For solo and small personal injury firms
Your paralegal just lost another week to a medical chronology. Again.
On a complex case that’s 20–40 paralegal hours of reading and typing, by one vendor’s estimate. Hours nobody pays for until the case settles, evenings spent matching bills to visit dates, and new cases you can’t take on while the records stack sits on the desk.
The Small Firm AI Kit for PI: one Claude Skill with 17 ready-made playbooks.
- Medical chronologies
- Specials tables
- Demand letter drafts
- One-time payment
- 30-day money-back guarantee
- Works on free Claude
Demand letter, medical narrative and specials (excerpt)
On March 14, 2026, Client A was stopped at a red light when the insured’s vehicle struck her from behind. She was taken to Provider 1’s emergency department the same afternoon, reporting neck pain radiating into the right shoulder (Source p. 4). Cervical X-rays were negative for fracture; she was diagnosed with cervical strain and discharged with a muscle relaxant (p. 7–9).
Over the following ten weeks she treated with Provider 2 (orthopedics) and Provider 3 (physical therapy), completing 18 therapy sessions (p. 41–118). An MRI on April 22, 2026 showed a C5–C6 disc protrusion (p. 63).
Checked before you see it
- Checked: Every chronology row has a source page (47 of 47)
- Checked: Specials total computed with code from the bills, inputs shown
- Flagged: 1 bill line with no matching invoice, marked [NO SOURCE]
If this sounds like your week, keep reading
- It’s 9 p.m. and you’re deep in the orthopedic records, still matching visit dates to the bills by hand.
- The adjuster spots a treatment gap you missed, and it shows up in the offer instead of being answered in your demand.
- Your specials total doesn’t tie to the invoices, and you can’t tell which bill line is wrong.
- A client calls again to ask where the case stands, and the update you owe them gets written late at night, from memory.
Where the hours go
Roughly 18 hours a week go to the same four jobs
The same week with Claude and these playbooks: about 9 hours back
- Today
- With The Small Firm AI Kit for PI
Medical chronologies
Today: 10 h/wkWith The Small Firm AI Kit for PI: 5 h/wkDemand letter drafts
Today: 3 h/wkWith The Small Firm AI Kit for PI: 1.5 h/wkClient updates and time entries
Today: 3 h/wkWith The Small Firm AI Kit for PI: 1.5 h/wkSpecials against the bills
Today: 2 h/wkWith The Small Firm AI Kit for PI: 1 h/wk
Today: ≈18 h a week, ≈864 h a year on this work.
Back in your week, our estimate
≈9 h
Example starting value: $250. Move it to your own number.
- Pro pays for itself after
- ≈24 min
- Time back, each month
- ≈$9,000
How we estimated these numbers
Only part of a small-firm lawyer’s week ever gets billed. A big share of the rest goes to paperwork that repeats on every file. This is a conservative picture for a small PI firm with one case reaching demand every two weeks. If you run more files, your numbers are higher.
- Medical chronologies, 10 h/week: 20–40 paralegal hours per complex chronology (vendor estimate). We took the low end, 20 hours, and assumed one complex case every two weeks.
- Demand letter drafts, 3 h/week: Our estimate: about 6 hours for the facts, medical narrative and damages of one demand, one demand every two weeks. No published figure found.
- Client updates and time entries, 3 h/week: Our estimate: about 36 minutes a working day on status emails and time-entry narratives. No published figure found.
- Specials against the bills, 2 h/week: Our estimate: about 4 hours to tie every bill line to its invoice for one demand, one demand every two weeks. No published figure found.
These are our estimates, not measured results. We assumed every task still needs you: reading the draft, checking rows and figures against the source pages, clearing every [VERIFY] and signing off. So we cut each task by half at most, even where vendors claim more: one says a first-draft chronology takes hours instead of 20–40, and time-capture vendors claim over 90% less time writing time-entry narratives. For comparison, in the 8am 2026 Legal Industry Report 38% of lawyers who use AI say it saves them 1–5 hours a week and 24% say 6 or more.
Week: A standard 40-hour week (our basis). Clio’s 2025 Legal Trends for Solo & Small Firms puts utilization at 27% for solos and 32% for small firms: at those rates only about 11–13 of the 40 hours get billed.. Yearly figures use 48 working weeks, monthly ones 4.
One Skill · 17 playbooks inside
Ask in plain words. Get the document.
One Skill in Claude: you describe the job, its router opens the right playbook, and back comes a draft with a source on every line. These are excerpts of what comes back, built on fictional, anonymized facts.
From a stack of records and bills to tables an adjuster can’t pick apart.
You ask
“Client A, rear-end crash 03/14/2026. 212 pages from Provider 1–3 attached. Build the medical chronology with a page cite on every visit.”
You get
A visit-by-visit table, one source page on every row, gaps flagged.
Playbook: medical-chronology.md · in every plan
personal-injury-lawyers/
├─ SKILL.md
the router: reads your request, opens the right playbook
├─ your profile, saved at setup
└─ playbooks/
├─ citation-guard.md
├─ confidentiality-preflight.md
├─ engagement-letter-ai-clause.md
└─ … 14 more
See all 17 playbooks
In every planBasic · $49
- Every citation flagged before anyone else sees it
citation-guard.md - Client data anonymized before any work starts
confidentiality-preflight.md - Client updates your clients actually read
client-update-writer.md - Time entries clients don’t push back on
billing-narrative-cleaner.md - A visit-by-visit medical chronology with a page cite on every row
medical-chronology.md - A specials table that ties to the bills
specials-bills-table.md - A demand letter draft built from your own chronology and specials
demand-letter-draft.md
Added in ProPro · $99
- An engagement letter with an AI clause, ready in minutes
engagement-letter-ai-clause.md - Interrogatory and RFP response drafts, one set at a time
interrogatory-rfp-responses.md - Deposition summaries you can skim in minutes
deposition-summary.md - A lien summary and settlement distribution letter
lien-settlement-distribution.md - A clean case summary straight from intake
pi-intake-case-summary.md - A negotiation sheet that tracks every offer and counter
negotiation-sheet.md - Records requests and follow-ups for every provider
records-request-tracker.md - Settlement offers explained to your client in plain English
settlement-offer-explainer.md - Adjuster letters that keep the claim moving
adjuster-correspondence.md - A briefing pack for your medical expert
expert-briefing-pack.md
Why not just ChatGPT?
Why not just paste the records into ChatGPT?
Around 70% of solo and small-firm lawyers already use AI (8am 2026 Legal Industry Report; Clio 2026), but only 9% have an AI policy they actually enforce and 54% have had no responsible-AI training (8am). A plain chatbot is fast, but it doesn’t know your file, your court or where its numbers came from. That gap is where the sanctions below come from.
Generic AI
- Fake citations end careers. A solo practitioner in Alabama was ordered to pay $17,200 and barred from filing without a co-signing attorney after briefs full of invalid citations (reported by Platinum IDS, 2026).
- In March 2026 the Sixth Circuit sanctioned Tennessee attorneys for more than two dozen fake or misrepresented citations. In the Middle District of Pennsylvania, AI misuse cost one lawyer a $1,500 fine and a six-month suspension (Platinum IDS).
- Generic chatbots skip provider visits and ICD codes and produce demand numbers with no grounded foundation in the documented bills. That critique comes from EvenUp’s own 2026 guide, a competitor, but it describes the risk accurately.
- A plain chatbot has no idea which state, county or court you are in, and no page references a reviewer can check. The adjuster will find the gaps you missed.
The Small Firm AI Kit for PI
Why this works where a plain chatbot didn’t
- 1
Anonymized before anything starts
Confidentiality Pre-Flight runs first on every task: it offers anonymized mode, swaps names for Client A and Provider 1, and reminds you to use a business plan that doesn’t train on your data.
- 2
Pinned to the page, totalled with code
Medical Chronology puts the source page on every row and flags gaps over two weeks. Specials & Bills Table adds each charge against its invoice with code, and anything without a source is marked [NO SOURCE].
- 3
No invented cases, and your signature last
Citation Guard never generates an authority: it marks every citation [VERIFY] and checks it against your uploads. Every output ends with a verification block, the human checks it needs and a line for your sign-off.
How it works
Set up once. Then just ask.
No coding, no prompts to copy. You install it the way you would add a document to Claude.
- 1
Download the ZIP
Right after checkout you get one ZIP, ready to download on the page: a single Claude Skill for your practice with every playbook in your plan inside. No account, no login, no subscription.
- 2
Upload it to Claude
Add it once in Claude’s settings. After that you just ask for the work: the Skill reads your request and opens the right playbook, so you never pick a file yourself. It runs on every Claude plan, including Free with code execution turned on. For real client files, use a business plan that doesn’t train on your data.
- 3
Answer the 5-minute Firm Profile interview
State, county, court, bar regulator, house style, signature and how you cite sources (page, Bates or exhibit). Saved once and read by every playbook, so no draft starts in the wrong jurisdiction.
Compare your options
What the other options cost
These are the real alternatives a solo or small PI firm has today, at the prices reported for them. None of them is wrong. They are priced for a different firm.
- Outsourced demand service (EvenUp)Reported ~$300 base, often $500–800+ per demand (third-party reports; no public rate card)Priced per case and sold through a demo, built for high-volume firms. EvenUp’s own guide says firms with fewer than 20 light-documentation cases can manage with Claude.
- Legal AI subscription (CoCounsel, Lexis+ AI)CoCounsel ~$220–639 a month; Lexis+ AI ~$128–494 a month on top of Lexis+ (third-party pricing, 2026)Built for legal research and billed every month per user, whether or not you have a demand to write.
- Your paralegal’s hours, or your own20–40 hours per complex medical chronology (vendor estimate)The same table typed by hand on every case, and those hours don’t go to anything else.
- A generic chatbotAbout $20 a monthSpeed without templates, page cites or verification. Records pasted into a consumer account can breach confidentiality.
- Claude’s official legal pluginsFree to install, paid Claude plans onlyNo personal injury plugin and nothing that drafts an engagement letter AI clause.
- The Small Firm AI Kit for PI$49 or $99, once$49 or $99, paid once: about a third of the reported base price of one outsourced demand, and yours for every case after.
Pick your plan
One payment. Yours to keep.
Less than the reported base price of a single outsourced demand, and no monthly bill like a legal AI subscription. One payment, yours to keep.
Pro costs, once
$99
Basic: $49 once
It pays for itself after
≈24 min
of time won back, at $250 for an attorney hour
Get back just 1 hour a month
$250
a month, against a one-time $99. Our estimate is ≈9 h a week.
Break-even = plan price ÷ the hourly value set in “What those hours are worth” above.
Basic
The core kit plus the three PI essentials.
$49one-time
7 ready-made playbooks
Try it on real work. Not for you? Full refund within 30 days.
- 4 core playbooks: Citation Guard, Confidentiality Pre-Flight, Client Update Writer, Billing Narrative Cleaner
- Medical Chronology with page cites and treatment-gap flags
- Specials & Bills Table with totals computed from your bills
- Demand Letter Draft built from your own chronology and specials
- Firm Profile interview: set your jurisdiction and house style once
- Verification block at the end of every output
Pro
The full PI workflow, from intake to settlement.
$99one-time
All 17 playbooks
Only $50 more than Basic: +10 playbooks and the Pro bonuses below.
Try it on real work. Not for you? Full refund within 30 days.
- Everything in Basic
- Interrogatory & RFP Response Drafts
- Deposition Summary
- Lien Summary + Settlement Distribution Letter
- PI Intake → Case Summary
- Negotiation Sheet for offers and counteroffers
- Engagement Letter + AI Clause
- Records Request Tracker for every provider
- Settlement Offer Explainer for your client
- Adjuster Correspondence
- Expert Briefing Pack
- Word templates for your demand letter and medical chronology
- Firm Style Guide: your house style, applied by every playbook
- Sample outputs from every playbook, to compare against your own
- 12 months of fixes and adjustments to the included playbooks
30-day money-back guarantee
Run the kit on a real, anonymized file. If it doesn’t earn its place in your practice within 30 days, email us and we refund every cent. No conditions.
- One-time payment, no subscription
- Works on free Claude
No Claude account yet?
And if I don’t have Claude?
Claude is Anthropic’s AI assistant. The free plan is enough to run The Small Firm AI Kit for PI: creating an account takes a minute, and you don’t need a credit card.
- Free plan works, no subscription needed to start
- Account ready immediately
- Paid plans only add more usage, for when you want it
- 1
Create a free account
Go to claude.ai and sign up with your email, Google or Apple account. It’s free and ready right away.
- 2
Turn on one setting
In Settings → Capabilities, switch on “Code execution and file creation”. Skills need it, and it’s free.
- 3
Upload your package
In Customize → Skills, click “+”, choose “Upload a skill” and select the ZIP you received. Then just ask.
Fair questions
What personal injury lawyers ask before buying
Is it ethical to use AI on client matters?
ABA Formal Opinion 512 doesn’t forbid it. It asks you to understand the tool, verify its output, protect confidentiality (informed consent may be needed), communicate with the client, supervise staff and charge reasonable fees. The kit is built around those duties: an AI clause for your engagement letter, an anonymize-first pre-flight and a human-verification block at the end of every document. It is aligned with the guidance; it doesn’t certify compliance in any state.
Is my client data safe?
Every task starts with Confidentiality Pre-Flight, which offers anonymized mode and swaps names for placeholders like Client A and Provider 1. Use Claude’s Free plan only to try the kit with anonymized or fictional data; for real client files, use a business plan that doesn’t train on your data.
Will it invent cases?
Citation Guard never generates an authority. It extracts every citation in a draft, marks it [VERIFY] and tells you whether it appears in the documents you uploaded. We don’t promise zero errors. We promise every citation is flagged for you to check before you file.
Doesn’t Anthropic already do this?
Claude’s official legal plugins, released in May 2026, focus on commercial, corporate, litigation and similar work. None is built specifically for personal injury, and none drafts an engagement letter AI clause. These playbooks fill that gap and run on Claude’s Free plan, while the plugins need a paid plan. We are independent and not affiliated with Anthropic.
Why not just use a per-case demand service?
If you run high volume, a per-case service may make sense. For firms with fewer than 20 cases and modest records, even EvenUp’s own guide says Claude can be enough. A one-time kit with verification built in is the lighter option.
Built for your rules
Set up for your state’s AI ethics guidance
The Firm Profile records your state, and the playbooks adjust what they remind you to do. ABA Formal Opinion 512 is the baseline everywhere; some states add their own rules on top.
Your setup
Any US state (ABA 512)
The default profile: the duties of ABA Formal Opinion 512 applied to every playbook.
- Engagement letter AI clause covers how AI is used, how it is billed, tool costs and how the client can ask questions
- Confidentiality Pre-Flight reminds you that informed consent may be needed before client data goes in
- Every draft ends with the verification and supervision block 512 expects
- Your state’s own opinion is noted for you to check; the kit doesn’t certify compliance
Guardrails
Verification isn’t a disclaimer. It’s the product.
Every output ends with the same verification block: key statements, the source of each, the items marked [VERIFY], the human checks this document requires and a line for your signature. We never promise zero errors. We promise every citation is flagged for you to check.
Sample verification block
From: Demand letter, medical narrative and specials (excerpt)
- Checked: Every chronology row has a source page (47 of 47)
- Checked: Specials total computed with code from the bills, inputs shown
- Flagged: 1 bill line with no matching invoice, marked [NO SOURCE]
- Verify: Treatment gap May 2–27: confirm the reason with the client
- 01
Citation Guard
No authority is ever generated. Every citation is marked [VERIFY] and checked against your uploads: found in your documents, or NOT FOUND, verify before filing.
- 02
A page cite on every fact
Every chronology row and every figure carries its page, Bates number or exhibit. Anything without a source is marked [NO SOURCE].
- 03
Numbers computed with code
Specials totals, liens and net-to-client run as code with the inputs and assumptions shown, never estimated by a language model.
- 04
Anonymize first
Before any task, anonymized mode is offered and names become Client A and Provider 1. Consumer plans are for trying the kit, not for client files.
- 05
Jurisdiction before anything else
Which state, county and court? Asked once in the Firm Profile and read by every playbook, so drafts start in the right place.
- 06
Mandatory human checks
The chronology against the source pages, every citation and the demand amount: listed at the end of each document for you to check yourself, with space for your sign-off.
- 07
No unreviewed advice to clients
Client updates carry an “Attorney review required before sending” banner. Nothing goes to a client as legal advice without you.
- 08
Disclosure wording when rules ask for it
Suggested AI-use paragraphs for engagement letters and filings, marked as drafts for you to adapt to your local rule.
FAQ
Everything else
Didn’t find your answer? Email us:hello@summonskills.com
What exactly is in the ZIP?
One Claude Skill for your practice. Inside: a router file (SKILL.md) that reads each request and opens the right playbook, one Markdown playbook per job (7 in Basic, 17 in Pro), each with its instructions, templates and verification block, and the Firm Profile interview every playbook reads. Pro also includes the Firm Style Guide inside the Skill, plus a bonus pack: Word templates for the demand and chronology and sample outputs from every playbook. 12 months of fixes and adjustments to the included playbooks are included (new playbooks for future rule changes are not part of that).
Does it work on Claude’s Free plan?
Yes. The Skill runs on every Claude plan, including Free, as long as code execution is turned on. Free is fine for trying the kit with anonymized or fictional facts. For real client files, use a business plan that doesn’t train on your data.
I use ChatGPT. Will this work there?
No. The kit is built as a Claude Skill, and ChatGPT has no equivalent way to install it once and have it open the right playbook for each request. Claude’s free plan is enough to try it, an account takes a minute, and you can keep ChatGPT for everything else.
Which jurisdictions does it cover?
It is built for US personal injury practice. The Firm Profile records your state, county, court and bar regulator, and the playbooks adjust their ethics reminders to ABA Opinion 512 and the state opinions from Texas, Florida and California.
Will it set the demand number or track my deadlines?
No. Totals are computed with code from your bills, but the demand figure is yours to set. Deadlines stay out of scope on purpose: calendar them in your docketing system and check them yourself.
Does it connect to Clio or MyCase?
No connector needed. Export the records, bills or notes as PDFs or documents from whatever system you use and upload them to Claude.
What if it isn’t right for my practice?
Email us within 30 days and we refund the full price. No conditions.
Is this legal advice?
No. The kit is for licensed attorneys and their staff. It drafts and organizes; you review, decide and sign. You remain responsible for every filing and every letter that leaves your office.
Your next chronology, built from the records, with a page cite on every row.
Records in; a page-cited chronology, specials that tie to the bills and a demand draft out, with every citation flagged and your sign-off last. About 9 hours a week back, by our estimate. $49 or $99, paid once. Use it on a real, anonymized file, and if it doesn’t earn its place within 30 days, we refund every cent. Not legal advice; for licensed attorneys.
One payment, yours to keep · 30-day money-back guarantee