Yekar.AI
Login

Support inbox triage & reply

Every inbound ticket read, grounded in your own policies, answered in your team's voice - and the ones that need a person routed to a person, with the context already attached.

Talk to usRead the docs

The brief

Written like you’d brief a person.

This is the whole setup - a procedure in plain language, with tools and specialist agents referenced inline. When it runs is not written here: that’s the trigger, configured beside it.

Read each ticket with #yekar.zendesk-support.get-ticket, answer from the support handbook and cite the passage, reply as a draft for anything sensitive, and hand billing disputes to @billing-review. Log every case with #yekar.google-sheets.append-rows.

How it runs

From trigger to logged outcome.

Trigger

Event - A new message lands in the connected support inbox

Help-desk queues without events are swept on a schedule instead.

  1. Read and classify

    Reads the ticket, pulls the customer's history, and classifies the request.

  2. Ground the answer

    Retrieves the relevant policy from your knowledge base - answers cite their sources or say so when the corpus does not cover it.

  3. Draft the reply

    Writes the response in your team's voice, with the evidence it used linked beneath.

  4. Route the exceptions

    Billing disputes and angry threads go to a person with the full context attached - nothing consequential is sent on its own.

  5. Log the outcome

    Appends the case and its resolution to your tracker.

Where people stay in control

Nothing consequential runs on its own.

  • Sensitive replies wait as drafts until a person sends them.
  • Billing disputes are handed to a named reviewer with the thread attached.
  • The whole agent can run draft-only until you trust the voice.

Tools it uses

Runs on accounts you already have.

  • Zendesk
  • Gmail
  • Knowledge base
  • Google Sheets
  • Slack

Connected once, governed per agent - this use case gets only the tools listed here.

Illustrative savings

$1,100–$2,900 / month

Assumes 300–900 tickets a month at 6–9 minutes of handling each, with roughly two-thirds resolved without a person.

Illustrative monthly savings, estimated from typical handling time at public salary benchmarks, reviewed August 2026. Not a promise or a guarantee - your numbers depend on volume and process.

What makes this dependable

Ground its answersLink answers back to their sourcesKeep people in controlPut people in front of risky writesOperate and improveSee what every answer rested on
All use cases →
SupportProduct & policy answers for frontline teamsAnswers product, policy and pricing questions from staff in the channel they already use, grounded in the internal content you maintain, and escalates what it cannot source.Helps save each month$500–$1,400OperationsOrder status & delayed-order outreachWatches orders, catches delays, and mails customers a realistic new estimate before they ask.Helps save each month$700–$1,800FinanceRefund handling with an approval gatePrepares each refund with the evidence, then waits for a person on anything over your threshold.Helps save each month$600–$1,500

Start with the job

See how Yekar.AI would run one of your real processes.

Bring the job, the systems it touches, and the decisions that need a person.

Talk to usRead the docs