Bookkeeping automation that leaves the judgement calls to your bookkeepers
Bank rules clear the routine lines; the rest still need a person. We build a workflow that reads uncategorised transactions from QuickBooks Online or Xero where the API allows, suggests a category from the client's own coding history with a short reason, groups unknowns into one tidy client query and summarises month-end exceptions for the reviewer. Nothing posts without a bookkeeper. A typical build costs $1,000 to $2,500 per workflow and takes about four to five weeks.
The problem
Where bookkeeping time really goes
For every client on the books, a month of bank lines comes in. Bank rules handle the rent and the software subscription; the transfers, mixed card payments and new suppliers wait for a bookkeeper to look up how they were coded last time, and the missing receipts become a string of separate emails to the client.
Before a sales tax or VAT return, a reviewer then opens each file to check suspense, control accounts and old unreconciled items. Across a full client list, both jobs are repetitive, but both still need judgement, which is why simple rules alone have not solved them.
What we build
What our bookkeeping automation includes
Suggested coding with reasons
Each uncategorised line gets a suggested account and tax code, based on how this client coded similar items, with the reason shown.
Grouped client queries
Lines nobody can identify become one tidy query per client instead of a dozen emails.
Receipt chasing
Missing receipts listed and requested through your portal or Dext, with reminders.
New rule candidates
Repeated patterns listed as candidates for new bank rules the bookkeeper can approve.
Month-end exception summary
Suspense, control and owner loan balances, old unreconciled items and unusual swings listed per client.
Review queue
Clients ordered by how much needs attention, so reviewers start with the worst files.
Who does what
Automation does the chasing, people make the calls.
-
01
Automated
Transactions read
Uncategorised lines and key balances are read from the ledger where access allows.
-
02
Automated
Suggestions drafted
Each line gets a suggested category and reason from the client's history.
-
03
Automated
Queries grouped
Unknown lines and missing receipts become one client query.
-
04
Staff review
Bookkeeper confirms
The bookkeeper accepts, changes or rejects every suggestion before anything posts.
-
05
Accountant or partner decides
Accounting judgement
Tax treatment and anything unusual is decided by the accountant or manager.
How it behaves
How bank reconciliation triage behaves
What the client sees
- One clear list of questions instead of scattered emails
- Receipt requests with a simple upload link
What staff see
- Suggested categories with reasons, ready to accept or change
- Rule candidates to approve
- A month-end exception summary per client
What the automation does
- Reads ledgers on schedule where access allows
- Groups unknowns and chases receipts
- Never posts or files anything on its own
Edge cases and fallbacks
- New client with no coding history
- No suggestions; lines go straight to the bookkeeper.
- Low-confidence match
- Shown as unknown rather than guessed.
- Ledger connection expires
- The client is skipped and the bookkeeper is asked to reconnect.
- AI provider outage
- The batch is held and rerun; bookkeepers can work in the ledger as usual.
Architecture
Bank feed triage for a bookkeeping team at a glance.
- Input
- Logic and services
- AI step
- Output
- People
- Data
How it flows
- 1 On a schedule, the workflow reads uncategorised lines and the client's past coding from the ledger.
- 2 Each line gets a suggested category and a reason; unknowns are grouped.
- 3 The bookkeeper confirms or changes every suggestion, and one query goes to the client.
- 4 A month-end exception summary lists what the reviewer needs to look at.
Project planner
How the project runs, phase by phase.
Bookkeeping automation & bank reconciliation triage project plan
Typical time to launch: about 4 weeks, then support
-
01
Discovery
2 to 3 days
Ledgers in use, API access per client, bank rule habits, review checklist and receipt tools.
-
02
Design
2 to 3 days
Suggestion rules, confidence thresholds, query format and the exception summary layout.
-
03
Build
About 2 weeks
Ledger connections, suggestion step, grouping, receipt requests and summaries.
-
04
Shadow run
About 1 week
Suggestions run on a pilot set of clients while bookkeepers code as normal and compare.
-
05
Launch
1 to 2 days
Switch on for agreed clients and train the bookkeeping team.
-
06
Support
Ongoing
Tuning suggestions and adding clients.
What it runs on
Real products only, connected through the access each vendor provides. See all integrations
Cost estimate
What it costs, line by line.
-
Discovery and design
Ledgers, access, suggestion rules and summary layout.
$200 – $400
-
Build
Suggestions, grouping, receipt requests and summaries.
$500 – $1,300
-
Integrations
QuickBooks Online, Xero, receipt tool and review queue.
$150 – $400
-
Testing and shadow run
Pilot clients coded both ways and compared.
$100 – $250
-
Launch and training
Switch-on and bookkeeper training.
$50 – $150
-
Total project estimate
$1,000 – $2,500
Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Ledger subscriptions, receipt tools and AI usage are billed to you directly. Mixed ledgers across clients may need a second workflow.
Monthly running costs you pay directly
Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.
- Ledger subscriptions: Your clients' QuickBooks Online or Xero plans, unchanged.
- AI model usage: Billed by the provider per use; short suggestion steps are usually a small monthly amount at firm volumes.
- n8n: Free self-hosted Community edition, or n8n Cloud from about €20 a month (Starter, billed annually) or €50 (Pro).
What pushes cost up
- Systems without an API, or with integration access that must be requested from the vendor
- Writing data back into your core system rather than only reading from it
- Several locations, brands or very different processes to support
- Custom apps, dashboards or a voice line on top of the workflows
What keeps cost down
- One location and one clear process to start with
- Cloud software with a documented API
- Using tools you already pay for instead of adding new ones
- Approved wording and sample data ready at the start
Privacy and consent
Rules we design for, with the sources.
US: service providers under the Safeguards Rule
Covered firms must select service providers capable of safeguarding customer information, require it by contract and assess them periodically, which includes any AI step.
Source: www.law.cornell.eduUS: data security plan
The IRS reminds firms that prepare returns that the FTC requires a written information security plan; ledger connections are listed in it.
Source: www.irs.govEU and UK: processor contracts
Ledger data about individuals is personal data, so AI and automation vendors need an Article 28 GDPR contract.
Source: gdpr-info.euFree tools
Try these first, free.
How we deliver
Agile delivery, in 1 to 2 week sprints.
Every sprint
- 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
- 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
- 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
- 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.
How scope stays under control
- Product backlog
- Every feature, fix and question in one prioritised list you can see at any time.
- Acceptance criteria
- Plain-language conditions for "done" on each item, agreed before work starts.
- Change requests
- New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
- User acceptance testing (UAT)
- Before launch your team tests the real workflow against the acceptance criteria and signs off.
Tools we use
Project manager / Scrum master
Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.
Business analyst
Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.
Automation engineer
Builds the n8n workflows, integrations, AI steps and error handling.
Backend developer
Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.
Frontend / mobile developer
Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.
QA engineer
Tests every workflow against the acceptance criteria, including edge cases and failure paths.
DevOps engineer
Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.
Who does what at each phase
- Free call
- Project manager, business analyst
- Understand the problem, check it is worth automating and outline a rough range.
- Discovery
- Business analyst, automation engineer
- Map the current process, systems and data, and agree success measures.
- Design
- Business analyst, automation engineer, backend developer
- Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
- Sprints
- Automation engineer, developers, QA
- Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
- UAT and launch
- QA, DevOps, project manager
- Your team tests and signs off, we switch on, monitor closely and train the team.
- Support
- Automation engineer, DevOps
- Stabilisation window, then optional monthly care with monitoring and changes.
A point of contact
One person who can answer questions and approve decisions, with about an hour a week during the project.
Access
Admin or API access to the systems involved, created as separate accounts with the least access needed.
Sample data
Real but non-sensitive records (or de-identified ones) so we can design and test against reality.
Approved wording
Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.
Vendor agreements
Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.
Time for testing
A few hours from the people who will use the system, for the demos and user acceptance testing.
Working system
Workflows, integrations and any apps running in your accounts, under your keys.
Documentation
Workflow specification, data-flow map, run book and exported workflow files.
Training
A walkthrough for the team and a short recorded video for new starters.
Handover
All access, credentials and code handed over; you can keep us or take it in-house.
Stabilisation window
Fixes for anything that does not meet the agreed acceptance criteria after launch.
Support options after launch
No plan
You run it yourselves after the stabilisation window and contact us when you need a change.
Monthly care
Monitoring, error alerts, small changes and updates each month, with an agreed response time.
Priority care
Faster response times for business-critical workflows and a monthly review call.
How a project moves through our team
- Input
- Logic and services
- People
- Output
- Data
How it flows
- 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
- 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
- 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
- 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.
FAQ
Bookkeeping automation & bank reconciliation triage questions, answered.
Not responsibly. Matching routine lines is automatable, and bank rules already do much of it. The lines left over need judgement, so we speed up the look-up and grouping and keep a bookkeeper confirming every posting.
Partly. Xero has said it will not offer reconciling bank statement lines through its public API, so in Xero we prepare suggestions and queries for the bookkeeper to apply in Xero itself. QuickBooks Online's API and webhooks allow more, confirmed per client file.
They come from how that client coded similar transactions before, so they are as good as the history. Every suggestion shows its reason and is reviewed, and tax treatment is always checked by a person.
No. We keep the receipt tool you use and connect around it. Dext's API access is limited, so the exact route is confirmed per project.
Some products do similar suggestions inside one ledger. We build around your mix of clients, ledgers and review habits, and connect the result to your practice system and client queries.
Time per client to clear the bank feed, share of suggestions accepted unchanged, queries per client and exceptions found before filing.
Free 20-minute call
Want this for your accountant?
Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.
More for accountants
All servicesCRM for accounting firms: pipeline to signed engagement
Every enquiry from your website, referrals, calls and partners in one CRM pipeline, with proposals, follow-ups and a hand-off into your practice system the moment an engagement is signed.
From $1,000 · About 4 weeks Details
Client onboarding, engagement letters & due diligence
Turn a signed proposal into a complete client file: engagement letter for e-signature, identity and ownership evidence, prior-accountant details and a risk summary ready for the partner.
From $1,000 · About 4 to 5 weeks Details
Tax document collection & automated chasing
Personalised request lists built from last year's file, a secure upload link, uploads matched to each item and reminders that chase on schedule until the job is ready to prepare.
From $1,000 · About 3 to 4 weeks Details