Reference · built on requestOperator by FibricCustomer support

Coaching Notes

Reads quality scores and sampled conversations per agent. Proposes coaching notes and a one-to-one agenda for the team lead.

Request accessPricing ↗

About

Evaluations get filled in. One-to-ones happen. The gap between them is a team lead re-reading a week of scores the night before. Coaching Notes reads the completed evaluations for each agent, pulls the conversations they were scored on, and adds the analytics the contact center already computed: sentiment by turn, interruptions, talk speed. From that it drafts a note per agent that names the contacts, what the scores show, and the one or two behaviors to work on.

It also drafts the one-to-one agenda, with the contacts to replay in order and a slot that falls inside both people's rostered hours. The team lead edits and approves. The agent sees nothing until then.

This is a reference listing. It documents what Fibric would read from Coaching Notes and what it could propose, based on the vendor's published interfaces. Fibric builds it under a managed deployment when you request it; selecting it here installs nothing.

Inputs

  • Completed contact evaluations in Amazon Connect, stored in the Content evaluations bucket you configure, with the form and each contact's scores
  • Reviews exported from Zendesk QA through /qa/api/export/reviews: score, reviewer, reviewee, category ratings with weight and the critical flag, and the comment
  • Sampled conversations in Kustomer per agent, with the sentiment score Kustomer assigns to each message on create
  • Conversational analytics for sampled calls in Amazon Connect: OverallSentiment per participant, Interruptions, NonTalkTime, and TalkSpeed
  • Call evaluations, summaries, and transcripts from Aircall Conversation Intelligence for the agent's calls
  • Published shifts in Deputy or When I Work, so the one-to-one lands in a rostered hour for both people

Proposed actions

  • Target capability: propose a coaching note per agent, as a draft for the team lead, citing the sampled contacts and the scores behind each point
  • Target capability: propose a one-to-one agenda with the contacts to replay, ordered by score and critical category, and a slot inside both rosters
  • Target capability: propose a tag on each cited conversation so the agent can open the examples the note refers to
  • Target capability: propose the next period's sample for that agent, so the lead can see whether the behavior changed

Proposed actions are target capabilities. Every action runs propose-first and needs a validated deployment and the appropriate permissions.

What you can build

  • Turn a week of evaluations into a note

    The lead completed evaluations for each agent's contacts in Amazon Connect. The operator drafts each note from those forms and the call analytics, then proposes a one-to-one slot that Deputy shows both people rostered for.

    With Amazon Connect, Deputy

  • Bring Zendesk QA scores into the one-to-one

    Reviews with a critical category failed are pulled from the Zendesk QA export. The operator lists the tickets, the reviewer's comment, and the category, and drafts the agenda item around them.

    With Zendesk

  • Show the calls behind a sentiment dip

    An agent's Kustomer conversations averaged lower sentiment this week. The operator finds the Aircall calls and transcripts from the same days and proposes them as the replay list, with the summary beside each.

    With Kustomer, Aircall

Requirements

  • A quality source: Amazon Connect contact evaluations or Zendesk QA reviews
  • A support or contact center connector holding the conversations: Kustomer, Zendesk, Amazon Connect, or Aircall
  • A scheduling connector so the one-to-one can be placed inside rostered hours: Deputy or When I Work
  • Evaluation forms or scorecards your team already uses. The operator adds none
Authentication
Runs on the credentials of the quality, support, contact center, and scheduling connectors you attach. It holds no key of its own and sends nothing to an agent.

Limits

  • Zendesk QA's export leaves out voice transcripts, AutoQA data, and dashboard data. Notes cite only what the export carries
  • Amazon Connect scores sentiment per turn from -5 to +5, from frequency and streaks. The operator reports the score; it does not grade the agent
  • Notes go to the team lead only. Nothing is written to an HR record, and the agent is not messaged
  • A sample is a sample. When fewer contacts were evaluated than the floor the lead set, the note says so instead of generalizing

Access and pricing

Reference listing. Fibric builds the operator under a managed deployment when you request it. Your quote covers the build, capabilities, usage, and support.

Request Coaching Notes ↗

Questions and answers

What does the team lead approve?
The note and the agenda for each agent. The lead edits wording, removes a contact, or changes the slot. Approval saves the note where the lead keeps coaching records and books the slot. Until then the draft is visible to the lead alone.
What record does a one-to-one leave?
The approved note, the agenda, the list of contacts cited with their evaluation ids, the tag on each cited conversation, and who approved and when. The next period's sample is recorded so the follow-up compares like with like.
Does the agent see anything before the lead does?
No. Drafts are addressed to the team lead. The agent sees the note only when the lead shares it, and the tag on a conversation is the only thing written to a shared system, after approval.
Ask about Coaching Notes

Ask about the capabilities and requirements in this listing.

For project-specific requirements, contact Fibric.

This operator is developed, published, and supported by Fibric. Third-party names and logos identify the systems an integration connects to; they are the property of their respective owners, who are not affiliated with Fibric and do not sponsor or endorse this listing. Trademark policy