---
title: "Keep engagement files your AI reads so deliverables build on the work already done"
description: "Give AI each client's situation, decisions, and prior analyses plus your method library, so drafts and meeting briefs start where the engagement stands."
canonical: "https://scalewithsearch.com/articles/ai-for-consultants"
date: "2026-01-27"
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)

# Keep engagement files your AI reads so deliverables build on the work already done.

Consulting runs on accumulated context. You spend months learning a client's organization, industry, internal politics, and strategic limits. That knowledge makes your advice worth paying for. A generic recommendation is worth little. A recommendation that fits the situation is why clients pay consulting rates.

Then you ask ChatGPT to help with a deliverable, and it knows nothing. It does not know your method, the client's situation, or the three months of discovery behind you. You rebuild all of it in a chat window before real work starts.

The tool that should add capacity takes it away. This page shows how to keep the engagement record in files that the assistant reads first.

## The consultant's problem with chat assistants

Most chat tools treat each exchange as complete in itself. That model fails consulting.

Engagements last months. Deliverables build on each other. The phase one analysis shapes the phase three recommendations. One client can produce dozens of documents, each one dependent on the ones before it.

A chat tool treats every document as the first. You have analyzed the client's competitive landscape three times in your own files. The assistant still needs you to explain it, because it cannot see what you already did.

At consulting rates, that rework is expensive. The cost is not only time. It is mental load, lower draft quality, and the friction that makes AI feel like overhead.

## What a consultant actually needs

The target is an assistant that works like a junior analyst who joined the engagement on day one. It knows the client's situation, understands your method, has read the prior deliverables, and produces drafts that need refinement, not a rewrite.

That is a design choice with three parts:

1. A client knowledge base. Each client's context is written down in a format the assistant can read: industry background, stakeholder map, strategic priorities, engagement history, prior analyses.
2. A method library. Your frameworks, templates, and approaches sit where the assistant can always reach them.
3. Automatic loading. When you start work on a client, the relevant context loads without a paste.

A default ChatGPT chat provides none of the three in a form you maintain as files. A [comparison of ChatGPT memory and Claude memory](/articles/chatgpt-vs-claude-memory-business) shows what each product keeps and what it leaves to you.

## Build the engagement files

The setup uses Claude Code and a folder of Markdown files, such as an Obsidian vault. Claude Code reads a file named `CLAUDE.md` at the start of a session.

Each client gets a context file. It holds the industry, org structure, the stakeholders you work with, engagement objectives, constraints they named, decisions already made, and recommendations already delivered.

```text
## Client: ENG-042 (regional distributor, phase 2 of 3)
Objective: reduce order-to-cash cycle; board wants a plan by 2026-11-30
Stakeholders: CFO (sponsor), VP Ops (skeptical of system change), IT lead
Constraints: no ERP replacement this fiscal year; union contract limits shift changes
Decisions:
- 2026-07-18 steering committee chose process fixes before tooling (minutes: mtg/0718.md)
Delivered:
- Phase 1 diagnostic (deliverables/p1-diagnostic.md); competitive scan (analysis/comp-scan-v3.md)
Open: pricing exceptions data requested from finance on 2026-09-02
```

Your method goes in a separate library: frameworks you use again and again, analysis templates, and the structure of each deliverable type. When you ask for a draft, the assistant already knows how you build that kind of document.

Past deliverables stay in the client folder. When you build on earlier analysis, the assistant cites what you concluded rather than starting fresh. The result reads like it came from someone on the engagement with you. The layers of this design are explained in [AI agent memory architecture for a small business](/articles/ai-agent-memory-architecture-small-business).

## Four uses that change the week

### Deliverable drafts

Ask for a first draft of the strategic recommendations section. The assistant knows the situation, the analysis you completed, and your usual structure for that section. The draft needs editing, not rebuilding.

### Meeting preparation

Before a client call, ask for a briefing. The assistant reports what you discussed last time, which deliverables are pending, which issues are open, and which decisions come next. Time your preparation for two weeks before and after the files exist; that measurement tells you whether the setup earns its upkeep.

### Proposals

A prospective client gets a proposal that names your method and speaks to their situation. The assistant knows your service packages, your pricing approach, and your usual scope structure. You set the price and approve the terms.

### Method application

When you take a client through your framework, the assistant knows the steps. It can guide the analysis, suggest questions, and flag missing information. Your method becomes systematic without losing flexibility.

## Knowledge that compounds, with a wall between clients

The value grows across the practice, not only within one engagement. After ten clients in one industry, your records show patterns: common objections, typical timelines, frequent pitfalls. Each new engagement starts faster.

Senior consultants carry that pattern knowledge in their heads. The files make it explicit.

Pattern knowledge must never carry one client's confidential facts into another client's work. Write cross-client lessons in a separate `patterns/` file, stripped of names, figures, and anything under a nondisclosure agreement. A stripped entry can read: "Phase 2 operations leads resist system change until one process fix shows a result. Seen in three distribution engagements, 2024 to 2026." It carries no client name, figure, or document title. Keep each client folder closed to other client work. The method is in [separate client context before an agent touches the work](/articles/separate-client-context-before-agent-work). A firm with several staff on shared accounts can use the fuller controls in [how to build an agency brain that retains client context](/articles/agency-brain-retains-client-context).

## Test the files before a client meeting

Run three checks in a fresh session.

1. Ask for the last steering committee decision on ENG-042. Pass: the answer cites the dated minutes. Fail: it paraphrases from general knowledge.
2. Ask for the open items. Pass: the pricing exceptions request appears with its date. Fail: it is missing.
3. Ask a question about ENG-042 while another client's folder is open. Pass: the assistant asks which client you mean. Fail: it mixes the two.

A fail points to a missing line in the client file or a missing rule in `CLAUDE.md`. Fix the file, then run the check again.

## Client data

Consultants hold sensitive client information, and the concern about AI tools is legitimate.

Claude Code runs on your computer, but it sends prompts and model outputs to the model provider over the network. [Claude Code: Data usage](https://code.claude.com/docs/en/data-usage) A client file that the assistant reads is part of that traffic. The same page states, as of 2026.09.25, that Anthropic does not train models on content sent under commercial terms. Consumer plans let the user choose. Retention periods differ by account type.

Check your engagement letters and nondisclosure agreements before client material enters any AI tool. Use a commercial account when your contracts require it. Keep restricted data, such as personnel files or deal terms, in the client's own systems and cite it by reference.

## The arithmetic

You can keep using AI the way many consultants do. Explain the client situation at the start of each session. Paste sections from earlier documents. Spend more time supplying context than receiving value.

Run the numbers for your own practice. Suppose context setup takes fifteen minutes per session and you run ten sessions a week. That is 150 minutes a week, or about eleven hours a month, spent briefing the assistant. Multiply by your hourly rate to see the opportunity cost.

The files take hours to build. Single-session tools do not fit multi-month engagements. A maintained engagement record does. Coaches face the same problem with a different rhythm; see the [coaching version of this setup](/articles/ai-for-coaches).

----

```text
                  .|########||.                                       .|########||.                                       .|########||.
               |##||.      .||##|.                                 |##||.      .||##|.                                 |##||.      .||##|.
             |#|.              .|#|.                             |#|.              .|#|.                             |#|.              .|#|.
           |#|                    |#|                          |#|                    |#|                          |#|                    |#|
         .#|                        |#.                      .#|                        |#.                      .#|                        |#.
        .#.                          .#|                    .#.                          .#|                    .#.                          .#|
       |#.                            .#|                  |#.                            .#|                  |#.                            .#|
      |#             ......             #|                |#             ......             #|                |#             ......             #|
     .#           ||#########|           #|              .#           ||#########|           #|              .#           ||#########|           #|
    .#.         |######||######|.        .#.            .#.         |######||######|.        .#.            .#.         |######||######|.        .#.
    #.        .##|###|##|#|######|        .#            #.        .##|###|##|#|######|        .#            #.        .##|###|##|#|######|        .#
   ||        |##|#||||||||||||#||#|        ||          ||        |##|#||||||||||||#||#|        ||          ||        |##|#||||||||||||#||#|        ||
   #        |#||||||||||||||||||||#|        #.         #        |#||||||||||||||||||||#|        #.         #        |#||||||||||||||||||||#|        #.
  ||       |#||||||||||||||||||||||#|       ||        ||       |#||||||||||||||||||||||#|       ||        ||       |#||||||||||||||||||||||#|       ||
  #       .#||||||||||||||||||||||||#|       #        #       .#||||||||||||||||||||||||#|       #        #       .#||||||||||||||||||||||||#|       #
 ||   ....|||#||||||##|#|||#|#||##||||....|. ||      ||   ....|||#||||||##|#|||#|#||##||||....|. ||      ||   ....|||#||||||##|#|||#|#||##||||....|. ||
 #.  .  ....|#  ....#|||   ||| .#|||  ....#. .#      #.  .  ....|#  ....#|||   ||| .#|||  ....#. .#      #.  .  ....|#  ....#|||   ||| .#|||  ....#. .#
 #   .  ||||#| .#####||  . .#| .#|||  ||||#   #.     #   .  ||||#| .#####||  . .#| .#|||  ||||#   #.     #   .  ||||#| .#####||  . .#| .#|||  ||||#   #.
.|   |||||  #. |#|||||. ||  #. |#||. .|||||   ||    .|   |||||  #. |#|||||. ||  #. |#||. .|||||   ||    .|   |||||  #. |#|||||. ||  #. |#||. .|||||   ||
||   |....  #. ....|#.      |. ...|. ....||   ||    ||   |....  #. ....|#.      |. ...|. ....||   ||    ||   |....  #. ....|#.      |. ...|. ....||   ||
#.  .||||||##||||||##||####|||||||#||||||#|   .#    #.  .||||||##||||||##||####|||||||#||||||#|   .#    #.  .||||||##||||||##||####|||||||#||||||#|   .#
#    .||####|###########################|.     #    #    .||####|###########################|.     #    #    .||####|###########################|.     #
#      .#||||||.#.|| # |. ..# #| #|||||#|      #    #      .#||||||.#.|| # |. ..# #| #|||||#|      #    #      .#||||||.#.|| # |. ..# #| #|||||#|      #
#      .#|||||| ..  |# ## |#| ...#|#|||#|      #    #      .#|||||| ..  |# ## |#| ...#|#|||#|      #    #      .#|||||| ..  |# ## |#| ...#|#|||#|      #
#      .#|||#|# .# .#| #| ##|.#..#|||||#|      #    #      .#|||#|# .# .#| #| ##|.#..#|||||#|      #    #      .#|||#|# .# .#| #| ##|.#..#|||||#|      #
#      .#||||||############|######|||||#|      #    #      .#||||||############|######|||||#|      #    #      .#||||||############|######|||||#|      #
#   |...||#||||||#||||#|#||||||#|||||#||| |.|  #    #   |...||#||||||#||||#|#||||||#|||||#||| |.|  #    #   |...||#||||||#||||#|#||||||#|||||#||| |.|  #
#. .. ||||# .|||##|.  |#| .|| || .|||#. #|  # .#    #. .. ||||# .|||##|.  |#| .|| || .|||#. #|  # .#    #. .. ||||# .|||##|.  |#| .|| || .|||#. #|  # .#
|| |  ...||  ...##| |  #| .|. |. #####  .. .| ||    || |  ...||  ...##| |  #| .|. |. #####  .. .| ||    || |  ...||  ...##| |  #| .|. |. #####  .. .| ||
|| ||||| || ||||#|  .  |. |. |#. ||||| |#| || ||    || ||||| || ||||#|  .  |. |. |#. ||||| |#| || ||    || ||||| || ||||#|  .  |. |. |#. ||||| |#| || ||
.# |.....#|....|#.||||.|||##.|#|....||.#||.#. #.    .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #.    .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #.
 #.|||||||#############################| ||| .#      #.|||||||#############################| ||| .#      #.|||||||#############################| ||| .#
 ||       ##||#||#||||||#||#||#||#||##.      ||      ||       ##||#||#||||||#||#||#||#||##.      ||      ||       ##||#||#||||||#||#||#||#||##.      ||
  #       .#|||||||||#||#|||||||||||#|       #        #       .#|||||||||#||#|||||||||||#|       #        #       .#|||||||||#||#|||||||||||#|       #
  ||       |#||||||||||||||||||||||#|       ||        ||       |#||||||||||||||||||||||#|       ||        ||       |#||||||||||||||||||||||#|       ||
  .#        |#||||||||||||||||||||#|        #.        .#        |#||||||||||||||||||||#|        #.        .#        |#||||||||||||||||||||#|        #.
   ||        |#||||||||||||||||||#|        ||          ||        |#||||||||||||||||||#|        ||          ||        |#||||||||||||||||||#|        ||
    #.        .######|#|#########|        .#            #.        .######|#|#########|        .#            #.        .######|#|#########|        .#
    .#.         |#####||||#####|         .#.            .#.         |#####||||#####|         .#.            .#.         |#####||||#####|         .#.
     |#           ||########||           #.              |#           ||########||           #.              |#           ||########||           #.
      |#             ......             #|                |#             ......             #|                |#             ......             #|
       |#.                            .#|                  |#.                            .#|                  |#.                            .#|
        |#.                          .#.                    |#.                          .#.                    |#.                          .#.
         .#|                        |#.                      .#|                        |#.                      .#|                        |#.
           |#|                    |#|                          |#|                    |#|                          |#|                    |#|
            .|#|.              .|#|.                            .|#|.              .|#|.                            .|#|.              .|#|.
               |##||.      .||##|                                  |##||.      .||##|                                  |##||.      .||##|
                 .||########||.                                      .||########||.                                      .||########||.

Scale With Search  2026  [scalewithsearch.com](https://scalewithsearch.com)
```
