Airclerk helps banks and lenders put AI to work on the document load behind a lending decision: the application evidence assembled and checked against policy, the credit memo drafted in the lender's own format, the gaps named before the file reaches the person who decides. The credit decision, pricing and sign-off stay with authorised lending staff, inside their delegated authority.
Illustrative example
Our lending practice is at an early stage. The first workflow is developed with your credit and risk team rather than installed from a finished playbook.
A business term loan application, assembled into a draft credit memo in the lender’s own format and checked against its credit policy before anyone with authority opens it. The workflow prepares the file. A person decides. Illustrative lender and borrower; no real customer.
Four checks under one section. One is complete and cited, one sits below a policy line and says so plainly, one rests on a document that was mentioned but never sent, and one makes sure the file lands with someone entitled to decide it. The credit officer opens a memo that already knows where its own weak points are.
The line the workflow does not cross: it never approves, declines, prices, conditions or sets a limit, and it does not recommend an outcome. It assembles the evidence, applies the lender’s checklist, names what is missing and routes the file within delegated authority. The decision, and the responsibility for it, stay with the person whose name goes on the approval.
The same discipline runs through nine other workflows, from onboarding to covenant monitoring →
Banks and lenders use AI models such as Claude, Microsoft Copilot or ChatGPT to support document-heavy work around lending decisions: credit memo drafting, affordability and serviceability assessment, responsible-lending file completeness, KYC and onboarding, collections and hardship correspondence, covenant monitoring and credit-committee papers. The assistant can be connected to the lender's core banking or loan origination system, document store, CRM and approved templates. Customer isolation, source citations and credit-officer approval are built into the workflow. The AI supports the work around the credit decision. It does not replace affordability assessment, responsible-lending judgement, pricing decisions or final loan approval.
These are starting patterns, not a packaged lending suite. Each workflow is adapted to the lender's product set, systems, credit policy and delegated authority. Each is a candidate first workflow.
Turns the application, financials, security information and credit history into a first-draft credit memo in the lender's own format. Key ratios, exposures, assumptions and open questions are separated out for the credit officer to check and sign off.
Assembles income, expense, liability and commitment evidence from the application and supporting documents against the lender's affordability policy. Flags missing evidence, inconsistent figures or thresholds not met, for a credit officer to review before a decision is reached.
Checks a consumer credit file against the lender's responsible-lending checklist: the required affordability inquiry, suitability assessment, disclosures and evidence. Surfaces gaps before the file goes to decision, rather than when a complaint or review arrives afterwards.
Assembles identity, source-of-funds and beneficial-ownership information from application documents against the lender's KYC and AML/CFT requirements. Identifies missing or inconsistent information for the onboarding team to resolve. Verification decisions and risk ratings remain with authorised staff.
Drafts collections and hardship correspondence from the account history, arrears position and any hardship application, following the lender's approved wording and required disclosures. Nothing is sent to a customer without review, and hardship decisions stay with authorised staff.
Extracts the circumstances, evidence and requested relief from a hardship application and checks it against the lender's hardship policy and any statutory requirements. Prepares a summary and recommendation for the hardship team; the outcome decision is theirs.
Tracks financial and non-financial covenants against a business or commercial facility, drawing on periodic financial statements, compliance certificates and correspondence. Flags approaching or breached covenants, missing reporting and required waivers for the relationship manager or credit team to act on.
Assembles the material for a business borrower's periodic credit review: updated financials, security position, covenant compliance, conduct of the account and any changes since the last review. Produces a draft review paper for the credit officer to complete and approve.
Classifies incoming customer and broker correspondence by product, urgency and required action. Drafts responses for routine queries, identifies items needing a credit or compliance decision, and escalates anything outside the workflow's boundary. Nothing is sent without approval.
Builds the standard credit-committee paper from the memo, financials, covenant position and prior committee notes, in the lender's own template. Assumptions, exceptions and matters requiring committee discussion are surfaced rather than smoothed over. The committee makes the decision.
Optional AI Process Assurance can sit behind the workflows we implement: the evidence, exceptions, review changes and sign-off retained as an AI Workpaper, so the lender can show what the AI did, what it did not do, how the result was checked and who approved it. It is a platform subscription, implemented alongside the workflow, and the workflow runs without it.
A free introductory conversation is enough to say whether the workflow you have in mind is a first workflow, and to quote a fixed fee for it. The detailed design happens inside the engagement, with your credit and risk team, against your own policy and systems.
Where AI could make the biggest difference, how that work runs today, the systems it touches and who owns it. We also work out together whether Airclerk is the right partner for it. If we are, the conversation gives us enough to quote.
One document: the outcome we are aiming for, what we deliver, what your team contributes, the fixed fee and timeline, and what acceptance looks like. Nothing starts until it is agreed on both sides.
The engagement opens with the detailed design, agreed with you before anything is built. Then we configure and connect the workflow to your documents and systems, build in the agreed review controls and audit trail, test it on real work, and prepare the people who will run it.
Handover, and the support that follows go-live, are written into the scope so you know what is covered before you sign. Ongoing operations and further workflows are a separate agreement, made when you want them rather than switched on by default.
Read how an engagement runs in detail →
Airclerk can implement Claude, Microsoft Copilot or ChatGPT depending on the lender's existing environment. Workflows run on the lender's approved enterprise instance and under its own vendor agreement.
The first workflow is chosen by volume, source availability, repeatability, review effort and credit risk. For many lenders that means credit memo drafting, affordability file assembly, responsible-lending completeness checks, covenant monitoring or credit-committee papers. Final approvals, pricing decisions, hardship outcomes and covenant waivers remain outside the first workflow.
Each workflow defines who reviews what: credit officer, relationship manager, credit committee or another authorised reviewer at the correct delegated authority level. The workflow stops at that boundary. It does not send a decision to a customer, approve a facility, waive a covenant or issue a hardship outcome by itself. The AI Workpaper records which evidence was used, what exceptions were raised, what changed during review and whether any required gate was missed.
The workflow is evaluated against held-out examples from the lender's own completed decisions. Does it correctly identify missing affordability evidence instead of inventing it? Does it respect delegated authority limits? Does it maintain customer and facility isolation? Does it flag rather than resolve a policy exception? Cross-customer leakage, prompt injection and false-completeness checks form part of the production gate.
The engagement produces: the configured workflow on the lender's approved AI platform and systems; a Workflow Charter defining its stages, permitted sources and approval gates; a clear boundary statement describing what the workflow must never decide or do; evaluation results from held-out file testing; a runbook for credit, collections and operations staff; training appropriate to each role; a retained AI Workpaper for each material run; the check-ins after go-live that confirm the workflow is being used safely, shaped to the firm and written into the scope. Ongoing operations beyond that are a separate agreement.
The first production workflow should not ask the AI to approve or decline an application, set pricing, determine a credit limit, make a hardship outcome or grant a covenant waiver. Those decisions stay with the lender's authorised credit staff, operating within their delegated lending authority. The AI fits around that authority: assembling the evidence, checking it against policy, drafting the narrative and surfacing what's missing or inconsistent, so the person making the decision has a more complete file, faster.
The most useful lending knowledge is rarely contained in a generic prompt. It sits in the lender's affordability policy, credit memo templates, delegated authority matrix, product terms, hardship policy and the judgement of its experienced credit staff. Airclerk works with the lender's own credit and risk team to turn those into repeatable AI skills, rather than imposing a generic lending playbook built for a different institution's risk appetite.
A workflow that drafts a recommendation above someone's delegated lending authority, or bypasses a required approval step, is a control failure whether or not the recommendation turns out to be right. The workflow is built to route to the correct authority level and stop there, and the AI Workpaper records whether that gate was met.
The objective is not to make the AI the credit officer. It is to make the application file more complete before a credit decision is made: the right evidence assembled, the affordability checklist applied, exceptions visible, sources identified and approval gates followed. The credit officer reviews the draft with its source references and the gaps it could not close.
Banks and lenders can use AI to support the document-heavy work behind lending decisions: credit memo drafting, affordability and serviceability assessment, responsible-lending file completeness checks, KYC and onboarding support, collections and hardship correspondence, covenant monitoring, and credit-committee papers. Airclerk implements these as governed workflows connected to the lender's approved core banking, loan origination, CRM and document systems. Credit decisions, exceptions and final sign-off stay with authorised lending staff.
Not in the workflows Airclerk recommends as a starting point. The AI can assemble the application file, check it against the lender's affordability and responsible-lending checklist, draft the credit memo narrative, and flag missing evidence or inconsistencies. It does not become the credit decision-maker. The approval, decline, pricing decision and any conditions remain with the lender's authorised credit staff, operating within their delegated lending authority.
Since 1 July 2026, the FMA has been New Zealand's single conduct regulator for consumer credit, having taken over from the Commerce Commission under the Credit Contracts and Consumer Finance Act. Certified lenders were deemed into an FMA market services licence at transition, and the FMA has said it expects lenders to have clear, well-documented policies and processes and will take a proactive, risk-based approach to supervision. Responsible-lending obligations already turn on how a decision was reached. In Airclerk's view, as AI moves into affordability assessment, pricing or collections, that question extends to the AI-assisted parts of the process too, and a platform's activity logs alone are unlikely to answer it.
Both. Consumer credit in New Zealand sits under the CCCFA and, since 1 July 2026, FMA supervision; in Australia, consumer credit sits under the National Consumer Credit Protection Act and ASIC. Business-purpose lending generally sits outside consumer-credit statute, and most non-bank business lenders aren't prudentially supervised either - the obligations that do apply come from privacy and AML/CFT law, the lender's own credit policy, covenant and facility terms, and, for banks and other prudentially supervised institutions, regulatory capital and risk requirements. Our lending practice is at an early stage, so we develop these workflows with the lender's credit and risk team rather than installing a finished playbook. Business lending workflows tend to centre on credit memo drafting, covenant monitoring and periodic financial review rather than affordability assessment, but the same discipline of evidence, review and retained proof applies.
Two controls come first. Customer and matter isolation: information for one applicant, borrower or facility is walled off from another's file. Permission-aware access: the workflow sees only the customer material the person running it is already authorised to access in the lender's existing systems, consistent with delegated lending authority and privacy obligations. Before customer information is connected, Airclerk reviews the AI vendor's enterprise terms, retention, training use, subprocessors and data-location arrangements. The implementation runs on the lender's approved enterprise instance, under its own agreement with the AI provider.
AI Process Assurance records the work that passes through an instrumented lending workflow. A Workflow Charter defines the expected path: the required evidence, authority limits and approval gates. A Semantic Audit records what actually happened during the run. The retained AI Workpaper shows the evidence used, exceptions raised, review changes and final approval for a specific decision. It does not claim to capture everything a lender does. It creates a reviewable record for the AI-assisted lending workflows the institution chooses to govern.
The approach applies to banks, non-bank consumer lenders, finance companies and business or commercial lenders in New Zealand and Australia. The first workflow is selected around the lender's actual work and book, not a generic lending template. A consumer finance company assessing affordability and a bank's business banking team monitoring covenants may share the same underlying discipline: evidence assembled, checklist applied, exceptions flagged, decision retained.
We are not aware of a packaged, configured Claude for Lending product, and we would be cautious of one built entirely off the shelf. Anthropic does offer Claude for Financial Services as a platform-level capability, but it is not a substitute for configuring the workflow around a specific lender's credit policy, delegated authority, origination system and governance requirements - which vary too much between lenders for a generic package to be installed safely. AI features inside core banking, loan origination and CRM platforms are useful too, and Airclerk does not try to replace them. What we build is the workflow layer that crosses systems and follows the lender's own process: pulling the required evidence from the origination system and document store, applying the lender's affordability and credit checklist, drafting the memo, routing it to the authorised credit officer, and retaining the evidence of review. The lender brings its credit staff, systems, policy and delegated authority; Airclerk brings the implementation method, governance controls and workflow architecture. The first engagement starts with a first conversation and runs as a co-design process. We implement Claude, Microsoft Copilot and ChatGPT; the platform is chosen around your systems and the work.
Bring the file that takes longest to get in front of a decision-maker: the credit memo, the affordability pack, the annual review. An introductory conversation is enough to say whether it is a first workflow and what it would cost to build.