AI Agents

Operations

Replenishment Agent

Watches coverage by store and SKU, and proposes the purchase order before the shelf goes empty.

PilotReviewed September 3, 2026
Internal apps · Replenishment
Demo data
  1. Replenishment cycle

    Wednesday run, 640 SKUs across 18 stores.

  2. Agent

    Nine SKUs break coverage before the next delivery. Six are a purchase, three are a transfer from the store that is 40 days long.

  3. SAP · 6 purchase orders drafted · 3 transfers drafted · none released · buyer approval pending
  4. Handoff to a person

    The buyer approves seven and rejects two because a promotion was cancelled. Both rejections become coverage rules for the next run.

Internal appsSAPNetSuiteYour ERP
KPI it moves
Stockouts and excessMeasured in pilot
Channels
Internal appsSlack / TeamsEmail
Integrates
  • SAP
  • NetSuite
  • Your ERP
  • Your WMS
  • Demand forecast
A store associate scanning shelf labels in a convenience store at night
Operations

What it does

Every store and SKU watched. The order proposed before the shelf is empty.

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

  • SAP
  • NetSuite
  • Your ERP
  • Your WMS
  • Demand forecast

Replenishment Agent

03Decides

Channels

  • Internal apps
  • Slack / Teams
  • Email

A person on your team

01

Receives

Wakes on the replenishment cycle for its assigned categories, stores and warehouses.

02

Looks up

Reads stock, in transit, lead time, the forecast and the promotion calendar per SKU.

03

Decides

Ranks what actually breaks coverage and proposes a purchase or a transfer, with the reason written.

04

Acts

Drafts the order in the ERP for the buyer to approve, or releases it under the limit you set.

05

Escalates

Flags supplier delays, price moves and any order above its limit to the category owner.

06

Learns

Compares each proposal against what the buyer approved and corrects its coverage assumptions.

KPI it moves

Targets set, being measured.

These are the numbers we sign in the KPI Contract, not results, until the pilot closes.

Proof Ledger
Pilot targets

Target, being measured

25% to 40% fewer

Stockouts on A items

Pilot target set in the Blueprint and measured against your baseline during the pilot. DaCodes, Sep 2026

Target

Target, being measured

10% to 18% lower

Excess inventory

Pilot target set in the Blueprint and measured against your baseline during the pilot. DaCodes, Sep 2026

Target

Target, being measured

Half or less

Buyer hours spent on manual review

Pilot target set in the Blueprint and measured against your baseline during the pilot. DaCodes, Sep 2026

Before

Baseline

Target

Half or less

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

Purchase order $412,000 MXN · above the buyer's limit

Category: beverages · 38 stores

Weekly eval

Passing

Proposal against buyer decision

92.4%

Last 8 runs
89.3% → 92.4%

Forecast error on the SKUs it acts on within target

Limit, enforced

Budget ceiling per category and cycle

78% of today's ceilingAuto-pause

Human approvals

  • Every order above the amount the buyer sets
  • New suppliers and any change of source

Typical evals

  • Proposal against buyer decision, week over week
  • Forecast error on the SKUs it acts on

Limits

  • No supplier negotiation and no price commitments
  • Budget ceiling per category and per cycle

Time to production

8 to 12 weeks

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

As a Library agent it needs 2 to 4 weeks of tuning inside the pilot, most of it on your policies and your systems, not on 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

Pilot

Running today. The figures above are targets signed in the KPI Contract until the pilot closes.

Reviewed September 3, 2026

Where this agent sits on the maturity policy

  1. Reference architecture
  2. PilotToday
  3. In production

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 maintenance technician checking readings on a tablet beside a CNC machine
Reference architecture

Operations

Telemetry Watch Agent

KPI it movesTypical target

Unplanned downtime 15 to 25% lower

FAQ

Direct answers.

Only under the limit the buyer sets, and only from approved suppliers. Everything else lands as a draft order with the reasoning next to it.

It uses yours if you have one. If you do not, it starts from sales history and lead times, and the Blueprint says plainly what that costs in accuracy.

Because the KPI is still being measured. The label moves to In production when the pilot closes with the stockout and excess numbers in the Proof Ledger.

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