Improving agents from the Console dashboard

Improving agents from the Console dashboard

The Dashboard Improve Agents feed is where Console suggests the next useful edit: run an AI recommendation job, open Studio when recommendations are ready, or check an underperforming web flow.

First-traffic recommendation prompt

When a flow first reaches 100+ interactions (all-time) and has no recommendation job yet, Improve Agents shows one card for that agent:

  • Title is the flow’s display name (not a version UUID).
  • Copy: This flow has 100+ interactions. Run an AI recommendation job.
  • Generate starts the same Studio recommendation workflow (force on) for that flow.
  • Skip hides the card in this browser for this company. It does not start a job and does not delete Studio recommendations.

One flow can have several Studio documents (versions or variants). Improve Agents collapses those into a single card so you do not see a list of IDs sharing the same traffic count.

After Generate succeeds, the prompt disappears. When the job finishes, a ready card can appear: N AI recommendation(s) ready with Open Studio. Skip works on those reminder cards too.

You can still generate anytime from Studio’s sparkles panel, including after you skip the dashboard prompt.

Ready recommendations

If recommendations are already ready, Improve Agents links Open Studio so you can Apply or Reject in the recommendations panel. Details: Using Studio Recommendations.

Underperformers

Web flows with enough sessions and a drop in leads vs the previous period can appear as View agent rows. Those are analytics tips, not recommendation jobs — they do not have Skip.

Related

Where AI runs

AI does the work. You review it.

Website chat, card flows, and LinkedIn share one system. AI does each job below. The line under the title says where that job runs.

Every agent

AI crawls the site and writes the offer, the audience, the voice, and the brand. Website chat, card flows, and LinkedIn start from that.

Dashboard · Lead Strategy

Set your lead goal. AI simulates thousands of channel mixes, ranks them by efficiency, and shows the most cost-effective plan. Your data and constraints shape the math.

Every agent · theme on web · list on LinkedIn

AI writes the flow. Theme runs on website chat and cards. Translation runs on every agent. AI finds the prospect list on LinkedIn.

Path on every flow · web and LinkedIn split

Reinforcement learning on the flow path runs on every agent. Recommendations run on web. Right timing and reply reading run on LinkedIn.

Every agent

AI proposes a variant, uses your review on the next draft, and starts from an example that already works. You apply the change.

Stay close to the shift in AI sales

Get product updates and perspective on proactive AI agents, multichannel orchestration, and conversion—without the noise.

Product of the Year Weekly signal on proactive AI sales
Join the newsletter