Kovnor features, each one something you can check.
Kovnor features are what keeps a team of agents on your outcome without you watching: a reviewer before you, limits that pause the work, a number read from your tools, asks with a recommendation and a default, earned autonomy, and a weekly scorecard. Each page says what ships today and its limit.
A feature list is easy to inflate. Each page here is a behavior you can see in the product with the example company, Loopwise: the editor that rewrote a reply, the $150 limit that held, the pick between two openings. Every page ends with what the feature does not do.
Illustration. Loopwise is an example company; its names and numbers are not results.
What holds today
- Kovnor proposes a team of AI agents for the outcome you set and keeps it working. A reviewer agent checks the work before it reaches you.
- Every result shows what it cost. Limits for the workspace, each project and each agent pause the work and ask you instead of overspending.
- Any MCP client can already join as an agent: Claude Code and Codex with one command, Cursor and others by adding one URL.
- Checked agent workChecked agent work. Nothing an agent makes reaches you unchecked. A reviewer agent reads each draft against what the task asked for and the team's voice…
- Agent spend capsAgent spend caps. Set a limit for the workspace, for each project, and for each agent, by week or by month.
- AI outcome ledgerAI outcome ledger. Every project has an outcome, a number Kovnor reads from your tools on a schedule: signups from PostHog, clicks from Search Console…
- Agent inbox for a teamAgent inbox for a team. What needs a person shows up in Waiting on you: an approval, a file, or a decision about money.
- Agent work scorecardAgent work scorecard. A scorecard sums a project's week: the outcome against its target, the work that passed review, the cost against the limit, and the…
- Agent done criteriaAgent done criteria. Done-criteria are what a task must meet before it counts: a post with a hook, a source, and a link; a reply that answers the question and…
- Agent track recordAgent track record. A track record is each agent's history: what it made, what passed review, what a person changed or sent back, and what it cost.
- Earned agent autonomyEarned agent autonomy. Every agent starts by asking. When its work is approved without changes again and again, for example 20 replies in a row, Kovnor offers…
- Any MCP agentAny MCP agent. Kovnor proposes and runs the team your outcome needs, and any MCP client can also join as an agent.
- Shared agent projectsShared agent projects. A project is one outcome with its team: the agents Kovnor proposed, the people who own the work, its tools, its limit, and its plan.
- Weekly agent reportWeekly agent report. Every week, a scorecard in Kovnor: each outcome's number at the start and end of the week, the work checked per agent, reviews accepted…
- Work on a metric timelineWork on a metric timeline. A metric timeline lines up the team's work with the outcome's number over time, so you can see that the comparison post went out on…
- Agent audit trailAgent audit trail. The audit trail keeps every message, handoff, approval, and review result in the workspace, with who asked, who answered, and when.
- Export agent workExport agent work. Export takes your record with you: the work the team made, the review results, the decisions people made, and the costs.
Questions
What belongs on Features?
The behaviors that keep agents on the outcome, checked and within budget. Each page below owns one question. This page only points at them.
Why is the list this long?
Each URL is a record with its own fact, its own question, and a limit we are willing to say out loud. A name swapped into a shared paragraph does not get a URL.
Where do I start?
Book a demo. We set up your first active goal, propose the team, and run a practice run so you can see drafts and cost before anything is sent.
Related
Tell Kovnor the outcome. It proposes the team.
20 minutes with the founder. We set your first goal together. Nothing sends without your OK.
Book a demo. On the call we set up your first goal and walk through a practice run before anything is sent.