What can AI agents take over in IT staffing & consulting operations?

tacitrun ships 9 IT staffing & consulting process blueprints — VMS requisition intake, MSP program scorecard & account review, Candidate sourcing & submittals and Initial phone screen and more — each stating its inputs, outputs, KPIs and the points where a person stays in the loop. They are the starting point: the domain agents themselves are built by reading your own procedure, and every write they make waits for your approval until they have earned autonomy.

Contract IT staffing through client VMS / MSP programs — requisition to submittal to placement, consultant compliance, bench and program performance.

Requisitions & program management

VMS requisition intake

Pick up requisitions a client releases in its VMS, read the full requirement (skills, rates, location, dates, client-defined fields) and open a matching job order in the ATS.

Inputs
VMS requisitions released to the supplier · Rate cards · Existing ATS job orders
Outputs
ATS job order linked to the VMS requisition · Requisitions skipped, with why
KPIs it moves
Time from VMS release to ATS job order · Duplicate job orders · Requisitions missed
Systems it usually runs on
VMS (Beeline) · ATS (JobDiva / Bullhorn)
Where a person stays in the loop
Job order creation in the ATS · A requisition outside the rate card

MSP program scorecard & account review

Assemble the supplier scorecard an MSP program measures — submittals per requisition, interview and fill ratios, time-to-submit, tenure — from the VMS and ATS, and draft the account review.

Inputs
VMS requisitions and candidates · ATS submittals and starts · VMS timesheets
Outputs
Program scorecard · Account review draft
KPIs it moves
Submittal-to-interview ratio · Interview-to-hire ratio · Time to first submittal · Fill rate
Systems it usually runs on
VMS (Beeline) · ATS (JobDiva / Bullhorn)
Where a person stays in the loop
Anything sent to the client or MSP

Sourcing, submittals & placement

Candidate sourcing & submittals

Search and rank consultants for a requisition, get the candidate’s right to represent in writing, record the submittal in the ATS and submit the candidate to the client’s VMS.

Inputs
Requisition · ATS candidate pool · Rate card
Outputs
Ranked shortlist with reasons · Right-to-represent confirmation · ATS submittal · VMS submittal
KPIs it moves
Time to first submittal · Submittals per requisition · Submittal-to-interview ratio · Duplicate-submission rate
Systems it usually runs on
ATS (JobDiva / Bullhorn) · VMS (Beeline) · Email
Where a person stays in the loop
Right-to-represent email · ATS submittal · VMS submittal (separate approval)

Initial phone screen

Initial phone screen: an AI screening call against the job and the client’s must-haves; a recruiter decides who moves on.

Inputs
Requisition · Client must-haves · Candidate record
Outputs
Transcript · Summary · Fit score with evidence
KPIs it moves
Time from shortlist to screened · Screens per requisition · Screened-to-submitted ratio
Systems it usually runs on
ATS (JobDiva / Bullhorn) · Phone
Where a person stays in the loop
The advance / decline decision · The ATS note

Client interview coordination

Coordinate client interviews for submitted consultants — propose times, book the calendar invite and log the outcome in the ATS.

Inputs
Interview request · Consultant and interviewer availability
Outputs
Booked interview · Outcome note in the ATS
KPIs it moves
Time to schedule · Interview no-show rate
Systems it usually runs on
Calendar · ATS (JobDiva / Bullhorn)
Where a person stays in the loop
Calendar invite to the client · Outcome note

Offer-to-start & consultant onboarding

Turn an accepted offer into a start: send the consultant agreement for signature, track the onboarding checklist and confirm the start with the client.

Inputs
Accepted offer · Start record · Agreement template
Outputs
Signed consultant agreement · Onboarding checklist status · Start confirmation
KPIs it moves
Offer-to-start days · Starts delayed by paperwork · Fall-off rate
Systems it usually runs on
ATS (JobDiva / Bullhorn) · E-sign (DocuSign)
Where a person stays in the loop
Agreement sent for signature · Start confirmation to the client

Consultant compliance & bench

Work-authorization tracking

Track each placed consultant’s work-authorization dates (H-1B, EAD, OPT/STEM OPT and others) and worksite changes, and draft what counsel needs to review — never deciding eligibility.

Inputs
Placed consultants · Work-authorization expiry dates · Worksite / assignment changes
Outputs
Expiry and worksite-change watch list · Drafts for immigration counsel
KPIs it moves
Days of notice before an expiry · Worksite changes reviewed before the move
Systems it usually runs on
ATS (JobDiva / Bullhorn)
Where a person stays in the loop
Every eligibility or filing decision (immigration counsel)

Bench management & redeployment

Find consultants rolling off or on the bench and match them to open requisitions before they leave.

Inputs
Assignment end dates · Open requisitions · Consultant skills
Outputs
Roll-off watch list · Redeployment matches with reasons
KPIs it moves
Bench days · Redeployment rate · Roll-offs with no match
Systems it usually runs on
ATS (JobDiva / Bullhorn) · VMS (Beeline)
Where a person stays in the loop
Any contact with the consultant or client

Time, billing & margin

Timesheet-to-invoice reconciliation

Reconcile approved VMS timesheets against ATS placements and rates before invoicing, and list every mismatch for a person to resolve.

Inputs
VMS timesheets · ATS placements and bill rates · Invoice run
Outputs
Reconciliation · Mismatches with their cause
KPIs it moves
Mismatches caught before invoicing · Invoice rejections by the VMS · Days sales outstanding
Systems it usually runs on
VMS (Beeline) · ATS (JobDiva / Bullhorn)
Where a person stays in the loop
Every correction (finance)

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 until the agent has earned autonomy. 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 index it so agents find the right passage. 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 governed domain agents run it across the systems you have, under your IT’s approval, with every write waiting for a person until the agent has earned autonomy.

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 until autonomy is earned
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, as a custom-priced Enterprise option, 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