Recruiting & placement
Job-order intake
Capture an employer job order — role, shift, pay, site, headcount, screening rules.
- Inputs
- Job order · Role criteria · Screening rules
- Outputs
- Structured open order
- KPIs it moves
- Order capture time · Order data completeness
- Systems it usually runs on
- TempWorks (ATS)
- Where a person stays in the loop
- Ambiguous order confirmation
Screen & match → shortlist
Screen and rank applicants against role / shift / pay and tenant screening rules; produce a shortlist.
- Inputs
- Applicants · Open order · Work-eligibility / cert data
- Outputs
- Ranked shortlist with reasons
- KPIs it moves
- Time-to-fill · Shortlist quality · Screen-to-interview rate
- Systems it usually runs on
- TempWorks (ATS)
- Where a person stays in the loop
- Shortlist approval
Candidate outreach & interview booking
Contact shortlisted candidates (bilingual SMS/email), answer FAQs, and book interviews/orientation.
- Inputs
- Approved shortlist · Message templates (EN/ES)
- Outputs
- Booked interviews · Logged dispositions
- KPIs it moves
- 30-min-callback SLA · Response rate · Interview show rate
- Systems it usually runs on
- TempWorks (ATS) · SMS · Email
- Where a person stays in the loop
- First outbound message approval
Placement / assignment
Create the worker assignment on the order and hand off to onboarding.
- Inputs
- Selected candidate · Open order
- Outputs
- Assignment · Onboarding handoff
- KPIs it moves
- Fill rate · Time-to-start
- Systems it usually runs on
- TempWorks (ATS)
- Where a person stays in the loop
- Assignment write approval
Scheduling & dispatch
Shift fill & dispatch
Match available, compliant workers to open shifts by skill, site, availability, and reliability.
- Inputs
- Open shifts · Worker availability · Compliance status
- Outputs
- Filled shifts · Coverage view
- KPIs it moves
- Fill rate · Time-to-fill · Coverage %
- Systems it usually runs on
- TempWorks (ATS) · SMS
- Where a person stays in the loop
- Assignment write approval
Reminders & no-show prediction
Send shift confirmations/reminders and flag likely no-shows (needs a schedule trigger — see runtime caveat).
- Inputs
- Upcoming shifts · Attendance history
- Outputs
- Confirmations · No-show risk flags
- KPIs it moves
- Confirmation rate · No-show rate
- Systems it usually runs on
- TempWorks (ATS) · SMS
Call-off → backfill
Intake a call-off, find eligible/compliant backfills, secure coverage, and notify the client.
- Inputs
- Call-off event · Eligible worker pool
- Outputs
- Backfill assignment · Client coverage notice
- KPIs it moves
- Backfill time · Redeploy rate · Coverage SLA
- Systems it usually runs on
- TempWorks (ATS) · SMS
- Where a person stays in the loop
- Backfill assignment write · Client notification approval
Workforce admin
Timecard reconciliation
Reconcile hours vs scheduled shifts, flag missing punches / overtime / mismatches pre-payroll; prepare, never commit, edits.
- Inputs
- Timecards · Scheduled shifts
- Outputs
- Pre-payroll exception report · Proposed edits
- KPIs it moves
- Timecard-exception rate · Exception catch rate
- Systems it usually runs on
- TempWorks (payroll)
- Where a person stays in the loop
- Any timecard edit
Attendance & absence tracking
Track attendance/absence and escalate problematic patterns.
- Inputs
- Punch data · Schedule
- Outputs
- Attendance record · Pattern escalations
- KPIs it moves
- Absence rate · Pattern-detection lead time
- Systems it usually runs on
- TempWorks (ATS)
- Where a person stays in the loop
- Disciplinary escalation
Worker pay Q&A
Answer worker paycheck/hours questions strictly from the tenant's data; never move money.
- Inputs
- Worker question · Pay/timecard data
- Outputs
- Grounded answer · Human handoff on low confidence
- KPIs it moves
- Answer accuracy · Deflection rate
- Systems it usually runs on
- TempWorks (payroll)
HR & onboarding
Worker onboarding
Collect I-9 / W-4 / direct deposit / IDs, validate completeness (not legal adjudication), provision portal, run a bilingual checklist.
- Inputs
- New placement · Onboarding checklist · Worker documents
- Outputs
- Completed checklist · Provisioned portal access
- KPIs it moves
- Onboarding cycle time · Doc completeness · First-day readiness
- Systems it usually runs on
- TempWorks (ATS) · Doc-gen · Email/SMS
- Where a person stays in the loop
- Document marked verified · Portal provisioning
HR Q&A (bilingual)
Answer PTO/benefits/policy/handbook questions grounded in the tenant's corpus (EN/ES); route out-of-corpus to a human.
- Inputs
- Worker question · Policy corpus
- Outputs
- Cited answer · Human handoff
- KPIs it moves
- Answer accuracy · Citation rate
- Systems it usually runs on
- Corpus (RAG) · TempWorks (ATS)
Safety & compliance
Safety & cert tracking
Track training/cert expiry, send renewal reminders, intake incident reports, collect required documentation.
- Inputs
- Cert/training records · Incident reports
- Outputs
- Renewal reminders · Incident records · Audit-ready log
- KPIs it moves
- Cert-expiry lead time · Doc completeness · Incident closure time
- Systems it usually runs on
- TempWorks (ATS) · Email · Doc-gen
- Where a person stays in the loop
- Compliance record write
Statutory compliance (IL Day & Temp Labor Act)
Track IL Day & Temporary Labor Services Act obligations (HB 2862 / HB 3641 — equal pay/notice/record-keeping); draft required notices.
- Inputs
- Assignment data · Equal-pay comparators · Statutory rules
- Outputs
- Required notices · Compliance audit log
- KPIs it moves
- Compliance-doc completeness · Lapse-prevention rate
- Systems it usually runs on
- TempWorks (ATS) · Doc-gen
- Where a person stays in the loop
- Every generated notice
Growth & service
Client / worker service
Answer service inquiries (order status, staffing requests, where-is-my-worker), triage, route, draft replies from corpus.
- Inputs
- Service inquiry · Order/assignment data
- Outputs
- Drafted reply · Routed escalation
- KPIs it moves
- First-response time · Resolution rate
- Systems it usually runs on
- TempWorks (ATS) · Email/SMS
- Where a person stays in the loop
- Any client commitment/promise
Sales development (employer prospecting)
Identify and qualify prospective employer clients, draft personalized outreach, book discovery meetings.
- Inputs
- Prospect signals · ICP criteria
- Outputs
- Qualified prospects · Booked meetings
- KPIs it moves
- Qualified meetings · Outreach reply rate
- Systems it usually runs on
- TempWorks (customers) · Email · CRM
- Where a person stays in the loop
- First outreach approval
Ops & client reporting
Compute fill/attendance/turnover/timecard KPIs, generate recurring client reports + internal ops digest, narrate variances.
- Inputs
- Fill/attendance/timecard data
- Outputs
- Client reports · Ops digest · At-risk-account flags
- KPIs it moves
- Time-to-fill · Fill rate · No-show rate · Days-sales-outstanding
- Systems it usually runs on
- TempWorks (ATS) · Doc-gen
- Where a person stays in the loop
- External report send
What a blueprint is, and is not
A blueprint supplies the vocabulary, the typical steps, the KPIs and the approval points for a process. It is a starting point, not a pre-built agent: tacitrun builds the domain agents by reading your own procedure, tests them against cases derived from it, runs them in shadow beside your team, and holds every write for a person. Your IT connects the systems and approves before anything goes live.
Questions people ask
- How do I give an agent a reference document (e.g. a sample template) to use at runtime?
- Two places, both drag-and-drop: (1) for ONE agent, open it → Knowledge tab → drop the file on “Documents it can look up”; (2) for the WHOLE process (available to every agent in it), the process page has a “Documents for this process” card — drop it there. For example, drop a sample proposal template for a Proposal Generator. Whatever the format — PDF, Word, Excel, CSV, HTML, text, OR a screenshot/image (PNG, JPG, etc.) — we handle it: documents convert to clean markdown (tables and headings preserved, not a flattened blob), and images/screenshots are read by vision (Claude) which transcribes all the text and describes what’s in them (e.g. a screenshot of an invoice becomes a markdown table of its line items). Then we cap it to a sensible size for efficient token use, chunk and embed it so retrieval is sharp. It’s added immediately (no IT approval needed, nothing hardcoded) and shows in the document list. From then on the agent searches it live every run and uses it as a reference — e.g. it drafts new proposals in the shape of your template. To have it ALWAYS apply a rule instead of just look it up, use “Teach it” on the same tab (or the Rules tab for enforceable policies).
- What is the Salesforce Data Hygiene blueprint, and how do I use it?
- It’s a pre-built end-to-end process (a "crew" of 5 domain agents) that replaces the manual job of cleaning up messy CRM data and re-importing it. In the Catalog it shows as a Blueprint with the problem it solves, the outcomes it delivers, and the process mapped to each domain agent: (1) Data Quality Auditor profiles the object and reports duplicates/blanks/malformed/stale records; (2) Duplicate Finder & Merger proposes human-approved merges; (3) Field Standardizer normalizes phone/state/country/titles/casing; (4) Data Re-import Loader picks up a cleaned file (SFTP/SharePoint/Drive) and UPSERTS each row by external ID — so re-runs update the same record instead of creating duplicates; (5) Import Reconciliation Auditor verifies the load matched the source. Adopt each step from the blueprint; we build a private copy in your workspace that you can adapt, connected to your own Salesforce. Every write goes through human approval until you trust it.
- What’s a Skill vs a Blueprint?
- A Blueprint is a starter process template. A Skill is a reusable knowledge pack a domain agent loads on demand at runtime.
- Do you have blueprints for private equity / deal teams?
- Yes. Pick "Private equity" in Blueprints to get the full deal lifecycle (origination → diligence → execution & close with IC + signing gates → value creation → exit), plus the cross-portfolio value-creation playbook as standardized levers (working capital, FP&A, pricing/margin, spend analytics, JML access) that deploy identically across every portfolio company. Human-approval gates are built into the deal-close and IC steps. On Ingest, choosing "Private equity" also offers starter templates — Deal Sourcing & Screening, DD Red-Flag Log, IC Memo & Approval, and 100-Day & Value-Creation Plan.
Why offload this process to tacitrun’s AI operating layer
tacitrun is built for exactly this handoff: a business team describes the process it already runs, and the platform turns it into governed domain agents that work across the systems you have, under your IT’s approval, with every write waiting for a person.
- Built from your procedure, not a vendor template
- Describe the process in plain English or hand over the SOP. tacitrun compiles it into a process graph and composes one domain agent per step, so the agents carry your rules, your exceptions and your vocabulary.
- Tested against the process before it can act
- Evaluation cases are derived from the graph itself, so a passing agent is one that does what your process says. Then it runs in shadow beside your team on real work before anyone lets it act.
- Every write stops for a person
- The approval gate sits on the actual call to Salesforce, Shopify, SendGrid, SAP or any connected system. A person accepts, modifies or rejects; the corrected version is what executes; the trace keeps the record.
- Runs across the systems you already have
- Built-in connectors, your own REST APIs or MCP servers, and on the Enterprise plan your own cloud project and your own models. The systems of record stay where they are; the layer does the work between them.
- IT approves, business leads
- Business users build and prove; IT connects the credentials, binds the fields and approves before anything goes live. Neither side inherits the other’s risk.
Read next
- What is an AI operating layer?
- How do AI agents improve operational efficiency without adding risk?
- Enterprise: agents in your cloud, gated by your IT
- AI agents for Retail operations
- AI agents for Consumer goods operations
- AI agents for Manufacturing operations
- AI agents for Insurance — personal lines operations