A Claude sidekick for the support desk

Every ticket, already researched before you open it.

When a ticket lands in your lap, Scout has already scouted ahead - read the customer's history, pulled the auction, sale and refund state from our systems, and worked out what's likely wrong. You make the call. It does the legwork.

You decide every action ↵ Pause anytime - it never hammers you
1 at a timeSurfaced at your pace, never a flood
Replies firstWaiting customers before fresh tickets
£0 without youNo refund or credit moves unapproved

The problem

The slow part of support isn't the reply. It's everything before it.

Before an agent can help anyone, they're hopping between Zendesk, the admin panel, and half a dozen internal lookups just to understand what happened. Scout collapses that.

Today, per ticket

  • Open the ticket, read the thread, find the customer
  • Cross-check the sale, auction, booking and refund state by hand
  • Work out the likely cause from scattered evidence
  • Only then start actually helping the customer

With Scout

  • The context is gathered before you look
  • Findings and likely cause presented in one place
  • A menu of actions, each tagged with its risk
  • You decide - it executes, or flags what needs doing

How it works

Gather → Present → Decide → Execute

A tight loop with you in the middle. Claude never acts on its own judgement - it hands you the picture and waits for your call.

1

Gather

A ticket is assigned or a customer replies. Claude reads the live ticket and pulls everything relevant from our systems.

2

Present

You get who the customer is, what they're asking about, what our systems actually say, and the likely cause.

3

Decide

You pick an action from the menu - or tell it what to do in your own words. The decision is always yours.

4

Execute

Claude sends the reply, applies the change, or - where there's no safe automated path - flags exactly what needs doing.

You set the pace

It works for you - not the other way round.

The biggest worry with anything automated is that it'll bury the team. Scout can't. There's a human at the keyboard the whole time, and one word puts it on hold.

Going for a break? Just pause.

Tickets keep queuing safely while you're paused - nothing is lost, nothing bounces to a customer. You come back and pick up exactly where you left off. It surfaces one ticket at a time, at your speed, never a flood.

/scout-pauseStop pulling new tickets - finish what's in hand. Toilet break, lunch, heads-down.
/scout-resumeStart pulling again when you're ready.
/scout-skipNot for you? Release the ticket back to the queue for someone else.
/scout-stopEnd the session entirely. Clock off.
/scout-statusWhat's in hand, are you paused or running, how deep is the queue.

Why it's worth it

Faster tickets, safer decisions, and it grows with you.

The research is done

Minutes of context-gathering per ticket disappear. You open a ticket to a full picture, not a blank page.

You decide, always

Claude presents and recommends; the human makes every call. No action happens without your explicit go-ahead.

£0 moves unapproved

Refunds and credits are never fired automatically. Where there's no safe path, it flags precisely what needs doing.

Replies before new

Customers already mid-conversation are worked first. Fresh tickets wait behind the people who've been waiting longer.

Grows without a rebuild

New abilities - a refund tool, a credit tool - slot in and light up automatically. No rewrite when the toolkit expands.

One less context-switch

It combines Zendesk, our production systems and rail data behind a single conversation. No tab-juggling.

Trust is built in, not bolted on. Every action is logged, gated, and impossible to run away with.

Full audit trail

Every action - taken or flagged - is written back to the ticket as an internal note, tied to the human who approved it.

It can't loop on itself

Its own notes and replies are ignored by the pipeline by design, so it can never re-trigger itself into a spiral.

Money can't move on its own

Actions that move money or change a booking have no automated path today - Scout flags exactly what's needed for a human to do. That boundary is locked by an automated test; nothing financial can fire by construction.

Where it is today

Built, shipped, and live in production.

Straight with you on status - the whole loop is real and running. What's left is proving it on live tickets and hardening it for scale.

Live
The event pipeline & zero-cost wake.

Signed, replay-protected Zendesk ingestion → two priority queues → a live session woken with zero cost while idle. Proven end to end on a real device.

Live
Gather → present → decide → execute.

The full interactive loop: identify the customer, gather across our systems, present the picture, and carry out your decision - reply, note, status, tag - with a hard confirmation on anything customer-facing.

Live
The controls.

Pause, resume, skip, stop, status - all shipped. A pause lands in about two seconds, and the queues are never touched while you're away.

Live
Claim-on-pull & clean hand-off.

Scout claims a ticket as it opens it - never one a colleague already owns - and /scout-skip or an offline agent's stranded reply reroutes cleanly to whoever's free.

Live
The money/booking safety boundary.

Anything that moves money or changes a booking is flag-only - no code path can execute it - and that boundary is locked by an automated test. Nothing financial can fire, by construction.

Next
Acceptance with a real agent, then hardening.

Prove it on live tickets with a CS agent; then the scale work - a claim/dedup guard, deeper observability, and a dedicated access role.

The roadmap

MCP servers to build - where a flag becomes an action.

Today Scout flags anything that moves money or changes a booking, because there's no safe automated path to do it. Each of these is that path. Build the tool and - with no change to Scout itself - the flag turns into a confirmed, one-click action. The registry lights it up automatically.

Adyen - payments & refunds

Our payment gateway. A safe, idempotent write path here lets Scout issue a refund or a payment adjustment on your confirmation - instead of flagging "£X refund needed, do it by hand." The single biggest chunk of manual money-work.

SilverRail - bookings & ticketing

The rail retailing engine behind reissues, exchanges, seat changes and rebookings. A write path here turns "reissue this ticket / change this seat - do it manually" into an executed action, confirmed by you.

Seatfrog-MCP - account credit & goodwill

Extend our own toolkit to write, not just read: add credit or goodwill to a customer's account, apply a voucher, adjust an order. The everyday "just sort them out" gestures that today mean a hand-off to another system.

Each is a self-contained MCP server - the same shape as the Zendesk and Seatfrog ones Scout already runs on - built and reviewed on its own, then declared as a dependency. When it lands, its flags become executes with the same confirm-the-exact-amount and full-audit-trail guarantees as every other action. No rewrite; the toolkit just grows.

What it's built on

The MCP servers Scout runs on.

Scout isn't monolithic - it stands on two self-contained MCP plugins, each with its own page. They're the reason a new ability can slot in without a rewrite.