Insights
Notes from building AI systems that have to hold up.
Written for the people who have to approve, defend and maintain these workflows.
- Engineering2026-09-038 min read
Bounding Agent Authority in Property Maintenance Dispatch
How to design agentic workflows for tenant maintenance requests that limit financial exposure, mandate human approval for costly repairs, and maintain rigorous unit economics per door.
Read - Engineering2026-08-058 min read
Shipping AI inside a multi-tenant property platform
Retrieval isolation, per-portfolio configuration, evaluation across thousands of small customers, and cost budgets that hold at platform scale.
Read - Governance2026-07-147 min read
What an auditable agent trajectory actually contains
Logging the prompt and the answer is not an audit trail. Here is the record a regulated firm needs to reconstruct any AI-assisted decision.
Read - Governance2026-06-247 min read
AI rent underwriting that survives a fair-lending review
Adverse-action reasons, disparate-impact testing and per-applicant explainability: what a model-assisted rental or credit decision has to produce before counsel will sign off.
Read - Engineering2026-06-026 min read
Reproducibility is the feature financial firms are actually buying
Non-deterministic output is the single most common reason an AI pilot fails risk review. The fix is engineering discipline, not a better model.
Read - Strategy2026-05-136 min read
Applicant screening agents: where the model helps and where it must not decide
Document reading, income verification and fraud signals are a good fit for a model. Approve and deny are not. A practical dividing line for screening workflows.
Read - Engineering2026-04-228 min read
The harness matters more than the prompt
Prompt quality plateaus quickly. The scaffolding around the model — contracts, validation, retries, routing, evaluation — is what makes a workflow dependable.
Read - Engineering2026-03-267 min read
Reconciling rent, fees and disbursements with agentic workflows
Money movement workflows need ledger-grade reliability. Idempotency, tolerance rules, exception queues, and why a payments agent should propose entries rather than post them.
Read - Strategy2026-03-056 min read
Choosing the first workflow in a regulated firm
The first agentic workflow should be chosen for reviewability and reversibility, not for impressiveness. A practical selection framework.
Read - Governance2026-02-198 min read
Automating Arrears Workflows: Bounding Agent Behavior in Tenant Defaults
How to design agentic workflows for rent collections that respect local compliance timelines, mandate human review for statutory notices, and control the unit economics of default management.
Read - Strategy2026-02-058 min read
Agentic Workflows for AML Alert Triage: Structuring the Pre-Investigation
How to deploy agentic systems to investigate transaction monitoring alerts, enforcing strict boundaries between automated data gathering and human disposition.
Read - Engineering2026-01-198 min read
Agentic Workflows for Earnings Season Triage: Bounding Extraction and Enforcing Thesis Verification
How hedge funds can deploy agentic systems to parse concurrent earnings releases and expert transcripts, enforcing strict extraction schemas and mandating human approval gates before thesis updates.
Read - Strategy2026-01-058 min read
Agentic Workflows in Deal Due Diligence: Enforcing Verification in Data Room Extraction
How private equity and venture capital firms can design agentic workflows to parse virtual data rooms, mandate human verification of extracted liabilities, and control the unit economics of deal screening.
Read - Strategy2025-12-198 min read
Agentic Exception Handling in Member Servicing: Structuring AI for Credit Union Operations
How credit unions can design agentic workflows for member requests that enforce policy consistency, mandate human approval for financial concessions, and maintain strict unit economics.
Read - Strategy2025-12-058 min read
Bounding Agent Authority in Claims First Notice of Loss: Structuring AI for Triage and Routing
How insurance carriers can design agentic workflows for claims intake that enforce policy constraints, mandate adjuster review for coverage decisions, and control the unit economics of loss processing.
Read - Strategy2025-11-198 min read
Agentic Workflows for Client Portfolio Reviews: Enforcing Assertions and Compliance
How wealth management firms can deploy agentic workflows to synthesize quarterly client reviews, mandating strict separation of performance data from language models and enforcing advisor approval gates.
Read - Engineering2025-11-058 min read
Agentic Workflows for Covenant Monitoring: Bounding Extraction in Private Credit
How private credit firms can deploy agentic workflows to automate covenant compliance monitoring, enforce strict mathematical determinism, and maintain human approval gates for breach determinations.
Read - Engineering2025-10-208 min read
Agentic Workflows for Commercial Lease Abstraction: Enforcing Verifiable Extraction
How to design agentic workflows for commercial lease abstraction that guarantee accuracy through source-grounding, enforce rigid extraction schemas, and incorporate a human-in-the-loop validation interface.
Read - Engineering2025-10-068 min read
Agentic Workflows for Chargeback Representment: Bounding Evidence Compilation
How fintechs can deploy agentic systems to structure dispute evidence, enforce network rule compliance, and maintain human approval gates for chargeback representment.
Read - Governance2025-09-198 min read
E-Discovery Readiness for Agentic Workflows: Preserving the Decision State
How in-house counsel must architect agentic workflows to support litigation holds, preserve complete decision trajectories, and survive e-discovery scrutiny.
Read - Strategy2025-09-056 min read
Agentic Workflows for Prior Authorization: Structuring Extraction and Enforcing Clinical Gates
How healthcare practices can deploy agentic systems to extract clinical evidence for prior authorizations, enforcing strict boundaries against medical inference and mandating human approval gates.
Read - Strategy2025-08-198 min read
Agentic Workflows in Executive Search: Bounding Sourcing and Outreach Drafts
How executive search firms can deploy agentic workflows for candidate mapping, enforcing strict extraction schemas, protecting client confidentiality, and mandating human approval gates for outreach.
Read - Engineering2025-08-058 min read
Bounding Agent Authority in Field Service Diagnostics and Quoting
How home and field service operators can design agentic workflows to parse OEM manuals and draft repair quotes while enforcing strict human approval gates for parts procurement and customer pricing.
Read - Strategy2025-07-218 min read
Agentic Workflows for RFP Response Generation: Bounding Synthesis and Protecting Firm IP
How professional services firms and agencies must structure agentic workflows to automate RFP responses while enforcing retrieval isolation, preventing capability hallucination, and mandating human approval for scoping commitments.
Read - Governance2025-07-078 min read
Agentic Workflows for Security Deposit Disposition: Bounding Deductions and Evidentiary Packaging
How property operators can deploy agentic systems to correlate inspection reports with vendor invoices, enforcing compliance timelines and mandating human approval gates for deposit deductions.
Read - Strategy2025-06-198 min read
Agentic Workflows for Trade Finance Discrepancy Checks: Bounding Document Examination
How banks can deploy agentic workflows to examine letter of credit presentations, enforcing strict UCP 600 rules mapping and mandating human approval gates for discrepancy waivers.
Read - Engineering2025-06-058 min read
Agentic Workflows for Alternative Data Ingestion: Bounding Discretion in Unstructured Pipelines
How hedge funds can deploy agentic workflows to normalize alternative data streams, enforcing strict extraction schemas, preventing unit hallucination, and routing exceptions to human analysts.
Read - Governance2025-05-198 min read
Agentic Workflows for LP Reporting: Bounding Narrative Generation and Data Reconciliation
How private equity and venture capital firms can deploy agentic workflows to synthesize portfolio company updates, enforce data isolation, and mandate human approval gates for quarterly LP reporting.
Read - Strategy2025-05-058 min read
Agentic Workflows for Field-of-Membership Verification: Bounding Extraction and Eligibility
How credit unions can design agentic workflows for field-of-membership verification, enforcing strict boundaries between data extraction and charter compliance decisions.
Read - Engineering2025-04-218 min read
Agentic Workflows for Subrogation Demand Processing: Bounding Extraction and Liability Assessment
How insurance carriers can deploy agentic systems to parse incoming subrogation demands, enforcing rigid evidence schemas and mandating human approval gates for settlement negotiations.
Read - Engineering2025-04-078 min read
Agentic Workflows for Cost Basis Reconciliation: Bounding Extraction in Wealth Management Onboarding
How wealth management firms can deploy agentic systems to parse unstructured legacy statements during asset transfers, enforcing strict mathematical determinism and mandating human approval gates before posting tax lots.
Read - Strategy2025-03-198 min read
Agentic Workflows for Amendment and Waiver Processing: Structuring the Investment Committee Memo
How private credit firms can design agentic workflows to parse borrower amendment requests, cross-reference credit agreements for voting thresholds, and stage memos for committee review.
Read - Engineering2025-03-058 min read
Agentic Workflows for Vendor Compliance: Bounding COI Extraction and Verification
How commercial real estate operators can design agentic workflows to parse Certificates of Insurance, enforcing deterministic logic for compliance checks and mandating human approval for vendor authorization.
Read - Engineering2025-02-198 min read
Agentic Workflows for KYB Onboarding: Bounding Beneficial Ownership Extraction
How fintechs can deploy agentic systems to unwrap complex beneficial ownership structures, enforce rigid extraction schemas, and mandate human approval gates for KYB compliance.
Read
Next step
Find your best AI workflow opportunity
A 30-minute discovery call: we look at two or three of your current processes and tell you plainly which are worth automating and which are not.