Ethan

Ethan

Building Zvena | Free work tools

About

I'm building Zvena: a free workspace connecting docs, tasks, designs, tables, calendar and mail. The goal is to spend less time copying updates between tools and more time doing the work. We're also researching how language models, action selection and checked memory can work together in Sapphire. This is ongoing research toward more capable AI. Interested in talking with freelancers, small teams and people building reliable AI systems.

Badges

Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

•

5d ago

Zvena: free docs, tasks and design for client projects

A client brief in one app, tasks in another, designs somewhere else then the same status update typed in every place.

I'm building Zvena to keep that work connected. A task inside a brief is the same task you see in Projects: change its status once and the page follows. Docs, Projects, Design, Tables, Calendar and Mail share one workspace.

For a first try, open the example studio, mark a task done and see what changes. No account needed: https://zvena.app/try

You can also import Notion pages and databases, Linear projects and issues, or Figma files. Start with one project before moving everything.

•

5d ago

what is your rule of thumb for letting ai agents run git commands directly?

giving an agent terminal access to stage and commit changes speeds up prototyping, but it comes with weird surprises. Yesterday an agent staged temporary log files and untracked config edits into a feature branch commit without mentioning it in the summary.

do you give your agent full shell execution rights, or do you strictly lock down git operations to manual user approval?

At what point during a long coding session do you notice your AI agent starting to hallucinate?

when starting a fresh thread, answers are crisp and precise. but after an hour of tweaking UI components back and forth, the agent starts referencing variables we deleted ten prompts ago.

I spent thirty minutes debugging an error only to realize the agent was silently modifying an outdated file copy it remembered from earlier in the session context.

how do you manage context drift do you hard-reset your agent chat regularly or prune system prompts?

View more