Salesforce Dictionary - Free Salesforce GlossarySalesforce Dictionary
Full Einstein Reply Recommendations entry
How-to guide

How to roll out Reply Recommendations with a training filter that actually works

The default training filter underperforms on most orgs. The work that matters: specify a tight filter that selects historical conversations representative of what good agent replies look like, then monitor insertion and edit rates to iterate.

By Dipojjal Chakrabarti · Founder & Editor, Salesforce DictionaryLast updated May 18, 2026

The default training filter underperforms on most orgs. The work that matters: specify a tight filter that selects historical conversations representative of what good agent replies look like, then monitor insertion and edit rates to iterate.

  1. Pick the channels for the pilot

    Chat and Messaging are usually the right pilots because reply volume is high and reply length is short enough that suggestions match well. Case Email is a good second wave once the chat models are tuned.

  2. Define a tight training filter

    Resolved within 7 days, CSAT 4 or 5, handled by tenured agents (one year plus tenure or top quartile by CSAT). The default all-resolved filter usually trains on too much noise.

  3. Enable Reply Recommendations and let the model train

    Setup, Einstein Service, Reply Recommendations. Apply the filter. Initial training takes 1 to 4 hours depending on volume.

  4. Add the sidebar component to the agent console for the pilot channels

    Without the component on the page, agents see no suggestions. App Builder edits per channel layout.

  5. Pilot for two weeks and brief agents on insertion modes

    Pick 10 to 20 agents. Brief them on the insert-and-edit pattern. Their reactions in week one tell you whether the suggestions are good enough to keep.

  6. Measure insertion, edit, and send rates

    Insertion above 40 percent, edit around 30 percent, send above 90 percent. Significantly off any of those, tighten the training filter and retrain.

  7. Expand by channel after the metrics stabilize

    Move from Chat to Messaging to Case Email as each channel hits target metrics. Each channel needs its own training filter; do not assume one filter works across channels.

Active channelsremember

Chat, Messaging, Case Email. Pilot one at a time; do not enable all simultaneously.

Training data filterremember

Filter that selects which historical conversations the model learns from. The most consequential setting in the feature.

Insertion moderemember

Insert as-is, insert and edit, insert and review. Most teams settle on insert and edit.

Retraining cadenceremember

Weekly by default; can be triggered after a policy change or a major filter adjustment.

Channel-specific layoutsremember

The sidebar component must be on the agent console layout per channel. Missing it is the most common reason suggestions appear to be off.

Gotchas
  • The default all-resolved training filter usually trains on too much noise. Tighten with CSAT and tenure filters before judging suggestion quality.
  • Insertion rate below 20 percent in the first month is a training data problem, not a model problem. Retrain with a tighter filter rather than disabling the feature.
  • Brand voice in suggestions is inherited from historical agent replies. Filter by agent group if one agent's phrasing should not dominate suggestions for a topic.
  • Per-channel layouts matter. Without the sidebar component on the channel's agent console layout, suggestions exist but no one sees them.
  • Suggestions can include retired phrasings if those patterns are over-represented in training data. Run a policy review pass after major brand voice or legal changes.

See the full Einstein Reply Recommendations entry

Einstein Reply Recommendations includes the definition, worked example, deep dive, related terms, and a quiz.