The @lokahq team post-trained our 26B Trinity Mini into an agentic harness specialized for scientific work.
Working with @PrimeIntellect and @AWS, Loka taught Trinity Mini to execute multi-step research workflows, coordinate tools, query databases, and log an auditable trail at every step.
Here is a look inside the harness. 🧵
Unstructured chat transcripts fail in real scientific work. The harness was built to generate deterministic, structured artifacts instead.
Commands like /plan or /report trigger fixed research workflows. An internal critic agent then steps in to stress-test the model's hypotheses against retrieved evidence.
It handles chemical structures with the same precision.
Researchers can view and analyze 2D molecular properties right inside the interface without jumping between external applications or losing context.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
generative engine optimization — Making a site the source an AI assistant cites when answering, rather than a link in a list of ten blue results.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Evidence that a 26B open model plus verifiable domain RL can drive multi-step research workflows, and a transferable pattern: structured artifacts and a critic AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → instead of free-form chat transcripts.
