企业知识智能Accounting · Knowledge Base
FOR ACCOUNTING FIRMS

Internal knowledge base for a small accounting firm:
three things decide whether it survives

We have built these for a handful of accounting and tax firms. Skipping any one of the three is usually why the project quietly dies within six months.

企业知识智能/常见问题/Accounting firm knowledge base

Written in response to a recurring question in public communities: has anyone built an internal knowledge base for a small accounting firm?

1. Recency has to be a first-class field, not an afterthought

Tax rules change constantly, and old versions pile up on the server. Dense retrieval has no concept of time — it ranks on semantic similarity. An obsolete treatment can match the question better than the current one and get served with total confidence. People usually find out when a client asks about it.

What to do

Put an effective date and an expiry date on every document, and archive the old version out of the index when a new one lands. Do not leave them side by side and hope ranking sorts it out. This is baseline, not an optimization.

2. People search by situation, not by document

The real question is rarely "find me notice 2026-XX." It is "how do we treat this situation for this client." That answer is spread across three places: the regulation, last year's working papers, and somebody senior's judgment. The first two are on disk. The third isn't, and no retrieval system will ever reach it.

What to do

Organize entries by scenario, each with a named owner and a review date. Entries without an owner rot silently — that is the single most common reason these systems stop being trusted.

3. Your main documents are tables, and tables break easily

Working papers, schedules, filings. If chunking separates the header row from the data rows, "what was this line in Q2" becomes unanswerable — and the system will not say it does not know, it will offer a plausible number from somewhere else.

What to do

Parse tables structurally before they go in, preserving the header-to-row relationship. Skipping this step is how firms end up concluding "the system is wrong."

Client isolation is non-negotiable in this industry

Working papers and client identifiers are highly sensitive. Tag everything with client ownership and confidentiality level at ingest, and filter the candidate set before retrieval — not after. If you filter what is displayed once the text already went into the model context, you are not really controlling anything.

Is it worth doing at all? A blunt test

Is there a question your team answers more than ten times a month?
If yes, it is worth building — start with that one scenario and make it work before expanding.
If not, organize your files first and revisit later. Bulk-importing everything just relocates the mess.

What we deliver

  • Assessment of your material: what is usable now, what needs cleaning first, what cannot go in at all
  • Scenario-based entry structure with owners and review cycles
  • Recency fields, version archiving, structural table parsing, client-isolation metadata
  • A knowledge-gap list at handoff — what the system genuinely cannot cover
  • Private deployment. Your working papers do not leave your environment.

We are in an initial pilot phase. Pricing is confirmed per engagement based on material volume and scenario complexity; we do not publish figures before they are confirmed.

Check these against your own files

Tell us the one query your team answers most often. We will tell you what can and cannot be done with the material you actually have.

提交后进入需求沟通,我们不会群发营销信息。若你的场景被判定为不适合做,会直接说明。

We are currently in an initial pilot phase. Pricing is scoped per engagement based on corpus size and scenario complexity — no unverified figures are published here.

已收到 ✓ 我们会在两个工作日内回复,先就你写下的那类查询给出「能做到 / 做不到」的边界判断,再谈方案。

相关页面