1. Home
  2. Help
  3. Engines
  4. Pay App Review (Reconciler)
Field · Engine

Pay App Review (Reconciler)

Pay App Review (Reconciler) is the deterministic engine that reconciles a subcontractor's AIA G702/G703 pay application line by line. It checks every line against the project Schedule of Values and the Procurement tracker, flags math errors, over-billing, retainage drift and billed-but-undelivered material, and recommends an overall review result.

Engine Phase: Billing Runtime: 20-40 seconds Pro+

What is Pay App Review?

Pay App Review (Reconciler) is the deterministic counterpart to Pay App Audit. Where Pay App Audit is an LLM-only narrative review, this engine parses pay application text (typically AIA G702 summary plus G703 schedule-of-values detail) into structured line items, then reconciles every line against the project's stored Schedule of Values and the live Procurement tracker.

The output is auditable line-by-line: every flagged finding has a severity (info / warn / error), a category (math / billing / retainage / procurement), and a citation back to the original line. The engine persists each run to the pay_app_reviews table plus an engine_runs receipt row, so the full reconciliation is replayable and ties into the Engine Run Record drawer.

When should I use Pay App Review?

Use Pay App Review when a subcontractor pay application arrives and you must approve, dispute or reject it before the prime's billing deadline, when you want every flag tied to a G703 line item, or when billed material may not match what was delivered.

Pair with the Procurement Tracker

The reconciler reads procurement state automatically when include_procurement is enabled. Make sure deliveries are logged in Procurement before running the engine — undelivered material that wasn't logged will show up as a billing error rather than a real exception.

What do I upload to Pay App Review?

Required: pay application text (the G702 cover + G703 SOV detail, or any equivalent SOV table). The engine accepts pasted text or extracted PDF text. Optional but recommended: the project's Schedule of Values as a reference — if not provided, the engine treats the pay app's own SOV as the source of truth.

How do I run Pay App Review?

To run Pay App Review, open it, paste or upload the pay application, optionally paste the Schedule of Values, set the application reference, choose whether to cross-check procurement, run the analysis, review the findings table and read the recommendation.

  1. Open the engine

    Sidebar → Engines → Pay App Review (Reconciler) card (field phase, cyan accent).

  2. Paste or upload the pay application

    Drop the pay app PDF into the upload slot, or paste G702/G703 text directly. The engine reads a PDF's text layer — there is no OCR on this path, so a scanned pay app comes through empty. Paste the text when all you have is a scan.

  3. Optionally paste the SOV

    If the project's canonical SOV isn't already linked to the project, paste it here. The reconciler will use it as the reference; otherwise the pay app's own SOV is used.

  4. Set the application reference

    Enter the pay app number (e.g. "Pay App #14") — surfaces on the receipt and helps cross-reference downstream.

  5. Toggle procurement cross-check

    Default ON. When enabled, the engine fetches the project's procurement snapshot and flags any line billing for material that wasn't delivered.

  6. Run analysis

    20–40 seconds typical. Faster than narrative engines because most work is deterministic parsing + numeric reconciliation.

  7. Review the findings table

    Every flagged line shows severity, category, expected vs billed amounts, and a one-line reason. Sort by severity to see errors first.

  8. Read the recommendation

    The engine outputs one of: Approve / Approve with conditions / Dispute / Reject. The recommendation is rule-based — the rules are visible in the result so you can disagree with the recommendation while keeping the underlying findings.

How do I read the Pay App Review results?

The result has a header summary, a findings table with severity and category breakdowns, a recommended action and an Engine Run receipt.

Header summary

Contract sum, completed to date, retainage held, payment due, recommended review result. The single-glance scorecard. A sentence under it says what the payment due and the retainage are netted against, from the pay application's own figures: completed and stored to date, less retainage, less previous certificates, and the balance to finish. If the pay application's own figures do not add up, the sentence says so.

Findings table

One row per flagged line item. Columns: line number, description, billed amount, expected amount, variance, severity, category, reason. Click any row to see the underlying SOV line and procurement record (if applicable).

Severity breakdown

Counts by severity (info / warn / error). Drives the recommendation engine — any error blocks an Approve recommendation.

Category breakdown

Counts by category (math errors, over-billing, retainage drift, undelivered procurement). Helps you see whether the issue is the subcontractor's accounting (math) or the work itself (procurement).

Recommended action

Approve / Approve with conditions / Dispute / Reject. Includes the rule that fired (e.g. "1+ error severity findings → Dispute").

Engine Run receipt

One-click open of the Engine Run Record drawer — full input/output, model used, duration, cost. Persisted to engine_runs for audit trail.

Every control, explained

Application reference field

Free-text label for this pay app run (e.g. "Pay App #14"). Persisted on the result and shown in the run history.

Pay app text upload

The G702/G703 source. Required. Accepts a text-layer PDF or pasted text. A scan is not OCR'd here: it yields almost no characters and the run is refused (80-character minimum) rather than reconciled against nothing.

SOV upload (optional)

The reference Schedule of Values. If omitted, the engine uses the pay app's own SOV as the reference.

Contract retainage % override

Defaults to the project's stored retainage rate. Override here if this pay app has a non-standard rate (e.g. 5% after substantial completion).

Include procurement

Toggle. ON = fetch the project's procurement snapshot and cross-check billed-vs-delivered material. OFF = SOV reconciliation only.

Run analysis

Executes the reconciliation. Consumes one engine run. ~20–40 seconds.

Sort by severity

Re-orders the findings table to show errors first, then warnings, then info.

Chain → Procurement Tracker

Jumps to the procurement tracker filtered to this pay app's line items. Useful when the recommendation says "Dispute — undelivered material."

What is the difference between Pay App Review and Pay App Audit?

Trueleveler ships two engines with similar names but different jobs. Pay App Review (Reconciler) — this engine — is deterministic, parses every line, and produces a structured findings table backed by the pay_app_reviews table. Pay App Audit is LLM-only and produces a narrative review with judgment calls (front-loading, schedule-of-values drift, retainage strategy). Use this engine when you need an auditable line-by-line reconciliation; use the audit when you want a senior PM's narrative read.

Sources