Origination & underwriting
Loan application intake & document collection
Intake an application across channels, verify identity, pull bureau + bank/income data, and assemble a complete, decision-ready file — chasing only the missing stipulations.
- Inputs
- Application (web / partner / phone) · ID + income / bank docs · Consent & disclosures
- Outputs
- Decision-ready file · Stipulation request · Fraud / IDV flag
- KPIs it moves
- Pull-through rate · Time-to-decision-ready · Doc-completeness rate · Fraud catch rate
- Systems it usually runs on
- Loan origination (nCino / Blend / MeridianLink) · Plaid · IDV (Socure / Persona) · Credit bureau
- Where a person stays in the loop
- Identity / fraud exception · Adverse documentation
Underwriting & credit decisioning support
Apply the credit policy to a complete file — bureau, DTI, income, fraud signals — auto-approve clean-within-policy cases, and route everything else to an underwriter with the analysis assembled. Never auto-denies credit.
- Inputs
- Decision-ready file · Credit policy / scorecard · Bureau + income / DTI
- Outputs
- Clean-within-policy approval · Underwriter review packet · Counter-offer scenarios
- KPIs it moves
- Auto-decision rate · Approval accuracy · Decision cycle time · Early-default rate
- Systems it usually runs on
- LOS / decision engine · Credit bureau + FICO · Income / DTI verification
- Where a person stays in the loop
- Any adverse action / denial — human + ECOA notice · Policy exception / override · Rate / term exception
Funding & disbursement readiness
Confirm all stipulations cleared, run final KYC / OFAC, validate the disbursement target, and stage the loan for funding — funding itself is a gated human action.
- Inputs
- Approved loan · Cleared stipulations · KYC / OFAC + bank verification
- Outputs
- Funding-ready package · Held / exception case
- KPIs it moves
- Time-to-fund · Stip-clear cycle time · Funding error rate
- Systems it usually runs on
- LOS · KYC / OFAC · Payment processor · Core servicing
- Where a person stays in the loop
- Fund release / disbursement authorization · OFAC / KYC hit
Servicing & debt resolution
Debt-settlement case management & creditor negotiation
Manage a member’s enrolled debts: prioritize accounts, prepare settlement offers within set authority, track creditor responses, and route every settlement authorization to a human.
- Inputs
- Enrolled debts + balances · Member dedicated-account funds · Settlement authority / policy
- Outputs
- Prepared settlement offer · Negotiation status · Authorization request
- KPIs it moves
- Settlement rate · Avg settlement % · Time-to-first-settlement · Member completion rate
- Systems it usually runs on
- Debt-settlement platform · Dedicated-account / escrow · Creditor portals · CRM (Salesforce FSC)
- Where a person stays in the loop
- Settlement acceptance / authorization · Funds movement
Collections & hardship handling
Run compliant, segmented outreach on delinquent accounts, intake hardship / forbearance requests, and route arrangements and any consumer-impacting action to a human.
- Inputs
- Delinquent account · Payment history · Hardship request
- Outputs
- Compliant outreach · Proposed arrangement · Hardship case
- KPIs it moves
- Roll / cure rate · Promise-to-pay kept % · Right-party-contact rate · Complaint rate
- Systems it usually runs on
- Collections system · Core servicing · Dialer / comms · Payment processor
- Where a person stays in the loop
- Payment arrangement / settlement approval · Hardship / forbearance grant
Member onboarding & enrollment
Guide a new member through program / loan enrollment — disclosures, dedicated-account setup, expectations — and confirm a complete, compliant enrollment.
- Inputs
- Enrolling member · Program / loan terms · Required disclosures
- Outputs
- Completed enrollment · Dedicated account set up · Welcome + plan
- KPIs it moves
- Enrollment completion · Time-to-activate · Early-attrition rate · Disclosure compliance
- Systems it usually runs on
- CRM (Salesforce FSC) · Debt-settlement / loan platform · Dedicated-account · E-sign (DocuSign)
- Where a person stays in the loop
- Suitability / affordability exception
Digital member self-service
Member self-service (status, payments, payoff)
Resolve common member requests digitally — application / loan status, payment, payoff quote, document upload — with guided answers and deflection.
- Inputs
- Member request (web / app) · Loan / account data · Payment history
- Outputs
- Self-serve resolution · Payoff quote · Escalation when needed
- KPIs it moves
- Digital containment · Self-serve adoption · CSAT · Call deflection
- Systems it usually runs on
- Member portal / app · Core servicing · Payment processor
- Where a person stays in the loop
- Dispute / hardship / exception
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