Service desk triage
Reads incoming tickets in your PSA or help desk, classifies and routes them, attaches the client's history and drafts a first reply. An engineer decides what is sent.
AI for Technology, Media and Telecoms
AI for technology, media and telecoms, with a person approving what customers see
Software, managed service and telecoms teams spend a lot of their time reading tickets, answering security questionnaires and keeping documentation in step with the product. We connect AI to your service desk, engineering and billing systems so that work arrives prepared, and a named person approves anything that reaches a customer or a client's systems.
.png?height=28&name=Gunnebo%20Logo%20(1).png){kind=small}
.png?height=28&name=Closer%20Still%20Media%20(1).png){kind=small}
.png?height=28&name=Ecommpay%20Logo%20(1).png){kind=small}
.webp?height=28&name=Tussell%20Logo%20(1).webp){kind=small}
-4npmo6jxod.png?height=28&name=iconsolutionsrgb%20(1)-4npmo6jxod.png){kind=small}
Where the time goes today, and what we build instead
SpotDev's AI for technology, media and telecoms builds working AI into the service desk, engineering and customer systems you already run, and writes down where a person has to approve before anything runs.
Without SpotDev
Common today
With SpotDev
What we build instead
Without SpotDev
Every ticket read and routed by hand
Engineers and support staff open each ticket, work out what it is, look up the client's history and decide who should have it.
With SpotDev
Triaged with the history attached
Tickets classified and routed by your rules, with the client's contract, assets and recent tickets pulled in and a first reply drafted for a person to send.
Without SpotDev
Security questionnaires answered from scratch
Each prospect's questionnaire lands on the same two people, who search old answers and policies to fill it in.
With SpotDev
Drafted from approved answers
Answers drafted from your policies, audit evidence and previous responses, with any question that has no approved answer marked for an owner.
Without SpotDev
Documentation trails the product
Release notes and help articles are written after the release, if at all, from memory and a list of ticket numbers.
With SpotDev
Drafted from the work itself
Release notes and help article updates drafted from merged changes and closed tickets, for the product owner to edit and approve.
Without SpotDev
Account reviews built the night before
Usage, support history and billing sit in different systems, so the renewal review is assembled by hand under time pressure.
With SpotDev
Account packs assembled in advance
Usage, tickets, billing and contract dates pulled into your review template ahead of the meeting, with gaps and risks flagged.
What we build for technology, media and telecoms
Each workflow is built into your own systems, with the approval point agreed before it runs.
Security questionnaires
Drafts answers from your approved policies, audit evidence and past responses, and never claims a certification you do not hold. A named owner signs off every answer.
Release notes and help content
Drafts release notes and help article updates from merged changes and closed tickets in Jira, Azure DevOps or GitHub, for the product owner to approve.
Account reviews and renewals
Assembles usage, support history, billing and contract dates into your review template before each meeting, and flags the accounts that need attention.
Complaint and report queues
Flags messages that read as complaints, and user reports on services that host content, and puts each one in front of the right person with its context. The decision stays with your team.
Enablement for your teams
Your support, product and account teams trained on each workflow: what it checks, what it cannot see, and when to send something back.
The systems we connect to
- 01
Service desk and PSA
ConnectWise PSA, Autotask PSA, Jira Service Management, Zendesk, Freshdesk and Intercom.
- 02
Engineering
Jira, Azure DevOps and GitHub, so release notes and documentation are drafted from the work your engineers have shipped.
- 03
Billing and finance
Stripe, Chargebee, Xero, NetSuite and Sage Intacct, so account reviews use the same figures as your invoices.
- 04
CRM and telephony
Salesforce and Dynamics 365, Planhat for customer success, and telephony such as 3CX, 8x8, Dialpad, Aircall and Twilio.
The rules we build to
Each workflow is built around the rules that already apply to your data and your customers, and the approval line is agreed in writing before it runs.
A DPIA before it runs
UK GDPR requires a data protection impact assessment where processing is likely to result in a high risk, and the ICO's AI guidance says that will be the case for most uses of AI. We give your data protection lead what they need to complete one before go-live.
Sub-processors approved first
Where you process your customers' data, UK GDPR says a processor must not engage another processor without the controller's written authorisation. The AI vendor goes through your sub-processor process before any customer data reaches it.
Online safety assessed before changes
If users can share content on your service, the Online Safety Act requires a further illegal content risk assessment before any significant change to its design or operation. Adding AI to moderation or recommendations waits for your assessment, and moderation decisions stay with your moderators.
Complaints recognised and kept open
Ofcom's General Condition C4 requires communications providers to follow its Approved Complaints Code for domestic and small business customers. Triage flags anything that reads as a complaint, routes it to a person and never closes one.
Nothing runs on a client's systems unattended
For managed service providers, the system can suggest a fix or prepare a script. An engineer working within the client's authorisation decides whether it runs.
Everything is logged
Every draft, approval and rejection is recorded, so you can show a customer, an auditor or a regulator what happened and who decided.
What AI for technology, media and telecoms costs
Three ways in, depending on how far you want to go. Prices exclude VAT, and AI subscriptions and usage are billed to you by the vendor. For a whole department of up to 100 people, AI Rollout starts at £18,000.
AI Starter
£3,500
Your team using AI on their own support, product and account work, set up and trained online over four weeks.
- Up to 15 people, fully remote
- Workspace and usage rules set up for you
- Three live online sessions on real technology, media and telecoms work
- Shared starter tools for ticket summaries, release notes and questionnaire drafts
- A review at day 30
Custom Agents
£20,000
One workflow built into your systems and put into controlled use.
- One workflow, such as service desk triage with routing, or security questionnaire drafting
- Integration with your systems and data sources
- Approval rules written down per action
- Training for the people who use it
- Measured against a baseline
- 60-day post-launch support
AI Accelerator
From £10,000 per month
One department at a time, in a twelve-month programme that moves a team into controlled production each quarter.
- Committed a quarter at a time
- Two production agents per wave
- Baseline, measurement and a monthly review
- Model and platform usage billed separately
Implementation expertise that drives adoption
An in-house engineering team that has delivered more than 300 technology projects. Work with engineers who have built this before.
300+HubSpot implementations, firm-wide
In-house engineering team.
Agents and integrations designed, tested and shipped by our own engineers. Nothing is subcontracted.
OpenAI Select Partner, Certified in the Claude Partner Network
SpotDev is an OpenAI Select Partner and is Certified in the Claude Partner Network, alongside HubSpot Diamond status and Custom Integration and Onboarding accreditations.
Model chosen for the job.
Honest evaluation of the right model for the work. We will say when the answer is the AI you already pay for.
AI with security in mind
- Not trained on by default
- Cyber Essentials Plus
- Built on your infrastructure
- In-house engineers
Common questions
Will it work with the service desk and tools we already run?
Probably. Jira, Zendesk, Freshdesk and Intercom are already in our integration library. For a PSA such as ConnectWise PSA or Autotask PSA, what is possible depends on your edition and the access it allows, which we check rather than assume.
Does it change anything on a client's systems by itself?
No. It can suggest a fix, draft a reply or prepare a script. An engineer decides whether anything runs, within the access your client has authorised.
Can it answer security questionnaires for us?
It drafts them. Answers come from your approved policies, audit evidence and previous responses, and any question without an approved answer is marked for an owner. A named person signs off every questionnaire, and it never claims a certification such as ISO 27001 or a SOC 2 report that you do not hold.
We are a SaaS company. Can you build AI into our product as well?
This page covers the work your own teams do. Building AI features into your product is a software project, and we scope it through our bespoke software service.
Is it safe to put our customers' data into AI?
On their business plans, Anthropic and OpenAI do not train their models on your content by default. We give each workflow access to only the data it needs, keep anything that does not need to go in out of the system, and log every action. Where you process data for your own customers, the vendor goes through your sub-processor process first, and we put the position for your chosen vendor in writing.
We host user content. Does the Online Safety Act affect this?
It may. The Act covers services where content shared by one user can be encountered by other users, with some exemptions, such as services where users can only comment on or review the provider's own content. Whether your service is in scope, and whether a change counts as significant, is for your advisers. We build so that moderation decisions stay with your team and any change can wait for your risk assessment.
Are you giving us legal or regulatory advice?
No. We give no legal or regulatory advice. We build the controls, and your advisers and compliance team rule on your obligations.
Does this replace anyone in the team?
It removes the reading, searching and retyping. Engineers still decide what is sent and what runs, and account managers still own the conversation with the customer. How you use the time it frees is your decision.
What does it cost?
AI Starter gets a team of up to 15 using AI on their own support, product and account work for £3,500, set up and trained remotely over four weeks. One workflow built into your systems is a Custom Agents project at £20,000. Running a department as one wave of the AI Accelerator starts at £10,000 per month, committed a quarter at a time. Model and platform usage is billed separately, and enterprise programmes are priced on complexity.
Start with a diagnostic.
A short, fixed-scope assessment of which technology, media and telecoms workflows are worth automating, which are not, and where the approval line has to sit. No obligation.
Related:
SpotDev is an OpenAI Select Partner and a HubSpot Diamond Solutions Partner, and is Certified in the Claude Partner Network. SpotDev is a separate company from OpenAI and from Anthropic, and partner status does not constitute endorsement of SpotDev by OpenAI or by Anthropic. OpenAI and ChatGPT are trademarks of OpenAI. Claude is a trademark of Anthropic, PBC. HubSpot is a trademark of HubSpot, Inc.