--- title: "Give AI your chart of accounts and client rules so accounting drafts follow them" description: "AI forgets your chart of accounts and client tax facts between sessions. Store them as files so categorization, close, and depreciation drafts follow them." canonical: "https://scalewithsearch.com/articles/ai-memory-for-accounting" date: "2026-01-28" modified: "2026-09-25" --- ## Site navigation - [Scale With Search](https://scalewithsearch.com/) - Real estate - Real estate - [Real estate](https://scalewithsearch.com/for/real-estate) - Work - Start here - [Send your brief](https://scalewithsearch.com/work#send-your-brief) - [Prepare your six-question brief](https://scalewithsearch.com/work#prepare-your-six-question-brief) - Build - [Site build, content library with SEO, signal desk](https://scalewithsearch.com/work) - For your business - Trades and home services - [Auto body and collision shops](https://scalewithsearch.com/for/auto-body-and-collision-shops) - [Foundation and home repair contractors](https://scalewithsearch.com/for/foundation-and-home-repair) - [Garage door and fencing contractors](https://scalewithsearch.com/for/garage-door-and-fencing-contractors) - [HVAC contractors](https://scalewithsearch.com/for/hvac-contractors) - [Janitorial and commercial cleaning companies](https://scalewithsearch.com/for/janitorial-and-commercial-cleaning) - [Locksmiths](https://scalewithsearch.com/for/locksmiths) - [Moving companies](https://scalewithsearch.com/for/moving-companies) - [Pest control companies](https://scalewithsearch.com/for/pest-control-companies) - [Plumbing and electrical contractors](https://scalewithsearch.com/for/plumbing-and-electrical-contractors) - [Restoration and water or fire damage companies](https://scalewithsearch.com/for/restoration-and-water-fire-damage) - [Roofing companies](https://scalewithsearch.com/for/roofing-companies) - [Towing companies](https://scalewithsearch.com/for/towing-companies) - [Tree services and landscaping companies](https://scalewithsearch.com/for/tree-services-and-landscaping) - [Solar installers](https://scalewithsearch.com/for/solar-installation) - [General contractors](https://scalewithsearch.com/for/general-contractors-and-construction) - [Paving, concrete, and flooring contractors](https://scalewithsearch.com/for/paving) - Practices and professional services - [Bookkeeping and tax practices](https://scalewithsearch.com/for/bookkeeping-and-tax-practices) - [Dental practices](https://scalewithsearch.com/for/dental-practices) - [Family and criminal defense law firms](https://scalewithsearch.com/for/family-and-criminal-defense-law-firms) - [Med spas and aesthetics practices](https://scalewithsearch.com/for/med-spas-and-aesthetics) - [Personal injury law firms](https://scalewithsearch.com/for/personal-injury-law-firms) - [Veterinary clinics](https://scalewithsearch.com/for/veterinary-clinics) - [Gyms and fitness studios](https://scalewithsearch.com/for/fitness) - [Therapy and outpatient health practices](https://scalewithsearch.com/for/therapy-and-outpatient-health) - [Medical billing companies](https://scalewithsearch.com/for/medical-billing) - [Insurance agencies](https://scalewithsearch.com/for/insurance-agencies) - [Financial advisors](https://scalewithsearch.com/for/financial-advisors) - [Property management companies](https://scalewithsearch.com/for/property-management) - [Recruiting and staffing agencies](https://scalewithsearch.com/for/recruiting-and-staffing) - [Architects and interior designers](https://scalewithsearch.com/for/architects-and-interior-designers) - [Logistics and supply chain companies](https://scalewithsearch.com/for/logistics-and-supply-chain) - Agencies, MSPs, and manufacturing - [IT and managed service providers](https://scalewithsearch.com/for/it-and-managed-service-providers) - [Machine shops and precision manufacturers](https://scalewithsearch.com/for/machine-shops-and-precision-manufacturing) - [Marketing agencies and freelancers](https://scalewithsearch.com/for/marketing-agencies-and-freelancers) - [SEO agencies and consultants](https://scalewithsearch.com/for/seo-agencies-and-consultants) - [Small manufacturers and fabricators](https://scalewithsearch.com/for/small-manufacturers-and-fabricators) - Restaurants, shops, studios, and nonprofits - [Restaurants and hospitality businesses](https://scalewithsearch.com/for/restaurants-and-hospitality) - [Retail stores and ecommerce sellers](https://scalewithsearch.com/for/retail-and-ecommerce) - [Photographers, event planners, and travel agents](https://scalewithsearch.com/for/photographers) - [Churches and nonprofits](https://scalewithsearch.com/for/churches-and-nonprofits) - [All industries](https://scalewithsearch.com/for/) - Learn - For your office - [Office job guides](https://scalewithsearch.com/guides/) - [Browser calculators](https://scalewithsearch.com/tools/) - Start here - [How it works](https://scalewithsearch.com/how-it-works) - [Free Starter Kit](https://scalewithsearch.com/kit/business-memory-starter-kit.zip) - [Synthetic specimen](https://scalewithsearch.com/specimen/working-session-specimen.zip) - Guides - [The Complete Guide to Business Memory for AI Agents](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [The Complete Small-Business Guide to AI Agent Governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [The Complete Guide to Leaving Vendor AI Memory](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - Articles by cluster - [Business memory](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [Agent governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [Migration and ownership](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - For machines - [llms.txt](https://scalewithsearch.com/llms.txt) - [llms-full.txt](https://scalewithsearch.com/llms-full.txt) - [Machine view](https://scalewithsearch.com/?view=machine) - Company - Evidence - [Proof](https://scalewithsearch.com/proof) - Company - [About](https://scalewithsearch.com/about) # Give AI your chart of accounts and client rules so accounting drafts follow them. You ask an AI to categorize expenses from a bank statement. It suggests account codes that do not match your chart of accounts. You correct it: software subscriptions go to 6420, not to a 5000-level account. Marketing expenses need a department allocation. Travel splits into meals, lodging, and transportation. Next month, the same problem returns. The AI has no record of your account structure. You teach the same categorization rules, explain the same client treatments, and restate the same reconciliation steps. Every accounting session starts from zero. ## Why accounting needs persistent context Accounting applies precise rules consistently. Every transaction follows an established rule. Every client has circumstances that change the treatment. Every month-end follows a documented procedure. Every tax situation has its own requirements. Your chart of accounts is not standard. It reflects your structure, your reporting needs, and your industry. One client capitalizes certain expenses. Another uses the cash basis. A third needs job costing by project. These details decide the correct treatment of each transaction. A chat session cannot hold that context for long. You paste the chart of accounts, explain the depreciation schedules, and list which expenses need approval documents. The session ends. Next time you work on that client's books, the context is gone. ## What accounting memory looks like Accounting memory is a small set of Markdown files that an AI reads before the task. One file holds the chart of accounts: account numbers, descriptions, normal balances, and usage notes. Another holds the reconciliation procedures for each account type: bank reconciliation steps, credit card matching, and the accounts receivable aging review. Client files hold the details that change transaction treatment: - entity type and tax elections; - depreciation methods for fixed assets; - inventory valuation method; - expense approval and documentation policy; - capitalization threshold; - state tax jurisdictions and requirements; - prior-year adjustments that need tracking. When you ask for a categorization, the AI reads the relevant chart. When you ask for journal entries, it applies the client's accounting basis and capitalization policy. When you need reconciliation support, it follows the documented procedure and knows which accounts need monthly attention. Client financial records are sensitive. Keep only what the task needs in these files, and keep each client in a separate folder. The article on [what client data belongs in AI agent memory](/articles/client-data-in-ai-agent-memory) sets the limits. ## Categorize transactions under the client's rules A bank download shows fifty transactions. Most recur: known vendors in standard categories. Some need judgment. A software purchase might be capitalized. A meal could be client entertainment or an employee expense. A payment might cover several cost centers. You ask: "Categorize these transactions for Acme Manufacturing." Acme is a fictional client in this example. The AI reads Acme's chart of accounts and client file. The file says Acme uses job costing, so material purchases need job numbers. It gives Acme's capitalization threshold. It says software is split into operating expense or fixed asset by useful life. It says credit card transactions need a matched receipt before posting. The draft follows those rules. Materials carry job numbers. A software purchase above the threshold is flagged for capitalization review. Meals go to the correct entertainment account with a note to verify business purpose. Credit card charges are marked pending receipt. You review and adjust. One job number is wrong. One transaction needs a different allocation. Record each correction as a rule in the vendor or client file, so the next categorization applies it. The AI does not learn from the correction by itself; the file does. ## Build the month-end close checklist Month-end follows a sequence. Bank reconciliations come first: clear outstanding items, investigate discrepancies, and document unusual transactions. The accounts receivable review comes next: age the report, identify collection issues, and assess the reserve. Then the prepaid and accrual analysis decides what needs adjustment for correct period matching. Your accounting standards file documents each step. Bank reconciliation compares cleared checks, verifies deposits, and explains timing differences. The receivables review follows set criteria for reserves. The prepaid analysis refers to the amortization schedule. You ask: "Generate the month-end checklist for Acme Manufacturing, January close." The AI combines your standard procedure with Acme's file. The bank tasks cover Acme's three operating accounts. The receivables review uses Acme's payment terms and collection patterns. The accrual analysis lists the items Acme accrues every month: utilities received but not billed, wages earned but unpaid, and the property tax allocation. The checklist names the accounts to review, the reports to run, and the adjusting entries that usually occur. You work through it without a setup step, because the context is already loaded. ## Apply entity-specific tax treatment The fictional practice has three clients. Acme Manufacturing is an S corporation. Widget Company is a partnership. Services Inc. is a C corporation with accumulated earnings and profits. The same transaction can have different tax results for each: distributions, compensation, and fringe benefits all depend on entity structure and elections. Acme's shareholder takes distributions. They are not deductible, and they reduce the shareholder's basis. Acme's client file tracks basis: beginning basis, income allocations, distributions, and loan basis where it applies. When a distribution is recorded, the AI flags it if it exceeds the tracked basis. Widget Company has three partners with different profit-sharing ratios and guaranteed payments. The allocation formulas and payment schedules live in Widget's client file. When you ask the AI to record guaranteed payments or allocate income, it applies the terms from Widget's partnership agreement as the file records them. Services Inc. needs careful dividend treatment. Its file records accumulated earnings and profits and current-year projections. A distribution is a dividend to the extent of earnings and profits, then a return of capital, then capital gain. The AI flags a distribution that approaches the earnings and profits limit. These are drafts for professional review. Tax elections and treatment are judgment calls that a qualified accountant makes and signs. The files make the facts available; they do not make the decision. ## Focus a reconciliation investigation A bank reconciliation shows a difference. You investigate: compare cleared items, look for duplicate entries, review timing differences, and search for unrecorded transactions. You ask: "Help me find the reconciliation difference for the Acme checking account." The AI reads Acme's reconciliation history. Checks to the main supplier often take weeks to clear. Wire transfers sometimes post at the bank a day before Acme records them. Three months ago, a duplicate entry caused a difference, and a journal entry corrected it. The AI suggests three checks: recent supplier payments against cleared items, last week's wires against their recording dates, and the earlier duplicate-entry pattern. The investigation starts from the probable causes in Acme's history. You find it: a wire recorded in February that posted at the bank in January. You make the correcting entry. Record the exception in Acme's file, so the same timing issue gets caught faster next month. ## Set up a fixed asset and its depreciation Acme buys a CNC machine. The purchase needs capitalization, a depreciation setup, and a tax review of Section 179 or bonus depreciation. Acme's client file records its fixed asset policy. For tax, equipment follows the MACRS recovery class that Acme's accountant assigned. Books use straight-line depreciation over a book life that the file states. Acme takes bonus depreciation when available, subject to the rules for the tax year. The file keeps a fixed asset ledger with description, acquisition date, cost, and method for each asset. You ask: "Record the CNC machine purchase and set up depreciation." The AI drafts the entry to capitalize the asset and calculates straight-line book depreciation over the book life in the file. It notes bonus depreciation for tax and the book-tax difference that must be tracked. It formats the ledger line with every required field. The machine goes into Acme's asset list in the client file. Later depreciation runs read that line. Tax projections include the bonus depreciation effect. When Acme sells or scraps the machine, the original cost and accumulated depreciation are on record. ## Set up the files and the loading The setup has three parts: 1. Claude Code, run in the folder that holds the accounting files. 2. An Obsidian vault, or any folder, with Markdown files for accounting standards and client details. 3. A root `CLAUDE.md` file that says where the accounting information lives and how it is organized. Put the chart of accounts in one file: account numbers, descriptions, typical uses, and restrictions. Give each client a file with entity details, tax facts, and special procedures. Document the reconciliation checklists and the month-end procedure. Record prior-period issues and their resolutions. No accounting software integration is required. You update the files as facts change, and the AI reads them for each task. The files persist across sessions: close Claude Code on Tuesday, open it on Friday, and ask about a client's depreciation schedule. The answer comes from the files, not from chat history. Keep one folder per client, and start each session in the folder of the client you work on. The guide to [separating client context before an agent touches the work](/articles/separate-client-context-before-agent-work) explains why that boundary matters in a practice with many clients. ## Keep the review and approval with people The AI drafts categorizations, checklists, entries, and investigation plans. A person reviews and posts. Decide in advance which actions the AI may prepare and which need a named approver. The [AI agent approval matrix](/articles/ai-agent-approval-matrix) gives a structure for that decision. When a review finds an error, fix the rule in the file, not only the entry. The workflow in [how corrections become part of the system](/articles/corrections-become-system-memory) records the fix, its source, and a test, so the next month's draft applies it. ## Related: AI memory - [Store bookkeeping rules as files so AI codes transactions the same way every month](/articles/ai-memory-for-bookkeeping) - [Turn repeated AI formatting instructions into rules the model reads every session](/articles/ai-doesnt-follow-my-instructions) - [Write down the business facts AI cannot guess before you ask for a draft](/articles/ai-doesnt-understand-my-business) ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```