Lumi / AI agents + BI for e-commerce

Know what your ad spend boughtbefore you raise the budget.

Hand the agent the weekly reconciliation: ad reports against orders, cancellations, returns and stock. BI puts spend and confirmed orders on one agreed definition, and the agent drafts options for your ads lead to approve.

ILLUSTRATION · SAMPLE DATA

Sales performanceSample week · VND
Advertising spend12.000.000
Confirmed-order revenue36.000.000
Confirmed orders90

Spend and confirmed-order revenue · million VND

SpendRevenue
Spend and confirmed-order revenue · million VNDMonTueWedThuFriSatSun
10 orders to reconcile

Ad report: 100 orders · Order file: 90 confirmed.

BI dashboard concept · authored sample data, not a running system.
Current scope

BI is deployed with customers. The ad and operations agents are proposals: scope and connection feasibility are confirmed before work begins.

Watch the agent work · 26 seconds

One run, from hand-off to approval.

Tuesday, 2:00 pm. The new batch has 12 products. How many are ready to list?

IllustrativeIllustration with synthetic data, matching the scenarios below and the CSV file. Not customer data.
Read the video as text
  1. Tuesday, 2:00 pm. The new batch has 12 products. How many are ready to list?
  2. Lumi Agent · Catalog preparation · batch of 12 (Read-only · approved folder): Read product-records.json, 12 products; Read supplier-note.md and channel template, Writing guide; Matched A source for every field, 10 fully sourced drafts; Flagged DEMO-001 capacity conflict, DEMO-002 missing size, 2 questions; Did not Publish listings or edit source records, Outside granted access.
  3. Batch of 12 · channel template: Drafts ready 10 / 12, Sources disagree 1, Missing 1. DEMO-001: Capacity: 450 ml or 500 ml? (Conflict); DEMO-002: Dimensions: in no source (Missing).
  4. Confirm DEMO-001 capacity and supply DEMO-002 dimensions before listing. Sources: product-records.json says 450 ml; supplier-note.md says 500 ml; DEMO-002 dimensions appear in no source. Approved · product owner. The agent hands 10 drafts to the listing team and holds 2 products for answers. Nothing published.
  5. Hand off the new batch. Get back sourced drafts. You approve before listing.

Before spending more, see where the money went.

Three jobs you could hand to the agent and BI.

Budgets grounded in sales

Compare spend with confirmed orders, cancellations and returns before discussing allocation.

Experiments with a clear question

Prepare hypotheses and measurement so specialists can choose what is worth testing.

Less report assembly

Propose gathering data, checking figures and drafting observations for review.

Results need real-world measurement. ROAS alone does not establish profit.

From raw numbers to a test worth running.

Say which budget decision is coming; the agent and BI prepare the evidence, and you decide.

Explore the proposed steps
  1. Agree data and metrics

    Identify ad, order, stock and cost sources; align periods, currencies, product IDs and revenue definitions.

  2. Build BI around the decision

    Propose a data flow and dashboard comparing spend, orders, cancellations, returns and stock, with freshness and unresolved discrepancies visible.

  3. Connect agents to checked data

    Prepare reviews, flag changes and draft budget options or content experiments. Each observation needs sources and explicit assumptions.

  4. Specialists approve and measure

    The responsible person chooses changes, approves budgets and sets timing. Record results to retain, revise or stop the experiment.

Proposed workflow

What is waiting for you at the budget review.

A dashboard and review packet scoped around your data, ready for review.

Explore the planned deliverables

Planned output structure

  1. BI dashboard and metric definitions

    Views of spend, orders and operations, with calculation rules, freshness and data limits.

  2. Experiment brief

    A hypothesis, creative or offer to test, measurement and stopping criteria for approval.

  3. Operations review

    Stock gaps, canceled or returned orders and questions to resolve before further promotion.

  4. Sources and data limits

    Files, periods, reporting definitions and missing data that affect comparisons.

  5. Decisions and owners

    Approved work, open questions, the responsible person and the next review point.

You decide budgets, prices and orders.

Lumi proposes preparing data and draft observations for review. Changes to ad accounts, storefronts or order systems require separate authorization and approval.

  • Use permitted files
  • Separate hypotheses from facts
  • Review before applying

The proposed scope does not launch ads, increase budgets, change prices, publish content or process orders automatically.

Hand off your next budget review.

Pick the report that takes the most work. We see where BI and an agent are worth trying.

Illustrative review desk with paper files, pencil and a ceramic cup in packaging.
  1. See how the work happens

    Choose a report and the decision it supports.

  2. Agree what is worth trying

    Confirm data, connection feasibility, reviewer and costs.

  3. Count checking and corrections

    Compare with today’s process, including support.

  4. Expand only if it earns its place

    Review results and whether the operator can repeat the work.

Experience and pricing

Try it free first. Pay only for what you need.

Start with a free trial on a slice of your data. To deploy, choose a BI dashboard, AI agent connections or both, for a one-time fee. Maintenance and training are chosen separately.

Trial experience

Free

Test the workflow using a representative subset of your business data. We align on the specific task, permitted files, and outputs to review before any work begins.

Lumi charges no fee for the trial experience. Scope and duration are agreed upfront; no hidden costs. Do not submit confidential data through the form.

Request a free experience

Two implementation options, available separately

ILLUSTRATION · SAMPLE DATA

Sales performanceSample week · VND
Advertising spend12.000.000
Confirmed-order revenue36.000.000
Confirmed orders90

Spend and confirmed-order revenue · million VND

SpendRevenue
Spend and confirmed-order revenue · million VNDMonTueWedThuFriSatSun
10 orders to reconcile

Ad report: 100 orders · Order file: 90 confirmed.

BI dashboard concept · authored sample data, not a running system.

Build a BI dashboard

9.9 million

VND · one-time build fee

Consolidate scattered data sources into a clear operational dashboard for sales, advertising, and fulfillment.

  • Agree data sources and standardized metric definitions.
  • Design and build the dashboard within your agreed scope.
  • Hand over the operational dashboard with practical guidance.

Confirm source counts, report views, refresh frequency, and acceptance criteria before starting.

ILLUSTRATION · SAMPLE DATA

AI Agent · Advertising review

Should we increase the ceramic cup budget?

Sources in this exampleAdvertising reportOrder export

More evidence needed before increasing spend.

The ad report attributes 100 orders; the sales file contains 90 confirmed orders.

Draft recommendation

  1. Reconcile the 10 remaining orders and reporting periods.
  2. Confirm stock before choosing the next experiment.
Awaiting specialist review

No budget or advertising account changes.

Agent output concept · authored scenario, not an AI execution result.

Connect AI Agents / agent packs

9.9 million

VND · one-time connection fee

Introduce purpose-built AI workflows into your team's day-to-day operations.

  • Select the right AI tasks and agent packs for your operational needs.
  • Connect authorized data and tools securely within agreed boundaries.
  • Verify deterministic outputs and hand over a workflow with human review.

Explicitly define tasks, tool connections, runtime environment, and access limits. Does not include a BI dashboard.

Concept interfaces and authored data illustrate the proposed scope. These are not screenshots of a running product.

Both options: 19.8 million VND in implementation fees.

9.9 million for the BI dashboard + 9.9 million for AI agent connections. Maintenance, applicable taxes, and third-party tools are itemized separately and never bundled without consent.

Discuss implementation options

Ongoing maintenance and enablement options

Three distinct options to keep your system performing reliably. Maintenance excludes one-time setup and third-party software fees.

Basic · Annual maintenance

6.9 million

VND / year

For teams confident in daily operations that need baseline system reliability.

  • System and agent pack updates within the deployed scope.
  • Technical support and issue resolution covered by the agreement.
  • Standard maintenance tier without dedicated live training sessions.

Annual fee covering twelve months. Support channels, response SLAs, and update scopes are specified in the agreement.

Monthly training & improvements

3 million

VND / month

For teams seeking hands-on coaching and steady incremental refinements.

  • One dedicated training and review session each month.
  • Continuous system adjustments based on evolving operational needs.
  • Training agenda and improvement scope agreed prior to each session.

Session length and monthly improvement scope are formally defined in your service agreement.

Extended AI training & improvements

6 million

VND / month

For organizations working closely alongside Lumi to deepen internal AI capabilities.

  • Two dedicated sessions per month for advanced training and system upgrades.
  • Hands-on refinement of complex business tasks within agreed boundaries.
  • Clear session goals and milestone planning established ahead of each meeting.

Session timing and improvement deliverables are clearly outlined in your agreement.

Choose the tier that matches your team's rhythm. Start dates, billing cycles, renewals, and cancellation terms are confirmed upfront; sending an enquiry does not activate a subscription.

Discuss maintenance options

What is charged separately?

Fees exclude applicable VAT/taxes, third-party software licenses, AI model API usage, infrastructure hosting, and travel expenses. Every quote itemizes applicable charges, the paying party, and usage-based calculations. Remote delivery is standard.

Clear boundaries before billing

Data source counts, report structures, AI tasks, integrations, revision cycles, and acceptance criteria are fixed in the statement of work. Any out-of-scope requests require agreed pricing before execution.

Clear commercial terms upfront

Both parties confirm technical feasibility, handoff milestones, payment terms, and cancellation policies before signing. Maintenance agreements explicitly state included deliverables and service boundaries.

Pricing proposal updated October 1, 2026. The enquiry form registers interest; pilot timing and deployment schedules are confirmed separately. No automatic account setup, billing, or renewal.

Before you begin

Is the BI and agent setup already available?

BI is deployed with customers and can be built for your data within an agreed scope. The ad and operations agents are proposals; Catalog is the first agent workflow in preparation, and no results for these agent tasks are cleared for publication.

Does Lumi replace the ad specialist running campaigns?

Not in this proposed scope. The ad specialist checks observations, chooses tests and approves budgets. Lumi does not publish ads or operate the account automatically.

How would Lumi improve budgets and advertising performance?

The proposed approach uses BI to compare spend with sales data, then AI agents to draft allocation options and experiments for specialist review. Results must be measured against agreed metrics; higher ROAS, revenue or profit is not guaranteed.

Do we need to connect ad accounts or storefronts?

No account access is needed for the initial conversation. A pilot may be considered using permitted exports; any direct connection must be verified separately.

Is Catalog still part of the scope?

Yes. Product information supports ad content and product pages, and remains the first workflow selected for validation. That does not establish readiness for the proposed ads and operations workflows.

Does sending an enquiry involve a payment?

The form sends a contact request. Scope, feasibility and pricing are agreed before an engagement; submitting the form does not create an account or take payment.

What does implementation cost?

A BI dashboard costs 9.9 million VND as a one-time fee. Connecting AI Agents / agent packs costs 9.9 million VND as a one-time fee. Both total 19.8 million VND in implementation fees. Maintenance is separate; taxes and third-party tool costs are excluded. Scope is agreed before work starts.

What does the free experience include?

A trial using a subset of your business data, with the task and limits agreed upfront. Lumi charges no experience fee; third-party costs require your separate agreement. Send an enquiry to discuss it; no data or account access is needed yet.

How do the three maintenance options differ?

Basic at 6.9 million VND/year includes AI Agents / agent-pack updates and support, without training. The 3 million VND/month option includes one training session and system improvements. The 6 million VND/month option includes two sessions for training and AI-system improvements. Duration and scope are agreed before signup.

What do you want to see clearly at the next budget review?

Describe the result you need, not the steps. One report your team still builds by hand is enough to start. No files needed yet.

Discuss your workflow

Which ads or sales report would you hand off first?

Tell us about a recent job and leave your contact details. No files needed yet.

For example: combining ad and order reports for weekly budget review, preparing test briefs or checking stock before promotion. Do not include customer data or credentials.

Your contact details and message are sent to Lumi’s internal Discord channel to handle this enquiry. Please do not include payment details or confidential documents.