Reseek
A practitioner's cookbook · all 7 role playbooks live

Claude for your small business — what to do today, this week, this month, this quarter.

Anthropic shipped the menu: 15 prebuilt workflows for finance, ops, sales, marketing, service, and HR. This is the cookbook for it. Seven role playbooks, each with a named weekly ritual, a project template you can fill in an hour, twelve copy-paste prompts, one integration walked through end-to-end, and the L4 sketches you should aim at — including the ones you shouldn't build yet. Written for the owner running the place, not the consultant selling the transformation.

84 prompts. 7 downloadable project templates. 7 walked integrations. No fake case studies, no consultant-bait frameworks.
In this cookbook: 01 Owner → 02 Ops → 03 Marketing → 04 Sales → 05 Service → 06 Finance → 07 HR →
Section 1 — The maturity ladder

Four levels. Most businesses jump too far, too fast.

Every role below sits on the same ladder. The biggest mistake we see: a business reads about autonomous agents (Level 4) and tries to build one before anyone in the company has spent a week on Level 1. Walk up the rungs.

LEVEL 1

Conversational

Open Claude. Paste a contract, a CSV, a customer email. Ask questions, draft outputs. No setup, no integrations.

SetupNoneValueToday
LEVEL 2

Project context

Use Claude Projects. Load your brand voice, SOPs, chart of accounts, customer list once — reuse everywhere. Consistency across the team.

Setup~1 hourValueThis week
LEVEL 3

Integrations

Connect QuickBooks, HubSpot, Canva, Google Workspace, Microsoft 365. Claude operates inside the tools you already use.

SetupA few hoursValueThis month
LEVEL 4

Automation / agents

Scheduled workflows. Autonomous tier-1 handling. Custom MCP servers for your specific data. Always human-in-the-loop on what matters.

SetupHalf a day → weeksValueThis quarter
Section 2 — The seven role playbooks

Pick the hat you wear most. The rest still apply.

In a small business, "roles" are sometimes one person wearing four hats. Read the one that's most you, then skim the others — the patterns repeat. Each playbook has the four levels, one anti-pattern to avoid, and what success looks like in 90 days.

01

Owner / Founder

Deep dive →

You're the bottleneck on judgment. AI doesn't replace your judgment — it gives you a faster way to surface what your judgment should be applied to. The full Owner playbook walks through all of this with copy-paste prompts, a project template, and a wired integration.

L1 — CONVERSATIONAL

Hard things, drafted

  • Difficult-email drafter (firing a vendor, raising prices)
  • 30-page contract → 1-page summary + 5 questions to ask
  • Pre-meeting brief from a LinkedIn URL or website
L2 — PROJECT

"My business" project

  • Team list, brand voice, last 3 P&Ls, top 10 customers loaded once
  • "Draft my Friday all-hands update from this week's notes"
  • "Review this vendor proposal against my normal terms"
L3 — INTEGRATIONS

QuickBooks + calendar

  • Monday-morning cash + week-ahead briefing, auto-generated
  • "What did I spend on contractors last month vs. budget?"
  • End-of-week wins/blockers summary from your calendar + email
L4 — AUTOMATION

Executive dashboard agent

  • Daily 8am Slack DM: cash position, pipeline movement, churn signals
  • Anomaly alerts: "AR aging is 18% worse than 90-day baseline"
  • Quarterly board-prep agent that drafts the deck from your data
Anti-pattern

Using Claude as a yes-man for decisions you've already made. The value is forcing yourself to articulate the question well enough for someone else to engage with it.

90 days from now

You have a weekly "Owner's Hour" ritual, a single "My Business" project everyone on the leadership team can use, and a Monday cash briefing you didn't write.

02

Operations / Office Manager

Deep dive →

Operations is the highest-leverage role for AI in a small business. Every recurring process is a candidate. Start where the same thing happens more than twice a month. The full Operations playbook walks through the SOP Hour ritual, the project template, twelve prompts, and a wired client-onboarding workflow.

L1 — CONVERSATIONAL

Knowledge work, on tap

  • SOP written from a 2-minute verbal description
  • Vendor quote comparison side-by-side
  • Handwritten notes (or whiteboard photo) → structured checklist
L2 — PROJECT

Your playbooks, loaded

  • All SOPs + org chart as a project
  • "New client signed — kick off our onboarding playbook"
  • "This is the third time a customer asked X — what should our SOP say?"
L3 — INTEGRATIONS

Google Workspace / M365

  • Auto-create client folder structure with templated docs
  • Send onboarding emails, schedule kickoff, prep the agenda
  • "Generate this month's status report for every active client"
L4 — AUTOMATION

Vendor / contract agent

  • Flags renewal dates 60/30/7 days out with renegotiation notes
  • Drafts dispute emails when invoices don't match POs
  • Quarterly vendor scorecard: spend, SLA hits, last 3 issues
Anti-pattern

Trying to systematize a process that's still half-figured-out. If you can't write the SOP yourself, Claude can't either — it'll just write a confident-looking wrong one.

90 days from now

Your three most-repeated processes (onboarding, monthly reporting, vendor renewals) each have a documented playbook, a project, and at least one integration doing the boring middle.

03

Marketing

Deep dive →

The role with the most AI hype and the biggest gap between hype and reality. The win is consistent voice and faster iteration — not "AI writes my marketing." The full Marketing playbook walks through the Source Hour ritual, the Brand Voice project, twelve prompts (including one that flags whether your draft sounds like AI), and a quarterly performance-to-calendar workflow.

L1 — CONVERSATIONAL

The content basics

  • One piece of content → eight (LinkedIn, blog, newsletter, email, etc.)
  • Social post drafts from a customer win or product update
  • "Rewrite this for a 7-second attention span"
L2 — PROJECT

Brand voice, captured

  • Your 10 best past posts + voice guide + ICP loaded as a project
  • "Write this in our voice" actually means something now
  • Consistent voice across whoever happens to be drafting
L3 — INTEGRATIONS

Canva + HubSpot

  • Ideate → draft → generate visuals without switching tools
  • "What did our top 5 posts last quarter have in common?"
  • Email campaigns drafted, segmented, A/B set up
L4 — AUTOMATION

Content engine

  • Topic ideas from competitor activity + SEO data, scored against your ICP
  • Month of content drafted in your voice, scheduled, ready to edit
  • Weekly performance digest with one specific recommendation
Anti-pattern

Posting AI-drafted content without editing. Your audience can tell. The lift is in volume × consistency, not "look ma, no hands."

90 days from now

You're shipping 3× the content with the same head count, your voice is more consistent than it was a year ago, and every post starts from a project, not a blank page.

The pre-meeting brief is the gateway drug. Once a salesperson walks into a call with a 90-second AI-generated brief and closes it, they're hooked. The full Sales playbook walks through the Pipeline Hour, the won/lost-deal log project, twelve prompts, the inbound triage workflow, and a full intent-signal outbound pipeline.

L1 — CONVERSATIONAL

Personalization, fast

  • Cold outreach personalized from a LinkedIn or website
  • Pre-call prospect research in 60 seconds
  • Sales call recording → next-step email + CRM notes
L2 — PROJECT

Your ICP, encoded

  • Last 12 won deals + ICP + objection handlers as a project
  • "Score this lead 1–10 against our ICP and tell me why"
  • Persona-specific email templates that actually sound like you
L3 — INTEGRATIONS

HubSpot, native

  • Every new contact auto-enriched on creation
  • Daily "hot leads" digest, ranked, with the suggested next action
  • Proposals drafted from your standard template + the discovery notes
L4 — AUTOMATION

Inbound triage agent

  • Every form fill researched, scored, routed within 5 minutes
  • Pre-meeting brief auto-generated for every booked call
  • Stalled-deal nudge agent: drafts the re-engagement email at day 14
Anti-pattern

Letting Claude write outreach with zero personalization signal. "Hi {{first_name}}, I noticed your company {{company}}…" is what gives AI a bad name. Always pass real context in.

90 days from now

Every booked call has a pre-meeting brief. Every lost deal gets a 5-line post-mortem. Your CRM hygiene is the best it's been in 3 years — because Claude is doing the typing.

05

Customer Service

Deep dive →

The role with the clearest ROI and the highest stakes. A bad AI answer to a real customer is a real problem. Move slow on autonomous; move fast on draft-assist. The full Customer Service playbook walks through the Service Hour, the project template, twelve prompts, the help-desk draft-assist workflow, and the careful path to a tier-1 agent.

L1 — CONVERSATIONAL

Drafts, summaries, translations

  • Reply drafts to common questions (always reviewed)
  • 20-message thread → 4-bullet summary for handoff
  • On-the-fly translation for non-English-speaking customers
L2 — PROJECT

FAQ + tone, unified

  • Product docs + FAQ + tone guide as a project
  • Consistent voice no matter who's on the keyboard
  • "This ticket — what does our policy actually say?"
L3 — INTEGRATIONS

Help desk, augmented

  • Suggested reply on every ticket (the agent sends, after a read)
  • Weekly sentiment + top-issue summary
  • "Which 5 customers should I call this week?"
L4 — AUTOMATION

Tier-1 agent (with care)

  • Handles password resets, order status, hours, return policy
  • Escalates anything ambiguous with full context attached
  • Logs every interaction; weekly review for drift
Anti-pattern

Turning on a tier-1 agent without a weekly transcript review. Drift is inevitable. The review is the entire control loop — skip it and you'll find out the hard way.

90 days from now

Average first-response time is cut in half. Your team is spending the saved time on the 20% of tickets that actually need a human, not the 80% that don't.

06

Bookkeeper / Finance

Deep dive →

QuickBooks integration is the headline. The real value is something quieter: a chart of accounts that's coded consistently across the whole team, every month, forever. The full Finance playbook walks through the Variance Hour, the project template, twelve prompts, a month-end close assistant, and the careful path to a cash-optimization agent.

L1 — CONVERSATIONAL

The small wins

  • "Categorize this CSV of transactions"
  • Translate an IRS notice into plain English + your next 3 steps
  • Draft a past-due-invoice email that's firm but not aggressive
L2 — PROJECT

Chart of accounts, codified

  • COA + categorization rules + last 12 months loaded as a project
  • "Code these receipts using our rules, flag anything ambiguous"
  • Consistent coding across whoever happens to be doing the books
L3 — INTEGRATIONS

QuickBooks, native

  • Month-end close assistant (reconciliations, accruals checklist)
  • AR aging review with draft chase-emails ready to send
  • Weekly 13-week cash forecast, updated automatically
L4 — AUTOMATION

Daily cash + anomaly agent

  • Cash position by 7am every day
  • AP anomaly detection: "this invoice is 23% above 6-month average"
  • Quarter-end variance commentary drafted from the numbers
Anti-pattern

Trusting AI-categorized transactions without spot-checks for the first 60 days. Your COA rules have edge cases you don't know about until Claude finds them — for better and worse.

90 days from now

Month-end close takes 40% less time. Your cash forecast is updated weekly, not "when we get around to it." You catch one anomaly per month that you'd have missed.

07

HR / People Ops

Deep dive →

A 12-person company doesn't have an HR department, but it has 100 hours a year of HR work. AI doesn't replace that work — it makes the owner stop avoiding it. The full HR & People playbook walks through the People Hour, the project template, twelve prompts, an offer-to-onboarding workflow, and the explicit lines AI must never cross with people.

L1 — CONVERSATIONAL

The HR basics

  • Job description from a 90-second voice memo
  • Interview question list for any role
  • Performance review template + delivery scripts
L2 — PROJECT

Handbook as substrate

  • Employee handbook + culture docs + comp bands as a project
  • "Is this situation covered by our handbook?"
  • Consistent voice across every employee-facing doc
L3 — INTEGRATIONS

Calendar + Docusign + Workspace

  • Offer letter generated, sent for signature, calendar scheduled
  • Onboarding doc set + accounts + first-week calendar in minutes
  • Exit interview summary across the whole year
L4 — AUTOMATION

Lifecycle agents

  • Resume triage against the job description, ranked + reasoned
  • 30/60/90-day check-in orchestrator (and follow-up drafter)
  • Anonymous monthly sentiment summarizer from a 3-question pulse
Anti-pattern

Using AI in employee-facing communication without disclosure. Trust is the only HR asset that matters. "Claude helped me draft this — here are my actual thoughts" is fine. Stealth AI is not.

90 days from now

Hiring loops are tighter, onboarding is the same every time, and your handbook is actually used — because you can ask it questions in plain English.

Section 3 — The five principles

The voice in your head when the playbooks aren't enough.

Playbooks are scaffolding. Once you've climbed past them, these are the principles that separate the businesses getting compounding leverage from the ones getting a 1.2× typing bump.

01

The Owner's Hour

Block 60 minutes every Friday. Use Claude on the single most important question of the week — not email drafts. Pricing review, churn analysis, a hard conversation you've been postponing, vendor renegotiation prep.

This is the practice that converts AI-curious owners into AI-leveraged owners. The output isn't a deliverable. It's that you actually thought hard about the thing you've been avoiding.

02

What NOT to use Claude for

Legal advice you'll act on without a lawyer. Medical decisions. Tax positions with real exposure. Anything where a wrong answer costs more than verifying it would.

Claude is great at drafting the question, terrible at being the final answer for high-stakes regulated work. Use it to prepare for the conversation with the professional, not to skip the professional.

03

The honest stack

Most small businesses don't need a multi-agent system or a custom MCP server. They need somebody to set up four integrations, write seven good prompts, and create three Claude Projects.

If a consultant's first move is "let's build you an agent," they're optimizing for their invoice, not your business. The right first move is almost always Level 2.

04

Verify what matters, trust what doesn't

Anything that leaves your business — to a customer, the IRS, a contract counterparty, a regulator — gets verified. Anything internal, anything in draft, anything you'd edit anyway — trust and move.

Without this rule, owners either trust nothing (and get zero leverage) or trust everything (and have an incident). The rule is liberating once you internalize it.

05

Human-in-the-loop, on purpose

Anthropic built Claude for Small Business around "Claude proposes, owner approves." That's not training-wheels for beginners — it's the right architecture for almost every workflow in a 50-person company.

The point of automation isn't to remove yourself from the loop. It's to remove yourself from the boring parts of the loop, so your judgment shows up where it actually matters.

06

One change at a time

Don't roll out Claude to sales, marketing, finance, and customer service in the same month. Pick one role. Get it to Level 2. Measure something. Then add the next.

Patience wins this. A half-working workflow rolled out across four roles produces four sets of frustrated users; a fully-working one in a single role produces a believer who pulls the rest of the team along.

Section 4 — Your 30-day starter plan

Specific, sequenced, and small enough to actually do.

If you do these four weeks, you'll be ahead of 90% of small businesses experimenting with AI right now. The trick isn't the prompts. It's not skipping a week.

WEEK 1 — L1

Just use it.

  1. Subscribe to Claude (one seat, your seat).
  2. Use it daily for the work you'd otherwise do alone — 3 real things, not toy examples.
  3. Note what worked and what didn't, plain text, somewhere you can find it.
WEEK 2 — L2

Build one Project.

  1. Pick one role (start with marketing or ops).
  2. Load context: brand voice, top 5 past outputs, SOP, ICP — whatever applies.
  3. Run last week's tasks through the project. Notice the difference.
WEEK 3 — L3

Wire one integration.

  1. Pick the system you're already in every day (QuickBooks, HubSpot, Google).
  2. Connect it, run 5 real queries against your real data.
  3. One new person on the team gets a seat. Their pick.
WEEK 4 — REVIEW

Decide what survives.

  1. What saved real time? Keep doing those.
  2. What was a novelty? Drop it without guilt.
  3. One automation goes on the L4 list — for next quarter, not next week.
Section 5 — When to call Reseek

Be honest about which side of the line you're on.

A consultant publishing the list of things you should do yourself is counterintuitive — which is exactly why we do it. If you're on the left column, you don't need us. If you're on the right, the 30-minute call is free.

Do this yourself

  1. Subscribe to Claude and use it daily for two weeks.
  2. Build your first Project with brand voice + a few SOPs.
  3. Wire one obvious integration (the one you live in).
  4. Take Anthropic's free AI Fluency for Small Business course.
  5. Pick one role to get to Level 2 before adding others.
  6. Run the 30-day plan above. Don't skip weeks.
  7. Read our cheat sheet for the prompting basics.

This is where help pays

  1. Designing a tier-1 service agent that handles real customers without a brand-damage incident.
  2. Connecting Claude to your specific data (custom MCP, internal API, the weird database your business actually runs on).
  3. Rolling AI across a team of 10+ without it fizzling at month two — the org change is harder than the tool.
  4. Untangling a stalled AI initiative someone else (or a vendor) sold you on six months ago.

The menu isn't the meal. The cookbook is the meal.

Anthropic gave you Claude. We give you the cookbook for your specific kitchen. Start with the 30-day plan. If you stall, the call is free and direct — no pitch, no deck.

Re-open the 30-day plan → Book a 30-min call