Skip to main content
Changelog

Changelog, July 9, 2026

Elnora carries your saved details, your own skills and your named protocol templates into each new conversation. Three specialist agents share the work, cell line shortlists are assembled from measured evidence, and a saved style profile shapes the reports, decks and figures it produces.

AgentProtocolsNew

Personal memory and named protocol templates

Elnora now carries your saved details, your own skills and your named protocol templates into each new conversation. Name a template and the next experiment is drafted to that structure, which means a group's house format holds from one protocol to the next.

AgentNew

Cell line shortlists built from measured evidence

Cell line shortlists are now assembled from measured evidence, with each candidate carrying the record it was drawn from and its gene entry in Ensembl. The reasoning behind a choice is visible before a plate is seeded and reads well in a methods section.

AgentWorkspaceNew

Style profiles for reports, decks and figures

A saved style profile now shapes the reports, slide decks and figures Elnora generates, setting colours, type, spacing and logos once for the group. A draft made for an internal review is already presentable when it reaches a collaborator or a funder.

AgentWorkspaceNew

Figure extraction from papers and scientific rendering

You can now name a numbered figure in an uploaded paper and have it lifted into the write-up, and Elnora renders its own molecular views, secondary structures and plots beside it. Published data and new results end up compared on one page.

AgentNew

Delegation to researcher, analyst and critic agents

Three specialists share the work: a researcher handles literature synthesis, a data analyst takes results, and a critic reviews the design, ranking each point it raises and proposing a concrete fix. Weak controls surface while the design can still be changed.

AgentWorkspaceImproved

Source lists carrying literature identifiers

Every answer closes with a source list naming the specialists Elnora consulted and the literature identifier behind each claim. A reader can follow a single statement back to the paper it rests on before that line goes into a manuscript.

New

  • You can author your own skills and subagents, and connect your own tool servers to them
  • A hypothesis-generation skill proposes candidate explanations and ranks them by the evidence behind each
  • Plate maps render as a viewer in the conversation, alongside document previews and generated pages

Improved

  • Each subagent runs on a model chosen for its job, so heavy reading work does not pay for the largest model
  • The activity panel names each step in plain language rather than raw tool names
  • Subagent steps stay out of the activity panel, which shows the work of the run you asked for
  • The skill index is grouped by domain, so a relevant skill surfaces on the first look
  • A run that stalls is bounded and reports what it reached rather than running on without output
  • Papers cited from memory are added to the verified resource list for the task
  • The preview panel follows the agent to the newest version of a file as it edits, and closes when you want the space
  • Search usage is metered per run and billed as it is used

Misc

  • Charts render without a network round trip for the plotting library