 oleg
|
d33c282b95
|
feat(core): Unify output schema mock generation and verify AI Assistant workflows with any trigger type (#33896)
|
2026-07-14 15:27:08 +00:00 |
|
|
Michael Drury
|
5e6be990f0
|
chore(ai-builder): Remove 056_ai_builder_template_examples experiment (no-changelog) (#31763)
|
2026-06-08 10:04:06 +00:00 |
|
|
EugeneandClaude Opus 4.6
|
00014420b1
|
refactor(core): Remove multi-agent architecture entry point from AI workflow builder (no-changelog) (#27925)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-02 16:32:19 +00:00 |
|
|
EugeneandClaude Sonnet 4.6
|
6294b0e56f
|
feat(ai-builder): Add agent text response evaluation and workflow changes binary check (no-changelog) (#27755)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-03-31 07:49:10 +00:00 |
|
|
|
6314cd4842
|
feat(ai-builder): Support dataset context and conversation history in evaluations (no-changelog) (#27618)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
|
2026-03-30 08:14:01 +00:00 |
|
|
oleg
|
834966e145
|
feat(ai-builder): Add binary-checks evaluation suite (no-changelog) (#26415)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2026-03-04 08:42:05 +00:00 |
|
|
Benjamin Schroth
|
ce32754088
|
feat(ai-builder): Add subgraph evaluation framework for responder (no-changelog) (#25419)
|
2026-02-18 12:33:34 +00:00 |
|
|
Benjamin Schroth
|
e4ac345eda
|
feat(ai-builder): Implement workflow execution in evaluations (no-changelog) (#25814)
|
2026-02-18 08:41:56 +00:00 |
|
|
Eugene
|
892f086579
|
feat(core): Add introspection diagnostic tool for AI workflow builder (#25172)
|
2026-02-12 10:57:44 +00:00 |
|
|
Mutasem AldmourandClaude Opus 4.5
|
9729c2a5da
|
feat(ai-builder): Add code-base workflow builder (#24535)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
2026-02-10 12:24:27 +00:00 |
|
|
Michael DruryandClaude Opus 4.5
|
832e580b39
|
chore(ai-builder): Add CSV output for evaluation results (#25193)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
2026-02-04 09:02:14 +00:00 |
|
|
olegandcubic-dev-ai[bot]
|
24bb638982
|
refactor(ai-builder): Consolidate AI Workflow Builder agents and simplify prompts (no-changelog) (#25020)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
|
2026-02-02 13:57:48 +00:00 |
|
|
Albert Alisesandcubic-dev-ai[bot]
|
341976947f
|
feat(ai-builder): Add webhook notifications with HMAC authentication for AI evaluation results (#24766)
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
|
2026-01-26 10:16:05 +00:00 |
|
|
Albert Alises
|
09222733e1
|
feat(ai-builder): Add webhook notifications for AI evaluation results (#24653)
|
2026-01-23 09:39:04 +00:00 |
|
|
Albert Alises
|
99cb5982a0
|
ci(core): Add automated AI workflow builder evaluations (#24582)
|
2026-01-21 15:30:45 +00:00 |
|
|
oleg
|
448522142c
|
feat(ai-builder): Add per-stage model configuration for evaluations (no-changelog) (#24344)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2026-01-15 12:58:49 +00:00 |
|
|
oleg
|
734bed4f84
|
fix(ai-builder): Remove pairwise multi-gen evals and improve logs (no-changelog) (#24270)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2026-01-14 08:44:09 +00:00 |
|
|
olegandcubic-dev-ai[bot]
|
f880a74d99
|
refactor(ai-builder): Implement unified evaluations harness (#23955)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
|
2026-01-13 12:11:13 +00:00 |
|
|
oleg
|
3504b982b5
|
chore(ai-builder): Remove legacy agent and make multi-agent default (no-changelog) (#24076)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2026-01-13 10:24:27 +00:00 |
|
|
oleg
|
be6d68408d
|
refactor(ai-builder): Improve pairwise evaluation architecture and LangSmith integration (no-changelog) (#23084)
|
2025-12-15 12:11:25 +01:00 |
|
|
Michael Drury
|
33a6aa665c
|
fix(ai-builder): Allow setting evaluation feature flags via environment variables (no-changelog) (#22813)
|
2025-12-05 13:37:56 +00:00 |
|
|
Eugene
|
2b53cc0f5c
|
feat(ai-builder): CSV input for evals (no-changelog) (#21150)
|
2025-10-24 14:15:36 +02:00 |
|
|
oleg
|
cf3b0f5b5a
|
refactor(ai-builder): Refactor prompt caching evals (#20911)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2025-10-24 09:34:43 +02:00 |
|
|
Eugene
|
49aa80fac1
|
feat: Add programmatic evaluations for workflow builder (no-changelog) (#20214)
|
2025-10-02 16:40:30 +02:00 |
|
|
Mutasem Aldmour
|
2ba544284f
|
fix: Update builder to better work with loops and binary data (no-changelog) (#19040)
|
2025-09-02 11:41:26 +02:00 |
|
|
oleg
|
fb3a2ae216
|
feat: Evaluation framework for AI Workflow Builder (#18016)
|
2025-08-20 11:11:14 +02:00 |
|