>_
solutionAIry
Free field guide · Keep it, use it, share it

The AI Advantage Field Guide

How to put Claude to work — what to hand it, how to ask, and how to get hours of your week back. No jargon, no hype, just what works.

a gift from Solutionairy — no signup, no catch
01 · Why this is worth 20 minutes

The people using AI at work aren't smarter. They started sooner.

A few numbers from real research — not vendor promises — on what's actually happening:

76%
of small businesses now use AI — and 93% of those report a positive impact (Goldman Sachs survey, Feb 2026)
2.2 hrs
saved per week by the average AI-using worker; a third of daily users save 4+ hours (St. Louis Fed)
40% faster
on professional writing tasks, with higher quality, in a controlled MIT study
+10%
better results for experienced users vs. beginners on the same tasks — skill with AI is itself a skill (Anthropic Economic Index)

Two more things the research shows. First, this isn't a coding tool anymore — around 90% of what people delegate to Claude's agent mode is ordinary office work: documents, reports, email, analysis, planning. Second, there's a learning curve, and it compounds: people who've used AI for six months get measurably better results than people who started last week. The advantage isn't access — everyone has access. The advantage is reps. This guide is designed to get you your first reps this week.

02 · The mindset

Four mental models that do most of the work

Most people fail with AI not because of bad prompts, but because of the wrong picture in their head. Fix the picture first.

Model 1

It's a brilliant new hire with zero context. Anthropic's own advice: treat Claude like a talented employee on day one. It doesn't know your business, your customers, or your standards until you tell it. The more context you give, the better it performs — same as any new hire.

Model 2

Its skills are jagged, not uniform. AI is startlingly good at some hard things and surprisingly bad at some easy ones — researchers call this the "jagged frontier." You can't know which side a task falls on until you try it. So try it on everything low-stakes, and keep score.

Model 3

You are the human in the loop. AI drafts, you decide. It can sound confident while being wrong, so anything with your name on it gets your eyes before it goes out. You're not being replaced as the judge — you're being freed up to only be the judge.

Model 4

Delegate outcomes, not keystrokes. Don't micromanage sentence by sentence. Describe the finished thing you want — "a one-page proposal my client can say yes to" — and let it work. But only delegate outcomes you're able to check.

The 3-question filter: what to hand over vs. keep

Q1
Can I check the result faster than doing the work? A draft email: 30 seconds to check, 15 minutes to write. Perfect delegation. If you can't verify it, don't delegate it.
Q2
What does a mistake cost? Brainstorm, draft, internal summary → delegate freely. Client-facing numbers, legal language, anything irreversible → AI drafts, you verify line by line.
Q3
Is it volume or judgment? Repetitive, high-volume, format-shuffling work → AI's sweet spot. Relationships, taste, and final calls → yours. That division is the whole game.
03 · The menu

What Claude can take off your plate this week

Nine categories of everyday work. Each one opens with real examples and a copy-paste prompt to try — tap a category, copy a prompt, paste it into Claude, fill in your details.

  • Routine replies — paste the incoming email, get a reply in your tone in seconds.
  • Invoice chasing — a personalized reminder for every overdue invoice, ranked by amount.
  • Voice-note to polished — dictate a rambling brain-dump; get a clean, structured message.
  • De-escalation — "make this firm but professional" before you send something you'd regret.
Try this
Here's an email I received: [paste it]. Draft a reply that politely declines the discount request but keeps the relationship warm. Under 120 words, friendly-professional. Give me two versions: one warmer, one firmer.
  • Proposal from call notes — feed your meeting notes and services list; get a structured first draft.
  • Contract plain-English — upload a contract or lease; get obligations, deadlines, and red flags. (Verify before signing.)
  • One thing → many formats — one case study becomes a one-pager, a deck outline, and a LinkedIn post.
Try this
You're my proposal assistant. Using these call notes [paste] and my service list [paste], draft a one-page proposal with: the client's problem in their own words, my recommended solution, timeline, a price section left blank for me, and clear next steps.
  • "Explain my numbers" — upload your sales CSV; get trends, top customers, and anomalies in plain English.
  • Clean messy data — dedupe, fix inconsistent names and dates, merge sheets.
  • Build a tracker — job tracker, cash-flow forecast, or inventory sheet with working formulas, from scratch.
Try this
Here's a copy of my sales data [attach a copy, not the original — and remove customer names if you don't need them]. Tell me: the monthly trend, my top 5 customers by revenue, my weakest month, and anything unusual I should look at. Explain it like I'm not a data person, then give me one chart worth sharing.
  • Transcript → decisions — paste any meeting transcript; get the summary, decisions, and action items with owners.
  • Pre-meeting brief — "summarize everything about this client and give me 5 smart questions."
  • The recap email — drafted before you're back at your desk.
Try this
Here's a meeting transcript [paste]. Give me: a 5-bullet summary, decisions made, action items with owners and deadlines, and a draft recap email to attendees that's short enough people will actually read it.
  • Vendor shootouts — compare tools, suppliers, or software on price, terms, and fit, in a table.
  • Regulation digests — "which parts of this new rule actually apply to my business?"
  • Prospect prep — a one-page brief on any company before you walk into the room.
Try this
Compare [Tool A], [Tool B], and [Tool C] for a 5-person [industry] business: monthly cost, key features, contract lock-in, and best fit for us and why. Table format. Flag anything you're not certain about instead of guessing.
  • Review replies — on-brand responses to Google/Yelp reviews, good and bad, in minutes.
  • FAQ from your inbox — feed 20 answered customer emails; get a reusable answer library.
  • Research note: support teams with an AI assistant resolved 14% more issues per hour — and the newest staff improved 34% (NBER study).
Try this
Draft a reply to this 2-star Google review [paste]: apologetic but not groveling, offers to make it right, under 80 words, sounds like a real person and not a corporation.
  • Month of posts from one brain-dump — 20–30 posts in your voice, organized by theme.
  • Campaign planning — find your weakest revenue month and build the promo to fix it.
  • Repurposing — every blog post becomes emails, captions, and a short script.
Try this
You're the social media manager for [business] in [town]. From this brain-dump [paste], write 12 posts for the next month: 4 educational, 4 promotional, 4 behind-the-scenes. Match the voice of this past post: [paste one you liked].
  • Job posts that sound human — plus screening questions that reveal reliability.
  • Resume shortlists — paste resumes and your must-haves; get a ranked list with reasons.
  • The docs you keep postponing — onboarding checklists, handbooks, review templates.
Try this
Write a job post for a part-time [role] at [business]. Requirements: [list]. Tone: warm, zero corporate jargon. Then give me 5 interview questions that reveal reliability and 3 red flags to listen for.
  • Weekly triage — dump everything on your plate; get it sorted into do / schedule / delegate / drop.
  • Decision support — "argue both sides of this, then tell me what you'd need to know to decide."
  • The morning brief — with scheduled tasks (see Level 5 below), this can run itself daily.
Try this
Here's everything on my plate this week [dump the list, messy is fine]. Sort it into: do today, schedule, delegate, drop. Then draft a realistic Mon–Fri plan with the top 3 priorities each day, and tell me which one thing matters most.
04 · The skill

How to ask: six rules that fix 90% of bad results

Anthropic's golden rule: if a colleague reading your request would be confused, Claude will be too.

R1

Brief it like a freelancer, not a search engine.

Give the audience, the purpose, the format, and the length. Vague in, generic out.

"write about our services" → "write a 100-word intro for homeowners who've never hired a landscaper, warm tone, end with one question"
R2

Explain the why, not just the what.

Claude generalizes from reasons. "This is for a nervous first-time client, so keep it reassuring" beats a list of ten formatting demands.

R3

Show one example of "good."

Paste a past email, proposal, or post you were proud of and say "match this style." One good example outperforms three paragraphs of description.

R4

Treat it as a conversation, not a slot machine.

The first draft is the starting point. "Shorter." "More casual." "Give me 3 options." "You missed X." Iterating two or three times is how it's supposed to work — correction is the core skill.

R5

Say what you want, not what you don't.

"Write in flowing paragraphs" works better than "don't use bullet points." Positive instructions aim; negative ones just fence.

R6

Give it permission to say "I don't know."

Add "if you're not sure, say so instead of guessing" to anything factual. It measurably reduces made-up answers — and tells you where to double-check.

One more that beats all six on big tasks: ask Claude to ask you questions first. "Before you start, ask me anything you need to know to do this well." It surfaces the context you forgot you had.

05 · The ladder

Five levels: from chatting to delegating

Most people stay on Level 1 forever. Each step up saves more time than the last — climb one level at a time, as your trust is earned.

LV 1

Chat

Ask questions, draft text, think out loud. Where everyone starts — and where copy-paste answers live.

LV 2

Reusable prompts

When a prompt works, save it. A note file of your five best prompts is a real business asset — you're building your own playbook.

LV 3

Projects — context that sticks

A Project is a workspace where Claude permanently knows your business: upload your services, prices, tone examples, and standing instructions once. Every chat inside starts already briefed. This is the single biggest upgrade most people never make.

LV 4

Real files, not just text

Claude creates actual working files: Excel spreadsheets with live formulas, Word docs, PowerPoint decks, PDFs. Stop copy-pasting into documents — ask for the document.

LV 5

Cowork — delegate whole tasks

Claude Cowork (paid plans) works like a colleague, not a chatbot: it plans multi-step work, works with entire folders of files, and keeps going after you close the laptop. Plus scheduled tasks — a Monday-morning report or daily brief that runs itself. This is where "using AI" becomes "having staff."

Level 3 starter — paste into a new Project's instructions
You're an assistant for [business name], a [what you do] in [where]. Our customers: [who]. Our tone: [3 words — e.g. warm, plain-spoken, confident]. Our services and prices: [list]. When drafting anything, match the tone, keep it concise, and ask me clarifying questions before big tasks. If you're unsure of a fact, say so.
06 · The guardrails

Trust, but verify — the habits that keep you safe

AI's most dangerous errors aren't the dumb ones — they're the polished, confident, plausible ones. A few habits neutralize the risk.

The verification habits

  • Match scrutiny to stakes. Anything leaving your desk — client numbers, legal claims, names, prices — gets your eyes first. Internal brainstorms don't need the same rigor.
  • The more polished it sounds, the more deliberately you check. Fluency is not accuracy.
  • Ask "what are you unsure about?" — Claude will usually tell you exactly where to look.
  • Get a second opinion. Paste the same material into a fresh chat and compare answers on anything high-stakes.
  • Never paste what you wouldn't email. Leave out customer SSNs, health details, and anything you don't actually need in the prompt.

Protect your data: the copy-first rule

  • Work on a copy, never the original. Before uploading a spreadsheet, contract, or client list, duplicate it first ("Save As → copy"). Your original stays untouched no matter what — and you can compare before/after.
  • Swap out what identifies people. If the task doesn't need real names, account numbers, or addresses, replace them first — "Customer A," "Client 2" — or delete those columns from your copy. The analysis works the same either way.
  • Paste the relevant part, not the whole thing. Claude only needs the section you're asking about. The three paragraphs in question beat the entire 40-page contract full of other clients' terms.
  • Know your plan's data policy. Business plans (Claude for Work) don't train on your data. Check what your plan says before making customer data part of your routine — 30 seconds of reading, one-time.
  • Back up before you let AI edit files directly. If you graduate to tools that modify files in place (like Cowork), keep backups and start with a dedicated working folder — not your whole drive.

The five beginner mistakes (and the fix)

One vague sentence, then disappointment. Fix: brief it like a person — context, audience, format.
Quitting after one bad answer. Fix: say what was wrong ("too formal, missed X") — the second draft is usually the good one.
Describing your file instead of uploading it. Fix: attach the actual spreadsheet, PDF, or doc. Claude reads files.
Cramming five jobs into one prompt. Fix: chain it — draft first, then edit, then format.
Sending AI text verbatim as your own. Fix: the 2-minute human pass. You own everything that goes out.
07 · The start

Your first week: one small win a day

Don't "adopt AI." Just do one 10-minute experiment a day for seven days. By Sunday you'll know exactly where it fits in your work.

Day 1
Reply to one real email with Claude's help

Paste it in, ask for a reply in your tone. Edit, send. Notice the time.

Day 2
Turn messy notes into a clean document

Any notes — a call, an idea, a plan. "Structure this into a one-pager."

Day 3
Upload a copy of a spreadsheet and interrogate it

Duplicate the file first (copy-first rule), then ask: "What trends do you see? What should worry me? What's my best month and why?"

Day 4
Feed it a meeting transcript or long email thread

Ask for decisions, action items, and the recap message.

Day 5
Rewrite something that matters

A tense reply, a pitch, a difficult message. Ask for three versions, pick the best parts.

Day 6
Set up one Project

Use the Level 3 starter prompt above. Ten minutes now, briefed-in-advance forever.

Day 7
Pick your one weekly workflow

Whichever experiment saved the most time — make it a standing habit. Then add one new use case a month.

That's the whole method: start small, start now, add one use case a month. The research says the learning curve pays off within weeks — and the people who feel most confident about AI's effect on their work are the ones who delegate the most, not the least.