AI Agents
Discovery Express

Finance & back office

Reconciliation Agent

Matches bank, gateway and ledger every morning, and leaves your team only the exceptions.

In productionReviewed September 3, 2026
Slack / Teams · Reconciliation
Demo data

  1. Daily close

    Yesterday: 4,180 bank lines, 3,905 gateway settlements, 4,012 ledger entries.

  2. Agent

    3,946 matched, 66 open. Sixty are the gateway holding weekend payouts. Six are real: same amount, two different references.

  3. NetSuite · 3,946 matches posted · 6 exceptions written with evidence · no adjusting entry posted

  4. Handoff to a person

    Accounting resolves the six and approves the adjusting entries. Each resolution becomes a matching rule so the pattern stops returning.

Slack / TeamsNetSuiteSAPQuickBooks
KPI it moves
Close 2 to 4 days shorterMeasured
Channels
Internal appsSlack / TeamsEmail
Integrates
  • NetSuite
  • SAP
  • QuickBooks
  • Your bank feeds
  • Payment gateways
An accountant comparing bank statements against a ledger at sunrise in Monterrey
Finance & back office

What it does

Bank, gateway and ledger matched every morning. Only the exceptions left.

Where it lives

Your cloud, your repo, your IP.

1. Receives 2. Looks up 3. Decides 4. Acts 5. Escalates 6. Learns

Systems it integrates

  • NetSuite
  • SAP
  • QuickBooks
  • Your bank feeds
  • Payment gateways

Reconciliation Agent

03Decides

Channels

  • Internal apps
  • Slack / Teams
  • Email

A person on your team

01

Receives

Pulls the day's bank statements, gateway settlements and ledger entries on schedule.

02

Looks up

Normalizes amounts, dates, currencies and references across systems that never agree on format.

03

Decides

Matches one to one, one to many and partials, and separates what is a real exception.

04

Acts

Posts the matches, and writes each exception with the probable cause and the evidence attached.

05

Escalates

Sends differences above your threshold and anything that looks like a duplicate to accounting.

06

Learns

Turns each resolved exception into a matching rule so that pattern stops coming back.

KPI it moves

Measured, with the source.

Every figure has a row in the Proof Ledger: source, date, owner and client permission.

Proof Ledger
Measured

Measured

2 to 4 days shorter

Monthly close

Range observed across deployments of this agent, Sep 2026

Measured

88% to 96%

Lines matched without a person

Range observed across deployments of this agent, Sep 2026

Measured

Under 4 minutes

Time per exception

Range observed across deployments of this agent, Sep 2026

Reviewed September 3, 2026

How it is governed

Every action has an owner, an eval and a limit.

Set in the Blueprint, enforced by the Govern layer of the platform.

Govern · Approval queue
Demo data

Waiting for a person

Adjusting entry for a $3,180.40 difference · accounting decides

Gateway settlement, Sep 14

Weekly eval

Passing

Match precision against the manual close

99.1%

Last 8 runs
96.0% → 99.1%

Monthly sample audit passed

Limit, enforced

Entry dated Aug 31 blocked · period closed

Human approvals

  • Any adjusting entry, always by accounting
  • Write-offs of unmatched differences

Typical evals

  • Match precision and recall against the manual close
  • Exception rate and time to resolve per cause

Limits

  • It never posts an adjusting entry on its own
  • No changes to closed periods

Time to production

8 to 12 weeks

of pilot to production under a KPI Contract, after a Blueprint of 1 to 2 weeks

The agent already runs in production elsewhere, so the 2 to 4 weeks of tuning inside the pilot go to your policies, your data and your systems, not to the model.

DaCodes delivery standard, Sep 2026. Integration is the long pole, not the model.

How we deploy
The four phases
Commitment gate

  1. 01Discovery Express

    2 sessions, no cost

  2. 02Blueprint

    1 to 2 weeks

  3. 03Pilot

    8 to 12 weeks

  4. 04Scale & Managed

    Continuous

  • Pilot, first 8 weeks
  • Up to week 12 of the pilot
  • This agent: 2 to 4 weeks of tuning, inside the pilot
  • Commitment gate: the KPI decides Scale

Proof and demo

What backs the label.

Proof Ledger note

In production

Measured in a real deployment and logged in the Proof Ledger with source, date and owner.

Reviewed September 3, 2026

Where this agent sits on the maturity policy

  1. Reference architecture
  2. Pilot
  3. In productionToday

The Discovery Express shows this agent on your data, live. Two sessions, no cost.

See this agent with your data

Related agents

Same function or industry.

All agents
A fraud analyst at two monitors at night above Paseo de la Reforma
In production

Finance & back office

Fraud Review Agent

KPI it movesMeasured

Review time down 55% to 70%

FAQ

Direct answers.

It posts matches. Any adjusting entry is drafted with its evidence and approved by accounting, because the close has to hold up in an audit.

It stays an open exception with everything it did find. The agent never closes a difference by forcing a match, and that limit is enforced by the platform.

Two to four weeks of tuning inside the pilot, running in parallel with your current close so you can compare line by line before you rely on it.

Which process do we automate first?

Two discovery sessions, no cost, and you leave with two or three quick wins whether or not you build with us.

We reply in under one business day.

Loading the form