEV) and column names (EXPECTED_TOOLS -> GROUND_TRUTH_DATA)
- Update documentation links for GA

Co-authored-by: Cursor <cursoragent@cursor.com>
… access control

- Expand prompt template variables table with all 12 supported variables
  (input, output, ground_truth, tool_info, span_id, span_type, llm_model, etc.)
- Update role configuration: remove User Impersonation, add warehouse USAGE
  and stage READ requirements
- Add Model Availability section (claude-4-sonnet / claude-3-5-sonnet with
  cross-region inference requirements)
- Add programmatic result retrieval: GET_AI_EVALUATION_DATA,
  GET_AI_RECORD_TRACE, GET_AI_OBSERVABILITY_LOGS
- Update YAML example to show ground_truth and input template variables

Co-authored-by: Cursor <cursoragent@cursor.com>
… access control

- Expand prompt template variables table with all 12 supported variables
  (input, output, ground_truth, tool_info, span_id, span_type, llm_model, etc.)
- Note that full execution trace is always available to LLM judge regardless
  of which template variables are used
- Update role configuration: remove User Impersonation, add warehouse USAGE
  and stage READ requirements
- Add Model Availability section (claude-4-sonnet / claude-3-5-sonnet with
  cross-region inference requirements)
- Add programmatic result retrieval: GET_AI_EVALUATION_DATA,
  GET_AI_RECORD_TRACE, GET_AI_OBSERVABILITY_LOGS
- Update YAML example to show ground_truth and input template variables

Co-authored-by: Cursor <cursoragent@cursor.com>
Two-tab Streamlit in Snowflake dashboard for monitoring Cortex REST API token budgets:
- Tab 1: Claude Code skill with usage reports and /pdf export
- Tab 2: Cortex Code skill with budget enforcement, burn rate, and rolling alerts

Uses get_active_session() pattern for Streamlit in Snowflake deployment.

.... Generated with [Cortex Code](https://docs.snowflake.com/en/user-guide/cortex-code/cortex-code)

Co-Authored-By: Cortex Code <noreply@snowflake.com>
…with-vision-models

Ajain ml batch inference with vision models
Add Cortex REST API Budget Monitor quickstart guide
Update Cortex Agent Evaluations quickstart for GA
fix fork_repo_link metadata parsing for golden-batch guide
@pull pull bot locked and limited conversation to collaborators Mar 13, 2026
@pull pull bot added the ⤵️ pull label Mar 13, 2026
@pull pull bot merged commit 7e94af6 into symopsio:master Mar 13, 2026
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants