Research
Inside χ-Bench’s healthcare workflows
A benchmark for complete healthcare workflows across providers and health plans.
Read the storyResearch, engineering, and ideas from Actava.ai.
Research
A benchmark for complete healthcare workflows across providers and health plans.
Read the storyResearch
How evaluation failures guide training data for a healthcare foundation model.
Read the storyProduct
How verified workflow experience supports training and checkpoint selection.
Read the story16 articles
ProductRelease notes
October updates add an organization-wide stop control, configured model fallback, workflow review gates, scheduling, and batch operations.
Product2 min read
How authorized workflow traces become training tasks, and how held-out evaluation and checkpoint comparison guide model selection.
ProductRelease notes
An expanded workflow library covers enrollment, authorization, claims, quoting, installation, appeals, and renewals.
ProductRelease notes
A control-status view connects framework assessments with run history, evaluations, policies, acknowledgments, and uploaded evidence.
ProductRelease notes
This release adds an organization API for managing agents through their lifecycle and introduces configured answer checks.
ProductRelease notes
Agent batches, recorded data access, model-selection limits, and skill review extend the platform’s execution and administration tools.
ProductRelease notes
Reusable agent workflows cover recruiting, onboarding, learning, compensation, workforce planning, and offboarding.
ProductRelease notes
Agent workflows for prospect research, outreach, account scoring, pipeline analysis, competitive intelligence, and sales enablement.
ProductRelease notes
A healthcare foundation model fine-tuned from Kimi-K2.6 through recursive self-improvement, with evaluations spanning clinical reasoning and interactive agent tasks.
Bring one workflow your team still runs by hand. We'll show you the agent that runs it.
Research, engineering, and ideas from Actava.ai.
Research
A benchmark for complete healthcare workflows across providers and health plans.
Read the storyResearch
How evaluation failures guide training data for a healthcare foundation model.
Read the storyProduct
How verified workflow experience supports training and checkpoint selection.
Read the story16 articles
ProductRelease notes
October updates add an organization-wide stop control, configured model fallback, workflow review gates, scheduling, and batch operations.
Product2 min read
How authorized workflow traces become training tasks, and how held-out evaluation and checkpoint comparison guide model selection.
ProductRelease notes
An expanded workflow library covers enrollment, authorization, claims, quoting, installation, appeals, and renewals.
ProductRelease notes
A control-status view connects framework assessments with run history, evaluations, policies, acknowledgments, and uploaded evidence.
ProductRelease notes
This release adds an organization API for managing agents through their lifecycle and introduces configured answer checks.
ProductRelease notes
Agent batches, recorded data access, model-selection limits, and skill review extend the platform’s execution and administration tools.
ProductRelease notes
Reusable agent workflows cover recruiting, onboarding, learning, compensation, workforce planning, and offboarding.
ProductRelease notes
Agent workflows for prospect research, outreach, account scoring, pipeline analysis, competitive intelligence, and sales enablement.
ProductRelease notes
A healthcare foundation model fine-tuned from Kimi-K2.6 through recursive self-improvement, with evaluations spanning clinical reasoning and interactive agent tasks.