--- title: "Build rep and pipeline files so AI coaching fits each rep on your team" description: "Keep rep performance, pipeline stages, buyer profiles, and talk tracks in files so Claude coaches reps and drafts follow-ups from your own process." canonical: "https://scalewithsearch.com/articles/ai-for-sales-managers" 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) # Build rep and pipeline files so AI coaching fits each rep on your team. You manage eight reps. Three are well above quota. Two are stuck in discovery. One keeps losing deals at the demo stage. Two are new and need a talk track for every objection. You ask an AI assistant, "How should I coach Sarah on her pipeline?" It gives generic advice about discovery questions and follow-up cadence. It does not know Sarah, her win rate, her average deal size, or where her deals stall. So you export her CRM data, paste it in, explain her trend, and list last month's lost deals with reasons. Now the advice is useful. Tomorrow you coach a different rep, and the assistant has forgotten Sarah. You start over. A sales manager does not need general sales advice. You need an assistant that starts from your team, your pipeline, and your process. ## Why a generic assistant cannot coach your team ChatGPT does not know your reps. It does not know your ideal customer profile, your sales process, your objection framework, or what separates your top performers from the rest. A sales manager holds all of this at once: - rep performance: quota, win rate, average deal size, pipeline velocity; - pipeline stages and what moves a deal forward at each one; - prospect profiles: company size, industry, pain points, decision-makers; - talk tracks that work and talk tracks that fail; - objection responses by buyer type; - CRM data that should inform coaching but sits in exports and spreadsheets. When you ask for help, the assistant has none of it. It cannot coach, because it does not know what good looks like on your team. It cannot judge a deal, because it does not know your process. The model is capable. It is uninformed. ## What the assistant needs to know Your reps and their patterns. In a synthetic team: Sarah is strong at discovery but loses deals at the price conversation. Mike closes fast, but his average deal size is 40 percent below target. Emma, a new hire, needs support with objection handling. Your pipeline stages. What happens at discovery, demo, proposal, and negotiation. What moves a deal forward, what stalls it, and what kills it. Your ideal customer profile. Company size, industry, tech stack, decision-makers, and the shape of the buying committee. The assistant should know if a prospect fits before you ask. Your talk tracks. The discovery questions that uncover budget. The demo flow that leads to a next step. The objection responses that work. What works and what does not. On this team, top performers ask about integration requirements in the first call. Low performers skip discovery and jump to the demo. Coaching advice should start from that pattern. ## Six context files Put each kind of knowledge in its own Markdown file in one folder. Claude Code reads `CLAUDE.md` at the folder root when you start it there. Use `CLAUDE.md` to name the six files and when to read each one. - `team-performance.md`: each rep's quota, win rate, average deal size, pipeline value, strengths, struggles, recent wins and losses, and coaching focus. - `sales-process.md`: pipeline stages, exit criteria, conversion rates between stages, average time in each stage, and common stall points. - `icp-enterprise.md`: the enterprise buyer profile, pain points, and decision process. - `icp-smb.md`: the small-business buyer profile, its different pain points, and its shorter sales cycle. - `talk-tracks.md`: discovery questions by buyer type, demo flow and proof points, objection responses, closing steps that work, and follow-up cadence. - `pipeline-current.md`: active deals, stage, next step, and risk factors. A synthetic entry in `team-performance.md`: ```text ## Sarah (AE, mid-market) source:: CRM export 2026-09-19, last two quarters win_rate:: 22 percent (team median 27 percent) stall_point:: negotiation; 4 of 6 losses cite price strength:: discovery calls score highest on the team coaching_focus:: value summary before the price conversation reference_track:: talk-tracks.md > "price objection, mid-market" last_review:: 2026-09-12 ``` Take the numbers from a CRM export, not from memory. Record the export date in each section, so a reader can see how old each figure is. ## Coaching, before and after Before. You ask, "How do I coach Sarah on her pipeline?" The answer covers discovery and follow-up in general terms. You paste her data, explain that she loses deals at the price conversation, and list the three deals she lost this month. Then the answer is relevant. Tomorrow you coach Mike and repeat the whole process. After. You ask the same question. Claude reads `team-performance.md` and sees Sarah's pattern: losses at the price conversation. It reads `sales-process.md` for your negotiation stage. It reads `talk-tracks.md` and suggests the price-objection track that your top performers use. The first answer is one you can act on. Next question: "Draft a follow-up email for Mike's enterprise prospect." Claude reads Mike's entry for his style and `icp-enterprise.md` for the buyer. The draft uses the right tone and the right call to action. You do not re-explain performance. You do not paste CRM exports into the chat. You ask the question, and you check the answer against the rep's record. ## A week with the files A synthetic sales manager at a B2B software company sets up the six files in one afternoon. When he asks for coaching advice, Claude knows the rep, the rep's pattern, and what has worked for others. When he asks for prospect research, Claude knows the customer profile and which questions matter. When he asks for help with a talk track, Claude starts from the tracks that already win. Each Friday, he updates `team-performance.md` from a new CRM export: wins, losses, and changes in each rep's pattern. He updates `pipeline-current.md` with deal progress. The answers improve because the records improve. The model itself does not learn between sessions. The files become shared records. New reps read them during onboarding. Claude reads them for coaching. The VP of Sales reads them before pipeline reviews. ## What you can ask for With the files in place, you can ask Claude to: - coach a rep from that rep's actual pattern; - review a deal against your stages and your customer profile; - draft prospect research, follow-up emails, and objection responses from your talk tracks; - find patterns across the pipeline, such as why deals stall and where new reps struggle. Each weekly update makes the next answer more accurate. [What context an agent should read](/articles/what-context-should-an-agent-read) shows how to keep each question to the smallest set of files that answers it. ## Test the files on a review you already gave Before you trust the files, test them on a coaching conversation you already had. Pick one rep review from last month where you know the right advice. Start a new session and ask the same coaching question, with no pasted data. Compare the answer with what you told the rep. The test passes when the answer names the same stall point and the same talk track. It fails when the advice fits any rep on any team. A failure points to a missing line in `team-performance.md`, such as a stall point you know but never wrote down. Add the line and ask the same question again. ## Keep the CRM as the source and the rep data private The CRM stays the source of truth for pipeline numbers. The context files hold interpretation: patterns, coaching focus, and the tracks that work. When a number in a file disagrees with the CRM, the CRM wins, and you update the file. [Chat history is not business memory](/articles/chat-history-is-not-business-memory) explains why the file, not the last conversation, must hold that update. Rep performance notes are personnel records. Keep them factual and dated, and limit who can open the folder. The files stay on your computer, but Claude Code sends the text it reads to Anthropic's servers during a session. Check your company's AI policy before you put rep or customer data in the folder. Drafted emails go to prospects only after the rep or you review them. When a draft goes wrong because a talk track is out of date, fix the track in `talk-tracks.md`. The [correction then reaches every later draft](/articles/corrections-become-system-memory). ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```