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 storyVideos
117 videos
VideosWatch video
ACTAVA | Agentic Workforce | Agents That People Actually Adopt
A working agent usually dies of neglect, not error. The pattern repeats: no one asks the team what they hate, the agent sits outside the tools where the work happens, or the win never shows up where anyone can see it. Fix those three, and adoption follows.
Watch ↗
VideosWatch video
ACTAVA | Release | CHRYSO v8 (September 2026)
ACTAVA now tracks AI compliance where the AI runs. CHRYSO, shown in the platform as Compliance, measures an organization against frameworks such as the NIST AI Risk Management Framework and HIPAA technical safeguards, and recalculates every control from what is happening on the platform: live agents, their evaluations and run history, approved policies, signed acknowledgments, completed training, and uploaded evidence. Organization administrators get a single page showing how many controls are satisfied, what is blocking the rest, and who needs to act. Members and citizen developers get a short task list of policies to sign and training to complete. For healthcare payers, providers, and life-science teams, the result is an audit-ready posture that stays current without a separate compliance spreadsheet.
Watch ↗
VideosWatch video
ACTAVA | Agentic Workforce | Agents That Someone Is On Call For
Unattended agents need an operating model, not just a dashboard: a failure signal, a runbook that says retry, disable, or escalate, and an off switch anyone can reach. Before you widen autonomy, name the person who gets woken up at three in the morning.
Watch ↗
VideosWatch video
ACTAVA | Agentic Workforce | Agents You Shouldn't Build
Some work doesn't need an agent. Deterministic rules want an if-statement, structured inputs want a query, and unreviewable mistakes want a person. This short piece makes the case that knowing where agents don't belong is what earns trust for the ones you do build.
Watch ↗
VideosWatch video
ACTAVA | Agentic Workforce | Agent Workspace Chaining
Accountability goes missing in handoffs between agents. ACTAVA KORA Agent Workspaces keeps state with the run and hands authority to the next Agent Card, so tools, models, verification policies, and approvals get reset at every transition. Approval comes before irreversible actions, and failed checks block release.
Watch ↗
VideosWatch video
ACTAVA | Agentic Workforce | Agents That Start With One Boring Workflow
Ambitious first agents collapse under their own scope. This one argues for the opposite: pick a frequent, rules-based job with a clear input, output, owner, and exception path, run it alongside the manual process, and widen autonomy only after you've seen where it fails.
Watch ↗
VideosWatch video
ACTAVA | Release | KORA v8 (September 2026)
V7 settled who's accountable for the agents. V8 settles who gets to build with them. Here's what shipped, what's still in beta, and what needs configuration before you roll it out. V8 ships 82 items, and one thread runs through all of them: other teams can now build on the platform. A partner can create, version, run, schedule, benchmark, and export an agent with an organization API key, without opening the dashboard. A team can require checks before an answer goes out. A downstream system can receive results in a schema it declared up front. ACTAVA released v8 with 82 product improvements, all around one idea: openness. Partners can work directly in shared delivery surfaces, teams can trace and check the evidence behind an answer, and workflows can run from intake through completion without hiding the handoffs in between.
Watch ↗
VideosWatch video
ACTAVA | Agentic Workforce | Agents Measured Against the Manual Baseline
Most agent pilots get graded against nothing. This video argues for the harder comparison: the same cases, the full manual loop including review time, the real error profile, and metrics defined before anyone sees the result.
Watch ↗
VideosWatch video
ACTAVA | Agentic Workforce | Agents That Match How the Work Already Runs
Procedure documents describe a workflow nobody actually runs. This one argues for watching the real work first: the undocumented checks, the exception rate, and the handoffs where responsibility changes hands. Those gaps are where delays and lost context live, and they're what an agent should be built around.
Watch ↗
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.