Research
Inside χ-Bench’s healthcare workflows
A benchmark for complete healthcare workflows across providers and health plans.
Read the storyNews & Blog
Research, engineering, and ideas from Actava.ai.
Research
How Cura 1T learns through evaluation
How evaluation failures guide training data for a healthcare foundation model.
Read the storyProduct
Training specialized models with Model Factory
How verified workflow experience supports training and checkpoint selection.
Read the storyEngineering
5 articles
Engineering2 min read
Scoped handoffs in Agent Workspaces
Shared artifacts carry the work forward while each specialist receives its own tools, knowledge scope, and approval policy at the handoff.
Engineering1 min read
Continuous evaluation for agents in production
From sampled trajectories to versioned rubrics: separate behavior checks, regression signals, and business outcomes.
Engineering1 min read
Measuring agent value with baselines and evidence
Separate projected value from measurable outcomes, and keep cost and attribution assumptions visible.
Engineering1 min read
Reusable skills inside agent workflows
Version reusable procedures independently from the runtime that schedules work and enforces permissions.
Engineering2 min read
Designing an agent harness for healthcare workflows
The runtime decisions behind tool access, durable state, execution budgets, escalation, and evaluation.
See what ACTAVA can do for you
Bring one workflow your team still runs by hand. We'll show you the agent that runs it.