Carrington SmurlProduct Designer / Engineer

AI Product Design2026

EquiStaff

An equestrian staffing agency placing horse people since 1982, out of Ocala with a real, differentiated business hidden behind a generic job-board template. I audited it, sold the rebuild, then grew the work into the admin portal and the ATS. Design, engineering, and the sale were all mine.

Role
Principal Designer — Carrington Design Co.
Timeline
Sept 2026 – present
Client
EquiStaff
Team
Solo audit and sale; build with the Saddle Pass engineering team
Surfaces
Public site · Job seeker · Employer · ATS & admin portal · AI concierge
Stack
Heuristic evaluation · FigJam workshop facilitation · Conversation design · HTML / CSS / JS prototype · Claude Code agents
Constraints
  • A live revenue-generating site that could not go dark
  • Domain knowledge held entirely by the founder
  • An assistant that must never invent a pay figure
  • A rebuild scoped against an existing back end

The engagement

EquiStaff has been placing barn managers, grooms, riders, and estate staff since 1982, out of Ocala. Recruiter-vetted placements, free for job seekers, a real database and a real reputation — four decades of it.

None of that was visible on their website.

I ran a full audit across the public site, the job-seeker experience, the employer experience, the admin portal, their social and marketing presence, and the technical stack — delivered as eleven documents.

The engagement, end to end

Five workstreams for one client, all still running:

Audit Eleven documents across the public site, both sides of the marketplace, the admin portal, social, and the technical stack. 60 findings, severity-rated, scored by audience × heuristic.
Brand & design direction Five directions built out as real pages, narrowed to two — one for the public site, one for the signed-in product — plus a logo redraw and a design system.
The rebuild Thirty-five pages as a clickable prototype the client reviews in her own browser, on her own phone, every round.
The ATS & admin portal Applicant tracking and billing built from scratch rather than licensed, so it fits how a recruiter-led agency actually works.
The AI concierge A grounded, scripted assistant designed in a workshop with the founder in the room, specified rule by rule, and built into every page.

It is one engagement, not five projects. The audit paid for the direction, the direction made the rebuild reviewable, the rebuild made the admin portal obviously worth having, and the admin portal made the licensed ATS the next thing that did not fit. The through-line is the working method, which is the next section.

The audit

The findings and recommendations deck: severity counts of 3 blockers, 24 major, 25 minor, 4 cosmetic and 4 works-well; a scorecard matrix of audience against heuristic colour-coded by worst severity; 60 findings ranked by severity; and seven themed design recommendations.
06 · Findings & recommendationsSixty findings, each tagged with the audience it affects and the heuristic it violates, scored into a matrix of audience × heuristic so the client can see at a glance that the job-seeker path is the one on fire. Four findings are logged as works-well — an audit that finds nothing good is not an audit, it is a pitch.

The headline finding was a positioning one, and it is the sentence the whole engagement turned on:

A real, differentiated business hidden behind a generic job-board template.

Three blockers were stopping the core loops outright. Job seekers, for one, were trapped behind a profile-gate modal that blocked every page even at 100% profile completion, and employers could not find out what a subscription cost or buy one.

Underneath the blockers was a consistent pattern rather than a list of unrelated bugs — unlabelled and dead controls, database-flavoured copy leaking into the interface, polluted option data, and a brand story told three different ways on three different pages.

My favourite finding is not a design problem and I reported it anyway. The site claimed two different founding dates. Resolved during the audit: founded 1982, online since 2000. An agency four decades old was accidentally telling visitors it had been around since 2000.

Why the matrix matters

Severity rating on its own produces a list nobody can act on. Cross-tabulating audience against heuristic turns the same findings into a decision:

  • The job-seeker row is the one with blockers in it, so that is where the rebuild starts.
  • The employer row has the revenue problem — they cannot buy.
  • The public site row is broad but shallow: lots of major, few blocking.

A client with a fixed budget needs to know what to fix first. The matrix answers that without me having to be in the room.

What the audit sold

The audit was the pitch. What it sold, in three steps:

First The rebuild — a new front end on their existing APIs, plus the AI concierge
Then The admin portal, added once she saw what the employer side could be
Then Their ATS, rebuilt from scratch internally rather than licensed
$50,000 Total, for one client, inside the Saddle Pass ecosystem

Each number came from the one before it. The audit proved the site was costing them placements; the rebuild made the employer side visible enough that the admin portal became obviously worth having; and once the admin portal existed, the applicant tracking they were paying someone else for was the next thing that did not fit.

I ran the design, the engineering direction, and the sale. That is the part I am proudest of — not the total, but that no part of it was handed to me.

How the work runs

Before any of the screens, the thing worth looking at is the machinery that produced thirty-five of them, at this quality, for one client, on a fixed fee — and that is still producing them. This section sits here rather than at the end because everything after it is an output of it.

A prototype index page headed Thirty-three screens, three journeys, dated 22 October 2026, with three journey cards — looking for work, hiring through Kaitlin, posting it yourself — each listing its screen count and a start link, a note that twenty-four screens changed in this round, and a section listing the public site pages with status chips.
The prototype is the deliverableThe client does not get a Figma link and a walkthrough call. She gets a URL, dated, organised by journey rather than by sitemap, with each journey showing how many screens it holds and where to start. “Twenty-four screens changed in this round” is at the top, and a section headed “deliberately not built yet” states the gaps rather than letting her discover them. A review request is a brief, and an unbriefed reviewer gives you notes on the font.
A What changed on this screen panel, dated 29 October design round, listing five changes — the assistant is now Evie with a profile photo and still says she is AI not a person; the chat works on every page; a new Design drawer for trying colours, launcher shape, side, size, name, greeting and typing speed live; the launcher uses Brittany's horseshoe instead of a plain dot; and live-note text lifted to clear AA on the brightened portal.
What changed on this screenEvery page carries its own revision log, in the corner, per round. The client can see what moved since she last looked without reading a changelog in another window — and because it is per screen, her feedback lands on the right thing. The script that renders it says outright that it is a review aid and gets deleted before launch, which is the right way to ship a scaffold.

The loop

  • A clickable prototype instead of flat comps. Every round is a real URL the client clicks through on her own time, in her own browser, on her phone.
  • Figma comments, gated by emoji. The internal design team marks up screengrabs in Figma. Only comments marked with a hammer get built — everything else is logged. Without that rule a shared file turns every opinion into a work item.
  • Granola for the calls. AI notes on every client call, so the decisions are captured while the conversation is still happening rather than reconstructed afterwards from memory.
  • Named agents per workstream. The prototype flows, the admin-portal redesign and the mobile audit each run as their own Claude Code session, producing pull requests against a repo with a PR template, a changelog and a written “how we work” section in the README. I review and merge; nothing lands on main without that.

That last one is the part worth stating plainly, because it is what the rest of this page is evidence of. I am a designer who ships to a codebase. The prototype is mine — the HTML, the CSS, the chat script, the revision marker — built by directing agents and reviewing their output the same way I would review a junior’s. It is why one engagement could carry thirty-five designed screens, an ATS and a working assistant, and why the later work followed at all: the client kept seeing more of her own product than she expected to, and asked for the rest.

Design direction

Five directions, narrowed to two — because the public site and the signed-in product are not the same room and should not pretend to be.

Five high-fidelity home page directions side by side at desktop width, ranging from warm cream and tan grounds through blue and white to a dark navy treatment, each with the same headline and layout so only the palette and type differ.
Five home pages, same contentThe only way to decide a direction is to build the same page five times and put them next to each other. Holding content, layout and headline constant means the conversation is about the thing being chosen rather than about whose copy is better — and the warm grounds lost on the spot, which a mood board would have argued about for a week.
Direction D, Blue and White: a brand board with a white-ground EquiStaff homepage, a colour balance bar weighted to white and blue, Libre Baskerville and Lato type specimens, applied buttons and a job card, and a Choose this if panel.
✅ Direction D · Blue & White — public siteBlue and white for everything a stranger sees. The “choose this if” panel at the bottom is the part I would carry into any client project: each direction argues for itself in the client's own terms — this one wins if Kaitlin wants the site to feel current and fast, and it keeps the one colour everyone already associates with EquiStaff.
Direction E, Navy House: the same brand board on a dark navy ground, with the colour balance weighted to navy, the same type specimens, and a Choose this if panel noting the trade that photography has to be strong because a dark ground gives a weak image nowhere to hide.
✅ Direction E · Navy House — signed-in areaNavy for the signed-in product. Both directions won, as two ends of one system: the public site is bright and quick, the portal is dark and dense. The trade is written on the board — a dark ground gives a weak image nowhere to hide, so the photography brief had to get stricter before this could ship.
A logo exploration sheet showing the current EquiStaff lockup and five evolutions — a minor facelift, a mascot version with horses, an Ocala coastal version, a hidden-message version in which a magnifying glass is concealed in the horse's neck, and a classical version.
Logo — five evolutionsFive routes from a facelift to a full redraw. The winner, unanimously, is the one with a magnifier hidden in the horse's neck — a search mark inside the animal, which is what a staffing agency for horse people literally does. Keeping the current lockup at the top of the sheet is deliberate: a client needs to see what they are giving up.
A comparison board headed Current on the left, V1 on the right, showing the existing site's header, buttons, form fields and job card beside the rebuilt equivalents, with the old versions marked in red.
Current on the left, V1 on the rightThe component-level before and after. Doing this as a direct pairing rather than a showcase is what makes a redesign reviewable by a non-designer: the client is not asked whether they like the new button, they are asked whether it is better than the one they have.

The rebuild

Thirty-five pages, live as a clickable prototype the client reviews in the browser. The screenshots below are from the current build.

The public site

The EquiStaff homepage: a dark hero over a photograph of a woman with a horse in a barn aisle, headed From the barn to the boardroom, with the line grooms, barn managers, directors and executives — recruited, vetted and placed by horse people, in Ocala since 1982; a Which are you question offering I'm hiring and I'm looking for work; and a trust strip reading every listing verified, references checked by phone, replacement guarantee in writing.
Home“From the barn to the boardroom” was logged in the audit as a works-well — their own story, buried three pages deep. It is now the first thing on the site. The dual-path question under it replaces a generic sign-up with the only question that actually routes someone, and the trust strip states the three things that make them different from a job board: they call the barn, they check references by phone, and the guarantee is in writing.

Job seekers: nothing to get past

The jobs listing page headed Every open role, with the pay on it, noting no account needed to browse; a search bar for role, location and type; filters for recruiter-managed versus direct, housing, commitment and discipline; and role cards showing Barn Manager at $55,000 to $68,000 housing included, Equestrian Director at $110,000 to $140,000, and National Sales Director at $150,000 to $185,000.
Find workThe blocker, answered twice over. “No account needed to browse” kills the profile gate; “Every open role, with the pay on it” kills the complaint underneath it. Pay is on the card, not behind a conversation. Housing is a filter, because in this industry housing is often worth more than the salary band beside it — and so is state, because equine work follows a circuit and people move for a season.
A Barn Manager role page: recruiter-managed by EquiStaff badge, 24-horse hunter jumper barn in Ocala Florida, $55,000 to $68,000 housing included, listing verified 3 October, with an about-the-role description and a facts panel for horses, team, housing, start and reports-to, beside an apply card reading one short form, no account needed to get started.
A roleThe facts a horse person actually decides on, pulled out as a panel: how many horses, how big the team, what the housing is, who you report to. “Listing verified 3 Oct” is the audit's verification promise turned into a per-listing fact with a date on it — a claim you can check beats a badge you cannot.
An application flow, step one of three, headed Let's get your application in, with name, email, phone and location fields, beside a panel titled What happens to this explaining that the application goes to Kaitlin's team who check it before the barn sees it, that details are never shared with anyone not applied to, that it is free, and that the profile can be deleted at any time.
ApplyingThe “What happens to this” panel is the piece I would defend hardest. People in low-paid work are cautious about where their details go, and the audit found nothing on the old site that told them. Four plain sentences, next to the fields rather than linked from a footer, at the exact moment the question occurs.
A job seeker's applications page listing three roles with statuses Shortlisted, Being reviewed and Sent to barn, above a panel titled What each status means explaining being reviewed, sent to barn, shortlisted and closed.
Application status, explained“Don't hear back from barns” was one of the loudest complaints in the research. Status alone does not fix that — a word like “Shortlisted” means nothing until someone tells you what happens next. The explainer panel is doing the work a recruiter's phone call used to do, for the hundred applicants who never got one.
A two-panel sign-in screen: on the left, a headline reading you don't need an account to look around, with bullets on avoiding re-typing the same form, tracking applications, getting a match alert and being found by the recruiting team, above a keep-browsing-instead link and an illustration of two running horses; on the right, a Welcome back panel with email and password, a stay-signed-in checkbox and a continue-with-Google option.
Sign in — and the case for notThe left panel argues against itself. It lists four concrete reasons an account helps and then offers “keep browsing instead” as a real option, because the audit's worst blocker was a profile gate that trapped people who had already finished their profile. Having been burned by a hard gate, the fix is not a softer gate — it is making the account earn its place, in four bullets, with an exit next to them.
A resume builder headed You don't need a resume to start, with a three-step progress indicator and fields for where you have worked, beside a live preview of a formatted resume for Dana Whitfield with experience, skills and references, and buttons to download as PDF or email it.
Resume builderRequiring a resume filters out exactly the candidates this agency is best at placing. Building one from questions, with the result rendering live beside the form, turns a barrier into a reason to finish — and the output is theirs to take anywhere, which is the kind of thing that earns a free platform some goodwill.

Employers: the revenue path

A pricing page headed Post it yourself, or hand it over, with a job board section offering one month at $49.99, one month featured at $69.99, three months at $139.99 marked most popular, and one year at $469.99, above a section headed When a listing is not enough, but a full search is more than you need.
PricingThe second blocker, closed. Employers previously could not find out what a subscription cost, let alone buy one. The framing — post it yourself, or hand it over — sells the agency's actual differentiator inside the pricing table, so the cheap self-serve option is the one that makes the managed search look like the better deal.
A request talent page headed Tell us the role, we'll bring you the people worth meeting, noting Kaitlin reads every request herself; a three-step form for the role, how to reach you and your program; and a panel explaining what you get back and how a managed search works.
Request talent“Kaitlin reads every request herself.” The high-value path is deliberately the one with a human at the end of it, and saying so converts better than any automation would. The panel beside the form sets expectations before the work starts — a shortlist of four, references checked by phone, never automated.
A post-a-job page headed Write it once, properly, with a post-completeness meter at 0 percent, fields for job title, location, commitment, pay range and discipline, and a live preview of the advert showing the warning no pay listed — this is the one candidates notice.
Post a jobA completeness meter and a live preview, with the advert rendering exactly as a candidate will see it. The inline warning — “No pay listed — this is the one candidates notice” — is research findings turned into a nudge at the moment of writing. Telling an employer why a field matters works; marking it required does not.
A plans and billing screen showing the current one-month plan at $49.99, options to switch to three months at $139.99 or one year at $469.99, a saved Visa payment method, and a downloadable invoice list.
Plans & billingThe employer's own side of the subscription the admin portal manages. An employer who cannot see what plan they are on, change it, or download an invoice will phone the agency instead — which is a staffing business spending recruiter hours on billing admin.
A messages screen with a thread list filtered by all, unread, Kaitlin and employers, and an open conversation with Kaitlin Veltkamp of EquiStaff about a barn manager role.
MessagesThreads separated by who is on the other end — the agency, or an employer directly. In a recruiter-managed marketplace those are different conversations with different rules, and collapsing them into one inbox is how a candidate ends up negotiating pay with the wrong party.

The ATS

Applicant tracking rebuilt from scratch rather than licensed, so it fits the way this agency actually works instead of the way generic recruiting software assumes.

An employer dashboard headed Your searches, showing a Barn Manager search opened 18 September with a progress track reading listened, searched, shortlist of four, references, placed; a note that Kaitlin has four people for you with a book the call button; and a shortlist of three candidates each marked references clear.
Your searchesThe pipeline as the agency describes its own method: listened → searched → shortlist of four → references → placed. Most ATS software models a funnel with arbitrary stages. This models their promise, so progress through it is legible to a client who was told what to expect on day one.
An applicants screen showing nine applicants for a Regional Sales Manager role, with tabs for all, new, shortlisted, contacted and not for this; a notice that these people have been spoken to and nothing is verified until a managed search adds it; and rows of candidates with view and shortlist actions.
ApplicantsTwo things worth noting. The tabs are decisions, not statuses — “Not for this” is a verb an employer actually performs. And the notice at the top draws the line between a direct post and a managed search in plain words, so the verification promise is not accidentally extended to candidates nobody has checked.
A candidate record for Pete Donnelly, a regional sales director with twelve years' experience, with buttons to message him and make a note; a row of consent checkboxes reading allow client to message candidate and release contact details; a Kaitlin's take panel of narrative notes from a phone call; an at-a-glance column listing availability, what he is looking for, housing, relocation, discipline and team size; and dated reference checks.
Candidate recordTwo things generic ATS software gets wrong. “Kaitlin's take” is the top section — four decades of this business run on a recruiter's read of a person after a phone call, and software with nowhere to put that pushes it into a spreadsheet. And the consent row beneath the name is explicit: whether the client may message this candidate, and whether contact details are released, are per-record switches a recruiter sets. In a managed search the agency is the gate, so the gate has to be a control rather than a convention.

The admin portal

The piece with the clearest before and after on this page. The agency runs on this software every day — it is where Kaitlin actually works — and it was the part nobody had ever designed.

The existing EquiStaff administration dashboard: a dark navy sidebar of nested menus beside a grid of eight small stat tiles — new jobs posted, new applications, revenue from subscriptions, new employers, new advertisers, upcoming renewals, total active subscriptions, newly registered unsubscribed employers — above donut charts, a subscription table and a transaction table.
Before — the dashboardEight numbers, three charts and two tables, and not one of them tells you what to do. Counting is not the same as prioritising: “55 new applications” is a fact, and a recruiter still has to go and find which of them needs her this morning.
The existing Manage Employers screen captured at full width — a table roughly twice as wide as a laptop screen, with around twenty columns of small data running off the right edge.
Before — Manage Employers, at its real widthThis is one screen, captured at the width it actually renders: about twice a laptop. The audit counted 34 menu screens plus detail pages, pop-ups and full-width tables like this one. A table that cannot be read without scrolling sideways is a table nobody reads — they phone someone instead.
The existing Manage Job Seekers screen: a filter row, a hidden-job-seekers toggle, and a dense striped table of first name, last name, user name, email and phone, paginated as showing one to ten of 8,555.
Before — 8,555 rows, ten at a timeEight and a half thousand people, paginated ten at a time, sorted by nothing in particular. The data is all there. The product does nothing with it.

Two dashboards, to be chosen between

Rather than present one answer, I built the two credible ones and let the person who lives in it decide.

Redesigned dashboard, direction A: a good-morning greeting dated Monday 2 November, a Needs You Today row of four tiles — jobs waiting for approval, photos and videos to check, new leads, direct-hire candidates waiting — each with a subline such as oldest waiting 2 days, above a This Week row and paired lists of jobs awaiting approval and employers signed up but not subscribed.
After — direction A: what needs you todayThe same counting, re-sorted into a judgement. “Jobs waiting for approval: 7 — oldest waiting 2 days” is the old tile plus the one fact that makes it actionable. Everything merely informational drops to a This Week row underneath, which is where a number that nobody acts on belongs.
Redesigned dashboard, direction B: a heading reading Today, Monday 2 November, 12 things to do, oldest first, with filter chips for all, approve, leads, direct hire and follow up, above a single chronological list of tasks each with an age pill and a single action button, and a note that done items drop off the list.
After — direction B: one list, oldest firstThe other credible answer: no tiles at all, one queue, oldest first, with chips to narrow it. “Done items drop off this list” is the whole promise — the screen gets shorter as you work, which a dashboard of counters never does. Offering A and B as a real choice is what gets a decision out of a client instead of a reaction.

Organised around the job that pays

The Direct hire screen: every active search in a table with columns for role and client, how the candidate came in, opened date, presented, interviewing, furthest stage and client reply, with red pills marking searches where the client has not replied in several days.
Direct hire, firstDirect hire is the agency's highest-value work, so it gets its own top-level section rather than living inside a jobs table. The rule is written under the heading — a red pill means the client has not answered in more than three days — which turns a status column into the thing the screen is for.
A single search for Barn Manager at Live Oak Stables, showing the brief, client interview availability, a shortlist of candidates each with feedback and two toggles, a client notes column and an activity log; a callout explains that two switches protect the fee by holding back contact details and messaging until a placement is settled, and that the client never sees them.
One search, with the fee protectedThe two switches on every shortlisted candidate are the commercial model rendered as interface: contact details and direct messaging stay off until the placement is settled, because an agency that hands over a phone number early has given away its fee. The callout says the quiet part out loud — “the client never sees these switches” — which is exactly the kind of rule that has to be designed rather than assumed.
A candidate record inside a search for Dana Whitfield, with EquiStaff's own narrative feedback, fee-protection toggles, a stage-and-dates tracker from presented through hired, the client's feedback marked read-only, and a private note to the recruiting team.
One candidate, three audiencesThe same record carries three kinds of writing with three different readerships: EquiStaff's feedback, which the client reads; the client's feedback, which is read-only here; and a private note to the recruiting team that neither side sees. Labelling who can see what, on the record itself, is the difference between a CRM people trust and one they keep a side spreadsheet for.

Everything that needs a yes

The Jobs screen, filtered to waiting for approval, with counts for live, sent back, closed and all; each row offers Review and Approve, sorted by waiting longest, above a recently live or closed list.
Jobs — nothing goes live without a yes“New posts wait here until you approve them. Nothing goes live on the job board without a yes.” The default filter is the queue, the default sort is waiting longest, and approve sits on the row. The verification promise the public site makes is only true if this screen makes honouring it the path of least resistance.
The Photos and videos moderation queue: uploads shown as a grid of thumbnails of barns and horses, each with the uploader, how long ago it arrived, and Approve and Reject buttons, with tabs for waiting, job seekers, employers and rejected.
Photos & videos — hidden until approvedVisual moderation as a grid rather than a list, because the decision is made by looking. “New uploads stay hidden until you approve them” is both the rule and the reassurance — on a platform placing people into barns, an unmoderated photo is a liability, and the default has to be off.
The Employers screen with tabs for all, subscribed, signed up not subscribed, direct-hire clients and deactivated; an amber banner states that nine employers signed up but never subscribed and are pinned to the top, with Follow up buttons on those rows.
Employers — the money that never arrivedNine employers signed up and never subscribed, pinned to the top of their own list with a Follow up button that opens a ready-to-send email. That is revenue the old portal held and never surfaced. A list sorted by signup date treats those nine as history; sorting by what needs action treats them as a to-do.
The Subscriptions and coupons screen: counts of active, renewing and cancelling subscriptions, a coupon table with codes, discounts, validity and usage, a by-plan breakdown, and a panel noting that the full subscription list, invoices and refunds live in Stripe with a button to open it.
Subscriptions — and where the line is drawnThe panel at the bottom right is the most useful decision in the whole portal: the full subscription list, invoices and refunds live in Stripe, and this screen does not try to be Stripe. It handles coupons and plan changes — the things a recruiter does — and hands off the rest. Scoping a build by what you deliberately will not rebuild is how a small line item stays a small line item.

The chatbot: a workshop, not a brief

The founder holds all the domain knowledge and none of the software vocabulary. So rather than write a spec and ask her to approve it, I ran a 60-minute FigJam workshop with her and the engineering side in the room, and designed the assistant live.

A run-of-show board for a 60-minute workshop: 0 to 5 why we are here, 5 to 15 personas, 15 to 30 journeys, 30 to 40 what they ask, 40 to 55 decision tree marked the main event, 55 to 60 boundaries; with a closing note that if time runs short, drop the journey map because the decision tree and the boundaries are what unblock the build.
Run of showSixty minutes, timeboxed, with the sacrifice decided in advance: “If time runs short, drop the journey map. The decision tree and the boundaries are what unblock the build.” Facilitating means knowing which artifact you are willing to lose before you are twenty minutes behind — and the opening line sets the frame, “Not designing screens. Deciding how the bot behaves.”
A board headed Who actually shows up, with columns for job seekers and employers filled with sticky notes, a section of additions from Monday's call in orange, and an empty Add your own column in purple.
1 · Who actually shows upPre-filled from the audit and Monday's call, with an empty purple column labelled “add your own.” Starting a workshop with a blank board wastes the first fifteen minutes and makes the expert feel examined. Starting with a draft she can correct makes her the authority, which is the role you actually want her in.
A journey map with two lanes — the barn manager, and the advert that is not working — across columns for arrives, wants, looks, decides, acts and after, filled with blue, green and yellow sticky notes.
2 · What happens when they landTwo journeys, one per side of the marketplace, with the employer lane framed as a situation rather than a person — “the advert that is not working.” The brief under it is the whole reason a bot is in scope at all: find the moments where an assistant changes the outcome. Most of the row is places where it would only get in the way.
A board headed What do they actually ask you, with blue job-seeker questions and green employer questions, a prompt to dot the five answered most often, and two further areas labelled what we missed and the awkward ones in red.
3 · What do they actually ask you?Pulled from her own inbox and the old site's dead ends, then dot-voted down to the five she answers most often. “The awkward ones” is its own red zone — the questions a recruiter fields that a bot absolutely must not attempt. Naming that area out loud is how you get an expert to volunteer the dangerous cases instead of discovering them in production.
A large decision-tree flow diagram headed The whole conversation, first draft, with a start node branching through diamond decision points into job seeker and employer paths, with orange and yellow sticky notes attached to branches.
4b · The whole conversation, first draftThe main event. I brought a full draft tree so the session could be spent walking it and arguing with it rather than drawing boxes — the sticky notes hanging off the branches are what changed while she talked. A decision tree is also the artifact that makes a non-technical client able to sign off a conversational product: every path is visible, so approving it means something.
A board headed What it must never do, with red sticky notes listing prohibitions, and a section at the bottom headed The throttle quoting the client — matching should work, but not work so well that it makes the recruiting service obsolete — asking where the line is.
5 · What it must never doThe boundaries list, and the single most interesting constraint on the project. She told me matching should work, “but not work SO well that it makes the recruiting service obsolete.” That is a business model expressed as an interaction limit, and it had to become a rule engineering could build to. Most AI features are designed to be as capable as possible; this one had a deliberate ceiling, and finding where it sits was a design decision, not a technical one.

The AI concierge

The EquiStaff Conversation Map: a three-state legend for drafted structure, boxes the founder fills in, and hand-off-to-a-person; an opening assistant message with four reply options; edge cases for already-signed-in, both-roles, and free-text answers; and branching paths for job seekers and employers.
Conversation mapThe structural skeleton, with a deliberate three-state legend: solid borders are conversation structure I drafted, amber dashed borders are horse-world knowledge only the founder has, and black borders are where the bot hands off to a person. Making the gaps a visible part of the artifact is what turns a review into a working session.

Designing around what I do not know

I am not an equestrian recruiter. I do not know what each barn role actually involves, how an experienced recruiter sizes up a candidate’s real level, or what makes someone a bad fit for a particular barn.

Rather than guess and be quietly wrong, those gaps are drawn into the document as amber boxes addressed to the founder: “The list of barn roles and what each one really involves. The disciplines. How you size up experience level.” · “What else do you ask every candidate in the first 5 minutes?” · “What makes someone a good fit for a barn? What are the dealbreakers on either side?”

That is a design device, not an admission. An assistant for a specialist domain is only as good as the domain knowledge inside it, and the fastest way to extract that is to show the expert exactly where their knowledge is load-bearing.

The specification, published as a page

An AI concierge specification page headed Every state, and the rule it enforces, explaining that V1 is a scripted assistant and not a self-learning AI, that every path is written in advance and anything it cannot answer goes to book a call with Kaitlin, and that it never generates an answer not in the approved content; below, a panel titled What she asked for — six capabilities covering answering with live numbers, troubleshooting accounts, improving what people write and capturing leads, and a panel titled Still unanswered listing money, live data, book time and hand off, identity, Spanish and resume accountability.
Every state, and the rule it enforcesThe handoff document rendered as a browsable page, with rule numbers R1–R12 carried through from the engineering spec. The opening paragraph is the governance decision stated plainly: V1 is scripted, not self-learning, and it never generates an answer that is not in the approved content. Below the capabilities sits a live list of what is still unanswered — money, live data, identity, Spanish, resume accountability — so the client reads the open questions in the same place as the finished behaviour.

Why scripted, for V1. In a staffing context a confident wrong answer about pay is not an embarrassment, it is a dispute between a barn and a candidate with the agency’s name on it. Scripted means anyone can test it and get the same answer twice, which is also what makes it signable by a client who does not build software.

A chatbot discovery board headed The chatbot, before anyone writes code, with a cream panel of context, a grid of six capability cards, a blue grid headed what is still genuinely open after five live questions, and a red strip about everything the route needs access to for it to exist.
Before anyone writes codeThe discovery page, written so an engineer could be handed it cold. Six capabilities in the middle, and underneath, in its own colour, “what is still genuinely open” — the questions whose answers change the build. Separating the decided from the undecided on the same page is what stops an engineer guessing at the second half.
A board headed The assistant, working on every page, showing fourteen numbered states of the chat panel — greeting, job question, job match, add-role nudge, request talent, published advert, consulting, troubleshooting, hand-off, two more and a Spanish variant — above three device views showing the same assistant on desktop, tablet and mobile.
Every state, builtFourteen numbered states plus the responsive views, laid out so the client can read the assistant as a product rather than as a demo. Numbering them against the handoff's rule table is what let a non-technical founder give sign-off that engineering could actually rely on — she was not approving a vibe, she was approving state 07.
The assistant open on the chatbot page in its signed-in job-seeker state, greeting Dana by name with the options find me a job, help with my profile, question about a job and account help, above the prototype toolbar.
The same assistant, signed inSigned in, it skips the opening question and greets by name — it reads the page it is on and the state you are in. The four options are the four things a job seeker actually does here, which is the decision tree from the workshop showing up as chips.
The chat widget open over a job page: a header reading Evie at EquiStaff, an AI assistant not a person, with a persistent Talk to a person button for Kaitlin and her team; an opening message asking what brings you here today with four reply chips; a message field; and a prototype toolbar offering try as visitor, job seeker or employer, a restart, a design drawer, and a note that the name and voice are Kaitlin to confirm.
The assistant, in contextThree decisions visible at once. It says “An AI assistant, not a person” in the header, because letting someone believe they reached a recruiter and then revealing otherwise is the fastest way to lose them. “Talk to a person” sits above the conversation, not at the end of a failure path. And the prototype toolbar marks the name and voice as “Kaitlin to confirm” — an unresolved decision left visible inside the thing being reviewed, which is the same device as the amber boxes in the map.

The constraints I would defend

Grounding. Job questions are answered only from what is in the posting. The assistant does not infer pay, horse count, or schedule.

Bounded retries, then a person. If someone types a free-text answer the assistant cannot route, it tries to classify twice and then offers a human. Two tries, not infinite patience.

A human gate on the revenue path. Employer inquiries do not get auto-handled. They become an inquiry, and Kaitlin reviews every one. The side of the marketplace that pays is the side where a person stays in the loop.

Role fluidity. A barn manager can be hiring and job hunting in the same week, so either path can be switched at any point. Exactly the same overlapping-identity problem I solved on Saddle Pass, arriving from a different direction.

The partnership

EquiStaff and Saddle Pass are partnering on the job board — EquiStaff’s established equestrian network and job data, Saddle Pass’s engineering. Their commercial terms are theirs to disclose, not mine, so they are not on this page.

What it means for the design is that the rebuild is not a one-off website. The job board has to work as a product EquiStaff runs and as a data source another platform consumes, which changes how the job posting itself gets structured — it stops being a page and starts being a record. That is also why the ATS was worth building rather than licensing: a licensed one would have owned the data on the wrong side of the partnership.

What I would tell you in an interview

This is the engagement I would point at for consulting judgment rather than craft. The audit was not the deliverable — the sale was, and the audit is what made the sale possible. Sixty findings with severities and a scorecard let a client see the size of their own problem without me arguing for it, and each of the three sales came out of a problem the previous piece of work made visible.

On the AI side, the decision I would defend in any room is choosing a scripted assistant for V1. It is less impressive and it is correct: the failure mode of a generative answer here is a pay dispute with the agency’s name on it, and four decades of reputation is not the thing to test a language model against. Ship the version whose behaviour you can enumerate, log every question it could not answer, and let that log decide what V2 is allowed to generate.

The thing I would keep doing: logging what works. Four findings in that deck are marked works-well, including the Barn-to-Boardroom story that is now the first line on their homepage. A consultant who finds only problems is selling, not auditing, and clients can tell.