Skip to content
Customer Support agent

Help articles from tickets

The questions your customers keep asking, found in your solved tickets and drafted into help articles from your team’s best answers. A person reads each one before it goes live.

  • $12,500 fixed
  • Live in 3 to 6 weeks
  • Yours to keep
Let’s build your agent How it works
The review screen for Help articles from tickets: four items, three done, and one (Answers differ) waiting for the support lead, who is asked: Most reps say annual plans can’t be paused, two said they can. Draft it as a no?
How it works

Less retyping the same reply. More customers finding the answer.

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 Help articles from tickets, in 5 steps. It starts with “A question keeps coming up” and ends with “A draft, ready to publish”. Each step lists what automation, the agent and your team do there.
Help articles from ticketsA typical run
Starts withA question keeps coming upThe same question shows up across solved tickets, worded a dozen different ways.
The agent: Reads this month’s solved tickets and sees that “stop billing for a bit”, “freeze my account” and “pause plan” are one question, asked 18 times.
~14h/mo

Step 1 of 5Group the questions

  • The agent

    Reads this month’s solved tickets and sees that “stop billing for a bit”, “freeze my account” and “pause plan” are one question, asked 18 times.

    Customers rarely word it the same way twice, so a keyword count misses most of them.

Reads
  • Support desk
Writes
  • Knowledge base

~14 hours a month back

Where teams differThe bar for a new article varies: ten asks a month, or any question that comes up three weeks running.

Automation: Searches your help center by title and tag, and lists the tickets where reps linked an article on the same topic.
~6h/mo

Step 2 of 5Check the help center

  • Automation

    Searches your help center by title and tag, and lists the tickets where reps linked an article on the same topic.

    Your help center and the links reps send already show which articles exist. Checking them is a lookup.

Reads
  • Knowledge base
  • Support desk
Writes
  • Knowledge base

~6 hours a month back

The agent: Writes the article from the clearest replies your team sent, in your style guide, with the steps checked from one answer to the next.
~36h/mo

Step 3 of 5Draft the article

  • The agent

    Writes the article from the clearest replies your team sent, in your style guide, with the steps checked from one answer to the next.

    The best answer is spread across four replies, each with a piece the others missed.

Reads
  • Support desk
Writes
  • Knowledge base

~36 hours a month back

Automation: When reps gave different answers to the same question, the draft waits for the support lead with each answer and its ticket side by side.
IfYour team: Confirms that annual plans can’t be paused, only moved to a smaller plan, and the draft says exactly that.
~4h/mo

Step 4 of 5Settle the policy

  • Automation

    When reps gave different answers to the same question, the draft waits for the support lead with each answer and its ticket side by side.

    The draft lists every answer it drew from. Any draft whose sources disagree is held, by rule.

  • Your teamIf your team’s answers differ

    Confirms that annual plans can’t be paused, only moved to a smaller plan, and the draft says exactly that.

    What your policy is, and what you say in public, is a call for the person who owns it.

Reads
  • Knowledge base
Writes
  • Knowledge base

~4 hours a month back

Where teams differProduct often reviews the drafts about how a feature works. Policy drafts stay with support.

Automation: Saves the draft in your help center as unpublished, links the 18 tickets it came from, and tells whoever publishes that it’s ready.
~4h/mo

Step 5 of 5Queue it for review

  • Automation

    Saves the draft in your help center as unpublished, links the 18 tickets it came from, and tells whoever publishes that it’s ready.

    Drafts always land unpublished in one place, so whoever publishes knows where to look.

Reads
  • Knowledge base
Writes
  • Knowledge base
  • Team chat

~4 hours a month back

Ends withA draft, ready to publishAn unpublished article in your help center, linked to the tickets it came from.
Total~64h/mo

What changes

Your help center keeps up with the questions customers ask most. Drafts come from your team’s best answers, and a person reads each one before it goes live.

  • 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

~64 hours a month back

$30,700 a year in time

For a support team solving about 4,000 tickets a month, at $40 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 publishes an article on its own

  1. Your systems

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

    For this agentSolved tickets from your support desk, drafts into your help center.

  2. Your rules

    The limits and exceptions it works to.

    For this agentHow often a question must come up, your style guide, and topics that never get a public article.

  3. Your team

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

    For this agentThe support lead for policy questions, product for anything about how a feature works.

  4. Your channels

    Where your team hears from it.

    For this agentSlack when drafts are ready, a monthly list by email.

  5. Your output

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

    For this agentAn unpublished draft in your help center, with the tickets it came from linked.

Answering tickets and reviewing conversations are other agents in the catalog. What your policy says, and what goes public, stay with your team.

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 support lead.
  • Your rulebookYour limits, exceptions and who signs off, in one place, often for the first time.
  • A test reportYour past tickets, 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 tickets.
The number we agree

Tickets a month on questions your help center already answers. 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, six months of solved tickets and your current help center, and a short weekly check-in.

  1. Before kickoff

    We send the access checklist.

    You, 2 hours. Access, an owner, and six months of solved tickets and your current help center.

  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 tickets.

    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.

Will it publish anything on its own?
No. Every draft lands unpublished in your help center, and someone on your team reads it and publishes it.
Does it update old articles too?
Yes. When your team’s recent answers no longer match an article, it drafts the change and marks what’s different, for the same review.
Will it sound like us?
It follows your style guide and your best existing articles. If you don’t have a style guide, we write a short one with you during setup.
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 tickets a month on questions your help center already answers. 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.

What does your team answer most often?

Tell us how your team handles tickets 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