Starting every job from zero
The lists you hold were unused.
BoldBellowsWorkable AI candidate sourcing for small teams that cannot afford agency fees
Workable AI candidate sourcing automation that matches the lists you already hold to open jobs, adds talent pool candidates through the API and drafts outreach for approval
Workable's API can create candidates in the talent pool, but its documentation says viewing talent pool candidates through the API is not currently supported. BoldBellows records the job shortcode, the lists you hold and the consent on each before a name is considered, adds people to the talent pool through the API and keeps its own ledger, since the pool cannot be read back, then reads the open job's requirements, compares each person on your approved lists with them, asks a model for a one-line reason quoted from the list data, creates the strongest matches as talent pool candidates with their source recorded, drafts a short first message for each in your voice and holds every draft for a person to approve. Nothing is sent automatically and no outside profile is scraped.
View Pricing
From $1,395, billed once.
- Source for Workable from your own lists
- Talent pool filled through the API
- Consent and source recorded
Why a Workable AI route can be trusted with real work
- Lists you holdno outside scraping
- Source recordedfor every name
- Ledger keptpool cannot be read back
- Person approvesnothing sends alone
- Evidence keptEach decision stores the identifiers and timestamps behind it
- No meter running$1,395 covers design, build, tests and handover; nothing accrues afterwards
01the cold-start problem
Every new job starts from a blank page and a job board bill
A small company opens a role and starts from zero, though it holds a list of referrals from the last offsite, a spreadsheet of event sign-ups and a hundred past applicants who were nearly right. Those people are not in Workable's talent pool because adding them by hand is slow. A tool that reaches outside your records to scrape profiles solves the wrong problem and invites a platform's or a regulator's attention. And because the talent pool can be written to but not read back through the API, a careless script can add the same person twice without anyone noticing.
Past applicants forgotten
They were never in the pool.
The same person added twice
The pool cannot be read back.
The same small team, starting from people who already know them
Before: a proposal for every retry
- A retried delivery adds another proposal
- Every opening starts with a job board and a hope
- Lists sit in spreadsheets, unused
After: retries find the proposal they made with Workable AI Candidate Sourcing
- A key combining the person's email, the job shortcode, the list they came from and the model run links every proposal to its source
- Your own lists are matched to each opening with a recorded reason
- Pool entries carry a source and outreach waits for approval
02how it works
How an open job becomes a talent pool built from your own lists
With Workable AI Candidate Sourcing in place, three moves: decide whether it counts, locate the proposal, then write and prove it.
- Interpret the source state. The route reads the Workable record behind the event and confirms the Workable event meets the documented rule.
- Read, compare, rate. The job is read, each person on your approved lists is compared with it, and a model gives a quoted one-line reason.
- Add, draft, approve. Strong matches are added to the pool with a source, drafts are written, and a person approves each one.
Constraints on Workable and the model, and how we meet them
- Write into the pool, never read it back. Workable's API can create candidates in the talent pool, but its documentation says viewing talent pool candidates through the API is not currently supported, so the route keeps its own ledger of whom it added and never depends on reading the pool.
- Write into the pool, then remember. Workable lets a route create talent pool candidates but not read them back, so every addition is recorded in a ledger keyed on the person's email and the job, and a repeat finds the ledger first.
- Uncertain results. A missing confirmation starts a lookup in the AI workflow by a key combining the person's email, the job shortcode, the list they came from and the model run; a new write is never the first response.
03What you get
Inside the sourcing route: the parts that match and add
Start with Core, which admits events and claims identity; Scale then shapes the proposal; Stewardship checks the AI workflow long after go-live, for this Workable AI Candidate Sourcing service.
CoreScaleStewardship
Trigger gatekeeper Core
Lets only the agreed Workable events through and keeps a reason for every one it stops.
Stable identity ledger Core
Records exactly which Workable fields the model saw and what it proposed, in a row that is hard to edit quietly.
Payload trimmer Core
Cuts each Workable payload down to the fields the AI workflow needs before the proposal is prepared.
List matcher and rater Scale
Reads a key combining the person's email, the job shortcode, the list they came from and the model run on every event so a repeat is recognised before it writes.
Person-and-job matcher Scale
Reads a key combining the person's email, the job shortcode, the list they came from and the model run on every event so a repeat is recognised before it writes.
Consent and list matrix Scale
Decides which lists may be used, who may be contacted and what the model may see.
Sourcing ledger Stewardship
Compares additions with replies, applications and hires.
Stale-list monitor Stewardship
Flags a list whose consent has aged past your limit.
Case register Stewardship
Keeps evidence, status and next step for every proposal that could not be confirmed, on the Workable AI Candidate Sourcing service.
Searching for workable ai candidate sourcing implementation? Also covered: workable ai candidate sourcing duplicate prevention and workable ai candidate sourcing error handling. Related searches include workable ai candidate sourcing consultant, workable add candidates to talent pool API, workable talent pool API, workable ai outreach draft, workable ai candidate sourcing automation workflow, workable ai candidate sourcing historical migration, workable talent pool automation, ai sourcing workable, workable referral list import, workable ai candidate sourcing automation consultant, workable ai recruiter assistant, workable sourcing for small business, workable ai candidate sourcing automation service, workable ai candidate sourcing, automate sourcing in workable, workable ai candidate sourcing automation API, workable past applicants rediscovery, workable ai candidate sourcing automation integration, workable ai candidate sourcing automation, workable candidate sourcing without scraping, workable ai candidate sourcing automation agency and workable ai candidate sourcing automation setup.
04Who it's for
If you are among the healthcare practices and clinics, you may also need to turn the lists you legitimately hold, such as referrals, event sign-ups and past applicants, into ranked talent pool candidates for an open job, with a drafted first message for a person to approve
Small teams want a head start. People on your lists want to be contacted only when it is welcome.
Founder
"We cannot afford agency fees."
Your own lists become the first pool.
Hiring manager
"I know a few good people."
Referrals are matched and added once.
Recruiter
"Save me the first-draft work."
Drafts arrive in our voice for approval.
Office manager
"Keep it tidy."
Each name has a source and a date.
Compliance lead
"Respect permission."
Consent is checked before any draft.
Head of people
"Show me why someone is here."
Every addition has a quoted reason.
05Compare
A spreadsheet of names a hiring manager sends over, a zap or a ledger-backed sourcing route: choosing how Workable reaches the AI workflow
Each can add a name. Only one matches against the job, records the source and keeps a ledger.
| How a run starts | A spreadsheet of names | A generic sourcing scraper | Our ledger-backed sourcing route |
|---|---|---|---|
| What starts the work | Whoever is watching Workable | Whatever the trigger allows | YesAn approved Workable event, judged before any write |
| How identity is decided | Matched by eye | The title or a label | YesOne key: email, job shortcode, source list and model run |
| What reaches the AI workflow | A pasted summary | A raw payload | YesA pool entry with source and reason, awaiting a person's approval |
| After an uncertain result | Staff search the AI workflow manually | A blind retry | YesFinds the proposal first, then decides |
Events arrive out of order
Delivery order is not trusted. Each Workable event is ranked by its own time against the state already held in the AI workflow.
A referral appears on two lists
The ledger finds the first entry by email and job, the second list is recorded as an extra source, no second pool entry is created, and the referrer is credited once. A search on a key combining the person's email, the job shortcode, the list they came from and the model run finds what exists; a comparison says whether it matches; the outcome is written down.
Everything in this route hangs from a key combining the person's email, the job shortcode, the list they came from and the model run, so it is agreed before any mapping begins.
PricingThe price follows people, lists and drafts
Cost your sourcing route, one list at a time
Tell the page what may start a decision, how repeats are recognised and how failures recover, and the figure follows from $1,395.
One setup fee · Range shown first · PDF handover included
View Pricing
Pricing
Build your Workable AI Candidate Sourcing price
Pick a package, answer three short questions about how Workable data should reach AI Candidate Sourcing, and your price and turnaround move as you choose.
06The process
Six steps from spreadsheets to a talent pool
Every step ends with something you can inspect: a map, a key, a test result or a signed note.
Gather the lists
We review each list, where it came from and what permission you hold for it.
Approve access
We agree what the route may read from Workable, which model it uses and who approves what it proposes.
Set the rules
Which lists may be used, how old consent may be and who approves drafts are decided and recorded first.
Rehearse the failures
Duplicates, out-of-order events, blank values and timeouts are staged in a test area so the repairs are proven.
Launch with notes
The last step is release: a defined start, a review window and a PDF you can keep.
Settle in
We watch the live route through its first cycle, compare both sides and tune thresholds where the data says to.
07Turnaround
How long the AI Candidate Sourcing packages take
The clock starts when Workable permissions and the model connection are in place.
Core
6 to 10 business days
Scale
10 to 16 business days
Stewardship
16 to 24 business days
08Before we start
What we ask of you
Authorisation to reach the Workable objects in scope
Workable API access you can grant, the lists you want used and a named approver for outreach
Read access to the Workable objects this route depends on
A plain-language list of the Workable events to include and exclude
The people who should be told when something fails
A time window in which testing can happen safely
09Security and ownership
Scoped access, small payloads, and no changes to either tool
The route separates reading from Workable, thinking in the model and writing back, and puts a gate between each stage.
Published interfaces only
Every request goes through the public interfaces of Workable and the AI workflow. No core file, theme or application code is touched.
Scoped, revocable access
Permissions are written down, minimal and reversible.
Data kept to the job
The proposal carries the values the business needs and no more; the rest of the Workable record is never copied across.
Retries that cannot duplicate
Every repair starts from a key combining the person's email, the job shortcode, the list they came from and the model run and a read of the AI workflow, so trying again is safe by construction.
Minimal logging
Evidence of a run is kept as references, not as copies of data.
Full handover
The PDF names each rule, credential and owner so your admins are never guessing.
10In their words
What BoldBellows clients say
Verified reviews from operations and finance teams who trust BoldBellows to keep their data moving correctly.
AI HR & Recruitment Automation
Our HR team was drowning in applications. BoldBellows automated screening, skills-based filtering and interview scheduling.
It saves us hours every week and means we only interview qualified people. Hiring is now faster, better organized and more professional.
AI Workflow Automation for Agencies
Running a digital agency with many clients was overwhelming. BoldBellows built one automation dashboard that tracks tasks, sends updates and creates client reports automatically.
Clients love the transparency and we love the time we get back. Productivity is up, and project delays have dropped to almost zero.
AI Translation & Localisation
When we expanded abroad we needed fast, accurate translations. BoldBellows built an AI translation system that turns our content into several languages instantly.
The translations read naturally and suit each culture. We now serve customers in five new countries without hiring translators. BoldBellows helped us go global.
AI Accounting & Invoice Automation
BoldBellows automated our whole invoicing process: creating invoices, sending reminders and tracking payments.
Late payments dropped sharply, and our accounting team finally has time for strategy instead of repetitive admin. Worth every penny.
AI Data Entry & Reporting Automation
We used to spend hours collecting data and building weekly reports by hand. BoldBellows automated all of it.
The reports are clean, visual and easy to read, and our managers rely on them for quick decisions. Human error is gone and our numbers are more accurate across the board.
AI E-commerce Listings Automation
BoldBellows automated our product listings. The AI writes descriptions, organizes photos and publishes listings across several marketplaces.
It even answers customer questions instantly. Our store looks more professional and sales have noticeably increased.
AI Customer Journey Automation
We wanted a smoother path from first contact to purchase. BoldBellows built an AI system that guides each customer there automatically.
It sends personalized messages, recommends products and follows up at just the right moment. Customer retention has improved dramatically.
AI Document & Contract Automation
Onboarding was slow because we wrote every contract by hand. BoldBellows automated the lot: contracts, welcome emails and client setup.
What took 48 hours now takes under 10 minutes, and clients regularly tell us how professional it feels.
AI Social Comment & DM Automation
We get thousands of comments and messages every week. BoldBellows built an AI system that replies instantly, filters spam and surfaces the important ones.
Engagement is up and our page looks active around the clock. It’s like having a full social media team that never stops.
AI Chatbot & Customer Support
BoldBellows built an AI support chatbot for our online boutique, and it has changed how we run the business. We used to have two full-time staff answering the same questions all day. Now the AI handles order tracking, product recommendations and even refund requests on its own.
What surprised me most is how natural it sounds. Customers compliment the ‘agent’ without realizing it’s AI. Our support workload dropped by 75% and customer satisfaction went up dramatically.
AI Content & Social Media Automation
Our marketing agency couldn’t keep up with content. BoldBellows set up an AI content engine that writes blog posts and captions and even designs our social media creatives.
It spots trends and suggests topics for us, so we stay ahead of competitors. We now produce three times the content with the same team, and engagement has soared. They didn’t just automate our workflow, they lifted our whole brand.
AI Lead Qualification & Sales Automation
Our sales team wasted hours chasing cold leads. BoldBellows built an AI lead-scoring system that reads behavior, email engagement and buying signals.
It filters out weak leads and sends personalized follow-ups automatically, so our team only talks to people who are ready to buy. Conversions rose 40% in the first month. It paid for itself straight away.
AI Video & Voice Automation
We publish product videos every week, and BoldBellows introduced us to AI video automation. The system writes the script, voices it and produces the finished video in minutes.
The quality is remarkable: professional voiceovers, clean visuals and smooth editing. Production time went from three days to under 30 minutes, and we scaled our video marketing without adding cost.
AI Email & Smart Inbox Management
Our inbox used to be chaos. BoldBellows built an AI email system that sorts messages, drafts replies and flags anything urgent.
It learns how we write and gets better every week. We reply faster and no longer miss important messages. It feels like having a personal assistant working around the clock.
AI Booking & Scheduling Automation
Our coaching business needed a better way to schedule. BoldBellows automated all of it: bookings, reminders, cancellations and follow-ups.
No-shows fell by 60% and clients enjoy how smooth it is. It feels personal, not robotic. One of the best upgrades we’ve made.
AI CRM Automation
Our CRM was barely used because updating it by hand was tedious. BoldBellows automated data entry, tagging, segmentation and follow-ups.
Now the CRM is always up to date and our campaigns are far more accurate. It improved our whole sales pipeline.
AI Voice Assistant
BoldBellows built a custom AI voice assistant for our customer hotline. It answers questions, books appointments and handles simple requests.
Customers love how fast it is, and our call-centre workload dropped dramatically. One of the smartest upgrades we’ve made.
AI Automation Partner
BoldBellows is hands-down the best AI automation partner we’ve worked with. Their systems are fast, reliable and built around how our business actually works.
Every automation they’ve delivered, from customer service to content, runs flawlessly. We’ve saved time, cut costs and grown faster than we expected.
11FAQ
Own-list sourcing in Workable: what small teams ask
We collected the questions that decide most purchases and answered them.
Would an AI action in a Workable workflow tool do the same?
For a talent pool built from people who already know you alone, a basic zap is enough. What it will not do is match people on your own lists to a job, record where each name came from or respect consent when the pool cannot be read back. This build covers exactly what a basic connector leaves open.
Does it scrape LinkedIn or the web on the Workable AI Candidate Sourcing service?
No. It uses only lists you hold and approve.
Can it read the talent pool?
Workable's API does not support that, so the route keeps its own ledger of what it added.
Does it send messages by itself?
No. Every draft waits for a person.
How is consent handled?
Each list carries the permission you hold, and anyone outside it is skipped.
Why was someone added?
Each entry carries a one-line reason quoted from the list data.
Which model writes the drafts?
Whichever you approve; each draft stores the model that wrote it, for this Workable AI Candidate Sourcing service.
Is there a written list of what leaves Workable?
You review each Workable field, its purpose and whether it is shared.
Can the route branch by type or by owner in the Workable AI Candidate Sourcing service?
Yes. Thresholds, reviewers and fallbacks are configured to your process, from $1,395.
Does a Workable update break the route?
The handover lists every interface the route uses. If one changes, the affected item stops and is flagged instead of being written from a guess. Repairs after your review window are quoted separately. It is also the answer to custom workable ai candidate sourcing automation.
Next stepStart your next hire from people who already know you
Give your small team a talent pool built from what you already hold
Give us one use case and one approver and you will see a fixed price for the Workable AI route, from $1,395.
- From $1,395, paid once
- Lists you hold
- Person approves
- No monthly fee from us
Unusual volumes or extra systems are quoted on request.