Utilization Management & Claims
Pended & exception claims adjudication
Triage claims that fail auto-adjudication: classify the pend reason, gather data across systems, auto-resolve deterministic pends, and route judgment calls to an examiner.
- Inputs
- Pended 837 claim · Member eligibility + accumulators · Provider contract + fee schedule
- Outputs
- Adjudicated claim · Examiner review packet · SIU referral
- KPIs it moves
- Auto-adjudication rate · Pend resolution cycle time · Cost per claim · Prompt-pay compliance
- Systems it usually runs on
- Core admin platform · Clearinghouse (837/835) · Code-edit engine
- Where a person stays in the loop
- Pricing/contract exception · Medical-record-required review · FWA referral
Member appeals & grievances
Classify appeal vs grievance, determine the regulatory track and clock, assemble the case file, and route to the right reviewer with the acknowledgment drafted.
- Inputs
- Appeal/grievance submission · Original determination · Claim/auth + records
- Outputs
- Classified + clocked case · Assembled case file · Acknowledgment + resolution letters
- KPIs it moves
- Timeliness compliance · Overturn rate · Cycle time · Misclassification rate
- Systems it usually runs on
- Core admin + A&G case system · Document management · Correspondence
- Where a person stays in the loop
- Determination by independent reviewer (clinical overturn requires clinician)
Coordination of benefits & overpayment recovery
Detect other-coverage and overpayments, establish primary/secondary order, and pursue recovery or adjustment.
- Inputs
- Claim + other-coverage indicators · Payment history · COB rules
- Outputs
- COB order · Recovery / adjustment case
- KPIs it moves
- Recovery rate · COB accuracy · Days-to-recover
- Systems it usually runs on
- Core admin platform · COB vendor · Recovery workflow
- Where a person stays in the loop
- Recovery pursuit / write-off decision
Provider & Member Operations
Provider credentialing & re-credentialing
Run primary-source verification and exclusion screening, flag adverse findings, and assemble a committee-ready file.
- Inputs
- CAQH application · License / DEA / board data · Exclusion lists
- Outputs
- Committee-ready file · Clean-file consent agenda · Flagged exceptions
- KPIs it moves
- Credentialing cycle time · PSV accuracy · Clean-file rate · On-time re-cred %
- Systems it usually runs on
- CAQH ProView · NPPES / state boards · OIG-LEIE / SAM / NPDB · Credentialing system
- Where a person stays in the loop
- Credentialing Committee / Medical Director approval · Adverse-finding review
Provider data / roster load & directory accuracy
Validate, dedupe, and load provider roster updates against the provider master and keep the public directory accurate within mandated windows.
- Inputs
- Group roster / change request · Provider master · NPPES
- Outputs
- Loaded provider record · Updated directory · Rejected rows with reasons
- KPIs it moves
- Directory accuracy · Auto-load rate · Roster turnaround · Mandated-window compliance
- Systems it usually runs on
- Provider master / network mgmt · NPPES / CAQH · Public directory
- Where a person stays in the loop
- Conflict resolution · Contract-linkage exception
Member enrollment & eligibility (834)
Process inbound 834 enrollment files: validate, apply adds/changes/terms, and reconcile discrepancies so downstream eligibility is correct.
- Inputs
- 834 enrollment file · Plan/benefit config · Premium/payment file
- Outputs
- Applied enrollment · ID card trigger · Reconciliation exception
- KPIs it moves
- Auto-apply rate · 834 cycle time · Reconciliation accuracy · Eligibility error rate
- Systems it usually runs on
- Core admin (enrollment) · EDI 834 / CMS-MARx · ID card + fulfillment
- Where a person stays in the loop
- Exception resolution · Retro-enrollment beyond window
Member services inquiry triage
Classify inbound member contacts, pull eligibility/benefit/claim context, draft the resolution, and route true exceptions to a representative.
- Inputs
- Member contact (call/chat/portal) · Eligibility + benefits · Claim/auth status
- Outputs
- Drafted resolution · Case + routing · Knowledge-grounded answer
- KPIs it moves
- First-contact resolution · Average handle time · CSAT · Containment rate
- Systems it usually runs on
- Core admin platform · CRM / service platform · Knowledge base
- Where a person stays in the loop
- Coverage/benefit exception · Escalation / complaint
Digital member & provider self-service
Member self-service (claim status, ID card, benefits)
Resolve common member requests digitally — claim status, digital ID card, benefit/accumulator lookups — with deflection and guided answers.
- Inputs
- Member request (web/app) · Eligibility + benefits · Claim history
- Outputs
- Self-serve resolution · Digital ID card · Escalation when needed
- KPIs it moves
- Digital containment · Self-serve adoption · CSAT · Call deflection
- Systems it usually runs on
- Member portal / app · Core admin platform · Eligibility (270/271)
- Where a person stays in the loop
- Coverage dispute / benefit exception
Provider portal auth & claim status
Answer provider portal/EDI status inquiries (auth status, claim status, eligibility) and surface what is needed to clear a pend.
- Inputs
- Status inquiry (277/portal) · Auth + claim records · Provider identity
- Outputs
- Status response · Required-action summary
- KPIs it moves
- Inquiry deflection · Response time · Portal adoption
- Systems it usually runs on
- Provider portal / Availity · Core admin platform · EDI (276/277)
- Where a person stays in the loop
- Disputed status / 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