Month-end reconciliations
Matches bank, supplier and balance sheet items against your rules and queues the exceptions with a suggested reason. It proposes, and a person approves.
AI for Finance
AI for finance teams, with every number signed off by your people
Month-end is mostly spent finding and checking numbers rather than explaining them. We connect AI to your accounting system, spreadsheets and bank data so reconciliations, variance commentary and the management pack arrive prepared, and a named person signs off everything that reaches the ledger or the board.
.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}
What we usually find at month-end close, and what we build instead
Four things we find in finance teams whose month-end has never been engineered.
Without SpotDev
What we usually find
With SpotDev
What we build instead
Without SpotDev
Reconciliations ticked by hand
Bank, supplier and balance sheet items matched line by line in spreadsheets, with the exceptions found late.
With SpotDev
Matched, with exceptions queued
Items matched against your rules, and the ones that do not match put in front of a person with the likely reason.
Without SpotDev
Variance commentary written from scratch
Every month someone rebuilds the same explanation of why costs moved, from three reports and memory.
With SpotDev
A first draft from the numbers
Commentary drafted from the ledger and last month's narrative, each statement linked to its figure, for your team to edit and sign.
Without SpotDev
The board pack takes days
Most of the time goes on collecting and formatting figures rather than deciding what they mean.
With SpotDev
Assembled in your template
Approved figures pulled into the pack you already use, with stale, missing or inconsistent inputs flagged.
Without SpotDev
Audit requests land on one person
The auditors send a list, and someone spends days finding invoices, approvals and reconciliations.
With SpotDev
Evidence found and indexed
Requested documents matched to the list and the gaps marked, for a person to check before anything is sent.
What a finance wave activates
A wave activates two of these, chosen against your own value case. Enablement is part of every wave, not an alternative to one.
Variance commentary
Drafts the explanation of movements against budget and last year from the ledger and your notes, with every statement traceable to a figure.
Management and board packs
Pulls approved figures into your template, refreshes the tables and flags anything stale, missing or inconsistent before anyone reads it.
Cash position and forecast
Assembles the cash position from your bank and accounting data and rolls the forecast forward from the latest actuals, for your team to review.
Audit evidence requests
Finds and indexes the documents your auditors ask for and marks what is missing, so the request list is answered from evidence.
Enablement for the finance team
Your team trained on the workflow: what the system checks, what it cannot see, and when to send something back.
The systems we connect to
- 01
Accounting
Xero, QuickBooks, Sage 50, Sage 200, Sage X3, Sage Intacct, Exact Online, FreeAgent, iplicit and Access Financials.
- 02
ERP
Microsoft Business Central, NetSuite, SAP Business One and Odoo, among others in our integration library.
- 03
Spreadsheets and bank data
The workbooks your close actually runs on, and bank data from your accounting system or bank, with each figure traced back to where it came from.
- 04
Your CRM
So revenue, billing and pipeline reconcile with the ledger rather than living in separate reports.
Where the human line sits
Finance work is audited, so the boundary is written down before anything runs.
Prepares, never posts
Reconciliations and journals are prepared for a person to approve. Nothing reaches the ledger on its own.
Segregation of duties kept
The person who prepares is never the person who approves, and the system does not change that.
Never decides treatment
Revenue recognition, provisions and tax coding are judgements for a qualified person, every time.
Every figure traceable
Commentary and packs link each number to its source, so a reviewer can check it in one step.
Points at numbers, not conclusions
It gets you to the figures faster. What they mean, and what to tell the board, stays with you.
Everything is logged
Every preparation, approval and rejection recorded, so you can show your auditors what happened and who decided.
What AI for finance 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 finance team using AI on their own reconciliations, commentary and reports, 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 finance work
- Shared starter tools for commentary, summaries and report checks
- A review at day 30
Custom Agents
£20,000
One finance workflow built into your systems and put into controlled use.
- One workflow, such as reconciliations with an exception queue, or variance commentary
- Integration with your accounting system 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
Finance as one wave of a twelve-month programme that moves a department 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 accounting system we already run?
Probably. Xero, QuickBooks, the Sage range, Business Central, NetSuite and others are already in our integration library. What each supports depends on your edition, which we check rather than assume.
Does it post anything to the ledger?
No. It prepares reconciliations, journals and commentary for a person to approve. Posting stays with your team.
How accurate is it?
We will not quote a percentage we have not measured on your own data. Accuracy is established against your past months during the first wave, and the approval step exists because it will never be perfect.
Our close runs on spreadsheets. Is that a problem?
No. That is the normal starting point. We work with the workbooks you have, trace each figure back to its source, and only suggest moving something out of a spreadsheet when there is a clear reason.
What will our auditors make of it?
Talk to them early, and we will help. Every preparation and approval is logged against its source, so you can show who did what and when. Whether a particular control satisfies your auditors is their decision, and we build to what they ask for.
Does this replace anyone in the finance team?
It removes the collecting and retyping, not the judgement. Somebody still approves, handles the exceptions and explains the numbers to the board. How you use the time it frees is your decision.
Is it safe to put our financial data into AI?
On their business plans, Anthropic and OpenAI do not train their models on your content by default. We give each role access to only the data it needs, keep anything that does not need to go in out of the system, log every action, and put the position for your chosen vendor in writing. Our guide to whether Claude is safe for business covers the detail.
Are you giving us accounting, tax or legal advice?
No. We give no financial, tax, legal or accounting advice. We build the controls, and your advisers rule on your obligations.
What does it cost?
AI Starter gets a team of up to 15 using AI on their own finance work for £3,500, set up and trained remotely over four weeks. One finance workflow built into your systems is a Custom Agents project at £20,000. Running finance 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 finance 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.