Skip to content
Customer Support agent

Conversation review

Your QA scorecard, applied to every call, chat and email your team handles. Team leads get the few worth coaching on, and any critical slip the same day.

  • $12,500 fixed
  • Live in 3 to 6 weeks
  • Yours to keep
Let’s build your agent How it works
The review screen for Conversation review: four items, three done, and one (Missed ID check) waiting for the team lead, who is asked: Account details given before the ID check on call 7731. Review it today?
How it works

If it reached a customer, it’s read against your scorecard.

Here’s a typical run, step by step: what automation handles, what the agent does, and the calls that stay with your team.

The workflow for Conversation review, in 5 steps. It starts with “A conversation closes” and ends with “Scored, or with a lead”. Each step lists what automation, the agent and your team do there.
Conversation reviewA typical run
Starts withA conversation closesA call ends, a chat closes or an email thread is solved, with the transcript saved in your systems.
Automation: Pulls yesterday’s call transcripts, chat logs and solved email threads, with the rep, the queue and the customer on each.
~8h/mo

Step 1 of 5Collect the day’s work

  • Automation

    Pulls yesterday’s call transcripts, chat logs and solved email threads, with the rep, the queue and the customer on each.

    Closed conversations already sit in your phone system and support desk. Fetching them is a date range.

Reads
  • Phone system
  • Support desk
Writes
  • QA tool

~8 hours a month back

The agent: Reads call 7731 against each line: the greeting, the ID check, the fix, the tone and the close, quoting the moment behind each score.
~40h/mo

Step 2 of 5Read it line by line

  • The agent

    Reads call 7731 against each line: the greeting, the ID check, the fix, the tone and the close, quoting the moment behind each score.

    Real care and a scripted sorry can use the same words. The difference shows across the whole exchange.

Reads
  • Phone system
Writes
  • QA tool

~40 hours a month back

Where teams differScorecards run from five lines to thirty, and some weight a few must-do items so one miss fails the call.

Automation: Any conversation that misses a line you marked critical goes to the rep’s team lead the same day, with the moment marked.
IfYour team: Listens to the two minutes where account details came before the ID check, talks it through with the rep, and decides if it goes further.
~6h/mo

Step 3 of 5Raise the critical slips

  • Automation

    Any conversation that misses a line you marked critical goes to the rep’s team lead the same day, with the moment marked.

    Your scorecard marks which lines are critical, so a miss on one goes up without anyone having to decide.

  • Your teamIf a critical item is missed

    Listens to the two minutes where account details came before the ID check, talks it through with the rep, and decides if it goes further.

    A missed ID check can be a slip or a pattern, and it’s about someone on your team. Their lead should own it.

Reads
  • QA tool
Writes
  • QA tool

~6 hours a month back

The agent: Suggests two or three conversations per rep for the week’s one-on-one: one that went well and one or two to work on, each moment quoted.
~20h/mo

Step 4 of 5Pick what to coach

  • The agent

    Suggests two or three conversations per rep for the week’s one-on-one: one that went well and one or two to work on, each moment quoted.

    The most useful example is rarely the lowest score. It’s the call that shows the habit worth changing.

Reads
  • QA tool
Writes
  • QA tool

~20 hours a month back

Where teams differWeekly one-on-ones are common, though some leads run a monthly group session with examples from the whole team.

Automation: Posts the week’s scores by team and by scorecard line, and sends each lead a summary on Monday morning.
~10h/mo

Step 5 of 5Report the week

  • Automation

    Posts the week’s scores by team and by scorecard line, and sends each lead a summary on Monday morning.

    The scores are in. Adding them up by team and by line is arithmetic.

Reads
  • QA tool
Writes
  • QA tool
  • Email

~10 hours a month back

Ends withScored, or with a leadScored line by line with the moments quoted, or in front of the rep’s team lead that day.
Total~84h/mo

What changes

Your scorecard is applied to every conversation, not just a sample. Team leads coach from quoted moments, and critical misses reach them the same day.

  • 3steps automated
  • 2steps for the agent
  • 1call kept with your team

Pick any step to see what happens there and why it sits in that lane.

What it could be worth

~84 hours a month back

$42,300 a year in time

For a support team handling about 5,000 calls, chats and emails a month, at $42 an hour. We work out yours from your own volumes before you sign.

Let’s build your agent
What we customize with you

One proven agent, plugged into how you work.

Every team does this job a little differently, so we set these five with the people who do it today. We’ve done this in dozens of businesses, so we know where teams usually differ and ask about those first.

The agent

Same for every client
  • Follows the same proven steps
  • A person on every exception
  • Every decision logged
  • Tested on your past work first
  • Never decides anything about a rep’s performance

  1. Your systems

    Where the work comes in, and where the result goes.

    For this agentCalls, chats and emails from your phone system and support desk, scores into your QA tool.

  2. Your rules

    The limits and exceptions it works to.

    For this agentYour scorecard, which lines are critical, and how much each one counts.

  3. Your team

    Who signs off, and who covers when they’re away.

    For this agentEach team lead for their own reps, the support manager when a lead is away.

  4. Your channels

    Where your team hears from it.

    For this agentSlack for same-day flags, a weekly summary by email.

  5. Your output

    What it hands back, in the format you already use.

    For this agentA scored conversation with the moments quoted, and a coaching list for each rep.

Answering tickets and handing over escalations are other agents in the catalog. Coaching, and anything that feeds a rep’s performance review, stays with your leads.

What you get

The agent, and everything that keeps it working.

  • The agentRunning on your systems, under your rules.
  • The review screenWhere the exceptions land for your team leads.
  • Your rulebookYour limits, exceptions and who signs off, in one place, often for the first time.
  • A test reportYour past conversations, run through it and checked against the number.
  • The runbookHow it works, what to check, and what to do if it stops.
  • 30 days of tuningAfter it goes live, through a full month of your real conversations.
The number we agree

Hours a week your leads spend finding conversations to review. We measure it before we start, and again at day 30.

How we get there

Live in 3 to 6 weeks. About seven hours of your time.

We do the building. Your side: access, your scorecard and a sample of past conversations, and a short weekly check-in.

  1. Before kickoff

    We send the access checklist.

    You, 2 hours. Access, an owner, and your scorecard and a sample of past conversations.

  2. Weeks 1 to 2

    We connect your systems and set it up.

    You, 1 hour. Walk us through your rules.

  3. Weeks 2 to 4

    We test it on your past conversations.

    You, 1 hour. Review what it flagged.

  4. Weeks 3 to 6

    It runs beside your team, then goes live.

    You, 1¼ hours. Work from the review screen.

Then 30 days of tuning, with a short check-in each week, about two hours of yours. At day 30 we show you the number and hand everything over.

After it’s live

It keeps running whether or not we stay.

  • It runs in your accounts

    Your cloud, your systems, and an AI account in your name, billed by the provider at their rates.

  • Changes in the first 30 days are included

    A new rule, a changed limit, someone new signing off. That’s what tuning is for.

  • After that, your call

    Your team edits the rulebook, the care plan covers it, or a bigger change is quoted first.

Questions

About this agent.

Does it listen to calls?
It reads the transcripts your phone system already makes. If yours doesn’t make them, we’ll talk through the options on the first call.
Should our reps know it reviews their work?
Yes, and we suggest telling them before it goes live. Every score links to the moment it came from, and their lead has the final word on any of it.
Can we change the scorecard later?
Yes. The scorecard lives in your rulebook, so a new line or a change in what counts as critical applies from the next conversation.
Our process isn’t quite like this. Will it still work?
That’s the usual case. The job looks the same in most businesses, but the details never do. We map how your team does it today, then set the rules, systems and approvals to match. That’s what most of the 3 to 6 weeks are for.
How do we agree the number?
Together, before any work starts. For this agent it’s the hours a week your leads spend finding conversations to review. We measure it before we start, and again at day 30.
What does it cost to run once it’s live?
Hosting and AI, paid straight to the providers, not through us. It usually runs 5x to 25x cheaper than doing the same work by hand, and we work out your figure from your real volumes before you sign.

Does your team already have a QA scorecard?

Tell us how your team handles conversations today. We’ll show you this agent on examples like yours, and whether it fits the fixed price.

Let’s build your agentBack to Customer Support
New to Switchboard Agents? How it works, what’s included, and what it costs.
  • 3 to 6 weeksto live, then 30 days of tuning
  • $12,500fixed, per agent
  • Yours to keepno license fees
See the service
Switchboard Agents$12,500 fixed · live in 3 to 6 weeks How it works Let’s build your agent