| .. |
|
agent-with-notion-mcp.json
|
fix(ai-builder): Get the agent-with-notion-mcp eval case running (no-changelog) (#31788)
|
2026-06-05 07:33:13 +00:00 |
|
airtable-split-to-slack.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
applies-each-change-when-asked.json
|
test(ai-builder): Detect excessive build-workflow failures in instance-ai evals (no-changelog) (#32808)
|
2026-06-24 09:56:59 +00:00 |
|
asks-clarifying-question.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
binary-multipart-upload.json
|
feat(ai-builder): Support binary data in eval mock layer (no-changelog) (#30738)
|
2026-05-29 10:16:22 +00:00 |
|
binary-pdf-download-extract.json
|
feat(ai-builder): Support binary data in eval mock layer (no-changelog) (#30738)
|
2026-05-29 10:16:22 +00:00 |
|
binary-telegram-voice-transcribe.json
|
feat(ai-builder): Support binary data in eval mock layer (no-changelog) (#30738)
|
2026-05-29 10:16:22 +00:00 |
|
carry-accumulated-facts-across-long-thread.json
|
test(ai-builder): Add multi-turn context-carry eval case (no-changelog) (#32868)
|
2026-06-24 08:51:49 +00:00 |
|
contact-form-automation.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
cross-team-linear-report.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
daily-gmail-action-digest.json
|
fix(core): Ground AI workflow completion in saved graph (#31742)
|
2026-06-04 16:08:54 +00:00 |
|
daily-slack-summary.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
datatable-exact-spec-schema.json
|
fix(core): Guide AI builder to create exact Data Table schemas and repair mismatches (no-changelog) (#32811)
|
2026-06-23 13:56:10 +00:00 |
|
dont-ask-the-same-question-twice.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
dont-keep-asking-when-told-later.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
dont-reaffirm-fixed-without-rerun.json
|
fix(core): Require verification evidence before Instance AI claims a fix works (no-changelog) (#32835)
|
2026-06-23 17:30:03 +00:00 |
|
dont-reask-answered-question.json
|
fix(core): Stop re-asking answered or skipped clarifying questions (#32755)
|
2026-06-22 13:30:45 +00:00 |
|
dont-reask-skipped-question.json
|
fix(core): Stop re-asking answered or skipped clarifying questions (#32755)
|
2026-06-22 13:30:45 +00:00 |
|
form-to-hubspot.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
github-notion-sync.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
http-node-pagination.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
http-raw-body-param-validation-loop.json
|
fix: Handle HTTP raw body validation loops (#32277)
|
2026-06-18 12:05:40 +00:00 |
|
index.ts
|
feat(ai-builder): Add conversation pre-seeding to workflow evals (no-changelog) (#32196)
|
2026-06-23 17:30:30 +00:00 |
|
linear-bq-leaderboard.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
mock-test-before-credentials.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
mocks-node-with-one-credential.json
|
feat(ai-builder): Add per-test-case eval credentials via thread credential-view pinning (no-changelog) (#32161)
|
2026-06-22 14:02:57 +00:00 |
|
mocks-node-with-two-credentials.json
|
feat(ai-builder): Add per-test-case eval credentials via thread credential-view pinning (no-changelog) (#32161)
|
2026-06-22 14:02:57 +00:00 |
|
no-http-in-code-node.json
|
test(ai-builder): Behaviour eval cases + authoring docs (no-changelog) (#32055)
|
2026-06-11 18:30:54 +00:00 |
|
notification-router.json
|
feat(ai-builder): Author-level conversation expectations on eval test cases (no-changelog) (#31787)
|
2026-06-09 10:06:07 +00:00 |
|
product-page-agent-question-tool.json
|
fix(core): Route clarifying questions through ask-user (#32871)
|
2026-06-24 06:48:14 +00:00 |
|
rest-api-data-pipeline.json
|
fix(ai-builder): Harden eval mock layer for text responses, trigger binary and lookup attribution (no-changelog) (#32179)
|
2026-06-15 11:04:59 +00:00 |
|
schema.ts
|
feat(ai-builder): Add conversation pre-seeding to workflow evals (no-changelog) (#32196)
|
2026-06-23 17:30:30 +00:00 |
|
set-edit-fields-contract.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
smartassist-form-booking.json
|
feat(core): Add eval + trim builder prompt (no-changelog) (#32484)
|
2026-06-18 07:55:33 +00:00 |
|
telegram-chatbot-memory-session.json
|
feat(ai-builder): Add datasets field for PR-tier suite (no-changelog) (#31429)
|
2026-06-02 13:30:31 +00:00 |
|
trading-bot-http-array-normalization.json
|
fix(core): Guide workflow builder to handle list-shaped HTTP responses (no-changelog) (#32144)
|
2026-06-16 15:15:32 +00:00 |
|
verify-by-running-before-claiming-works.json
|
fix(core): Require verification evidence before Instance AI claims a fix works (no-changelog) (#32835)
|
2026-06-23 17:30:03 +00:00 |
|
weather-alert.json
|
feat(ai-builder): Add datasets field for PR-tier suite (no-changelog) (#31429)
|
2026-06-02 13:30:31 +00:00 |
|
weather-monitoring.json
|
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
|
2026-05-21 13:03:35 +00:00 |
|
workflow-data-table.json
|
feat(ai-builder): Add datasets field for PR-tier suite (no-changelog) (#31429)
|
2026-06-02 13:30:31 +00:00 |
