The challenge
Purchasing was split across Excel, supplier messages, and delivery notes. Even after the ERP, stockouts, seasonality, and customer growth lived in the buyer’s memory.
Portfolio · AI product design
I moved purchasing out of Excel and chat into an ERP, then designed an AI Agent to carry the judgment buyers still kept in their heads.
The challenge
Purchasing was split across Excel, supplier messages, and delivery notes. Even after the ERP, stockouts, seasonality, and customer growth lived in the buyer’s memory.
My approach
Connect the purchase lifecycle first. Then give an Agent those signals, draft one editable plan, and keep every handoff explicit.
The outcome
A purchase plan that took 30 minutes to 2 hours across suppliers now takes 5 to 10 minutes, and three staff members use it daily. AI prepares the recommendation; the buyer commits the order.
01 / My role
DEF Beauty Supply is an Italian B2B beauty wholesaler. I owned research, workflow and AI interaction design, and implementation.
Map how buyers estimate, confirm, and receive a purchase.
Specify context, recommendations, exceptions, and human authority.
Build the workspace and refine its handoffs with testers.
02 / The problem
A purchase moved through three places. Only the last one left a record in the system.
Export recent sales, then calculate the order by hand.
Confirmation stays in chat or email, and can differ from the order.
The only record, keyed in from the DDT that arrives with the goods.





03 / Phase 1
When I built the ERP, the purchasing lifecycle came first.
It did not recommend a quantity.
04 / Why an Agent
After launch, the records were better, but the slowest part had not moved. Buyers still worked out each quantity themselves.
Now I don't need to switch between Excel and the system anymore. But the part that takes the most time is still the same. I still have to decide what to buy and how much.
Procurement team, after Phase 1. What they adjusted for was information the system did not hold.
Confirmations show shortages. The buyer remembers and orders around them.
Sales drop while an item is out, so they understate real demand.
Some products sell differently across the year.
More customers, or a different customer mix, changes future sales.
This knowledge lived in messages and personal notes, and was gathered again for every order. The cost was cognitive, and that is what the Agent should reduce.
05 / Agent design
The work is gathering and weighing evidence, which an Agent can do. But an order commits the business, so the Agent proposes and the buyer decides.
Stockouts, notes, and exceptions are recorded on the purchase, ready for next time.
One recommendation, not a menu. Each line lists its demand signals: stockout recovery, seasonality, customer mix, buyer notes.
Quantity comes from a deterministic engine. The model interprets and explains, it does not invent numbers.
The plan stays editable and reversible. The buyer places the order, and confirms what the Agent learns.
Suppliers behave differently, so each one gets its own long-term memory, built from every purchase:
Each supplier’s forecast is designed to improve with every purchase; accuracy has not been measured yet. The buyer reviews what to keep and makes the final decision.
I split the work so every number can be checked.
Read the request and supplier documents. Explain the plan and any differences.
Use sales, coverage, stock, inbound, and lead time, adjusted for demand signals.
Edit the plan, resolve exceptions, and place the supplier order.
One plan brings every input together, and the reasons appear on demand.
06 / Key decisions
Each decision was logged with its alternatives, the evidence behind the pick, and the cost I accepted.
07 / The experience
The purchase list coordinates purchases. Each order keeps its own evidence, rules, activity, and conversation.
Replenishment cards say when to order and how much the goods cover, with one action to start a draft.
Quantities and prices edit in place. Each row explains itself on demand, and lasting supplier terms stay apart from this order.
Only real exceptions surface, each on its SKU. Approving is not ordering.
Autosaves become checkpoints. Preview an earlier plan, then explicitly apply it.
Order, DDT, and actual counts stay separate. The buyer resolves differences before closing, and learning waits for review.
Conversation, documents, evidence, and activity stay with the same order.
The Agent prepares and explains; the buyer edits, approves, orders, and receives.
Autosaves support recovery; order notes and supplier terms keep separate scopes.
08 / Iterations
Three scenarios, so the buyer sees the trade-offs.
Replenishment needs one best plan to check and edit fast.
One editable plan with evidence on every row.
DEC-014 → DEC-026Receiving as confirmation to stock-in, with “entry error” as a reason.
A delivery note (DDT) sits between them, and real over-delivery was being mislabeled.
DDT as the baseline. Only differences are recorded.
ITER-001 · DEC-017Chat that explains the page.
Buyers already knew what they wanted. Explanation added little.
Chat as the entry point to creating a purchase.
INT-021 · DEC-044A separate approval flow for risky orders.
An order only turns risky after the confirmation arrives.
One order that escalates in place when a real exception appears.
DEC-035Approve, then the platform places the order.
Ordering happens off-platform and creates a binding commitment.
Approval and ordering split. The platform only records the order.
INT-008 · DEC-02509 / Design an AI agent
Twelve steps follow a purchase before, during, and after a task, then over time. Six themes run through all of them. Every card is held to four goals: explainable, controllable, predictable, recoverable.
01—03 · Before the task. Start with a replenishment opportunity or a request. Establish the goal before generating a plan.
Discover the next step where purchasing already happens.
User need. Buyers need a next action, not a directory of AI features.
Design. The purchase list brings together existing orders, Ask Agent, and supplier replenishment opportunities. The list coordinates work; the order holds the decision.
Trade-off. Organize entry points by business object, rather than by AI feature.
Express intent in business language and carry known context forward.
User need. Users should not reassemble information the business already knows.
Design. A new request asks for supplier and sales coverage. A replenishment card carries its calculated supplier and fixed coverage directly into the new draft.
Trade-off. Fix the coverage of a calculated opportunity; let a self-initiated purchase set its own window.
Make the output and the next commitment clear before work starts.
User need. A recommendation can look like a supplier commitment.
Design. The supplier card states estimated goods, coverage, order timing, and commercial thresholds. Create purchase order produces an editable draft; formal ordering remains a separate buyer action.
Trade-off. Creating a draft and formally ordering from a supplier remain different commitments.
04—07 · During the task. Show progress, preserve human control, and make work resumable and recoverable.
Give waiting a visible start, process, and result.
User need. An unexplained spinner leaves users unsure whether their request is being handled.
Design. The guided empty canvas becomes a plan-loading state while the conversation shows stages. The finished table arrives in the same place. Send becomes Pause during work.
Trade-off. Keep loading and delivery in the same canvas, with matching conversation progress.
Reserve attention for decisions that need business judgment.
User need. Constant confirmation creates fatigue, but commercial decisions need an accountable person.
Design. Quantities and prices stay editable in the table. Missing items, price changes, and quantity changes trigger focused review. Approval, recording an external order, and receipt confirmation remain distinct.
Trade-off. Apply low-risk draft edits directly; keep commercial responsibility with the buyer.
See work in progress and continue it without starting over.
User need. Buyers cannot watch one conversation while other purchases need attention.
Design. Workspace Tasks shows running and completed work across purchases. Notifications report changes. Within an order, Pause and Resume share the composer button and preserve progress.
Trade-off. Task progress and notifications serve different purposes; controls stay in the composer.
Inspect the past and safely return to an editable present.
User need. An accidental edit should not force a buyer to regenerate the whole plan.
Design. Activity log combines business events with draft snapshots. Current draft stays at the top; edit rounds become grouped autosaves. Preview a snapshot in the table, then explicitly apply it.
Trade-off. Preview before applying a compatible draft, and retain the previous state.
08—10 · After the task. Deliver the result in the familiar order. Verify, refine, and retain the reasons behind a decision.
Deliver a result the buyer can scan and verify.
User need. A long answer makes it difficult to verify what changed and why.
Design. Results separate status, key differences, and next steps. Evidence summarizes sales, stock, inbound, rules, and documents consulted; each row’s Why explains its specific recommendation.
Trade-off. Show a source overview separately from SKU-specific recommendation reasons.
Make local adjustments where the result is already visible.
User need. Small corrections should not require another conversation or a separate editing mode.
Design. The familiar product table keeps inline quantity and price fields, product search, row actions, and recalculated totals. The table hugs its rows while the surrounding card fills the workspace.
Trade-off. Preserve the familiar business table and support local edits.
Connect feedback to the decision that produced it.
User need. The reason for a buyer’s judgment can disappear into the conversation.
Design. Order notes retain this purchase’s context. After receiving, structured prompts revisit demand, arrival timing, and SKU variance. Reviewed notes and activity remain linked to the purchase.
Trade-off. Order notes, supplier rules, and audit events retain separate purposes.
11—12 · Over time. Keep supplier information separate from order notes, and surface the next purchase at the right moment.
Find lasting supplier information without confusing it with this order.
User need. Supplier terms and one purchase’s exceptions should not become the same memory.
Design. Supply rules holds contacts, minimums, shipping, lead time, and payment terms. Order notes stay with the order. Two entry points offer supplier-detail editing or a chat-led change.
Trade-off. Give lasting supplier information a stable place beside the order.
Appear at the right time and offer a concrete next action.
User need. Late replenishment creates stock gaps; too many alerts obscure useful action.
Design. Scheduled checks surface supplier opportunities with an order date. Confirmation and delivery changes go to supplier-labelled notifications with a clear primary action, read state, and deletion.
Trade-off. Schedule proactive checks, but leave creation to the buyer.
A—F · Cross-cutting themes. Check safety, coordination, language, context, resources, and experience quality across the entire workflow.
Align access, information scope, and business responsibility.
User need. Reading a document does not grant the Agent authority to commit the business.
Design. Order panels stay scoped to the current purchase. Upload, approval, ordering, and receiving have separate boundaries. Deleting a draft requires an explicit confirmation.
Trade-off. The list coordinates globally; each order contains its own context and decisions.
Keep collaboration continuous without exposing orchestration work.
User need. Internal specialization should not make users carry context between experts.
Design. One Procurement agent coordinates sales, stock, rules, document checks, and approval around the same order. Evidence exposes business sources, without requiring expert switching.
Trade-off. Coordinate internal capabilities through one order and one Agent.
Make what happened and what comes next immediately readable.
User need. Long explanations and confident technical language hide what a buyer needs to do.
Design. The Agent speaks as a purchasing assistant. A general opening serves the list; order replies lead with state and facts, use structured sections, and finish with one clear next step.
Trade-off. Use business facts and put detail in the table and evidence panels.
Adapt the layout while keeping the same purchasing mental model.
User need. Supplier documents, physical goods, and different window sizes must support one workflow.
Design. Confirmation, DDT, and attachments share the purchase context. The compound composer accepts documents. Narrow layouts retain access to both order and Agent without changing the business sequence.
Trade-off. Change layout and reading order while preserving the purchase workflow.
Spend analysis effort where it adds value.
User need. Repeated analysis and duplicate drafts consume resources and interrupt judgment.
Design. Global controls schedule replenishment checks. Existing results, local edits, pause/resume, and historical previews let work continue without regenerating the whole purchase.
Trade-off. Control the checking cadence instead of exposing internal resource machinery.
Evaluate correctness, control, and the ability to continue.
User need. Generation success or acceptance alone cannot show whether the buyer understood the decision.
Design. Review task completion, discrepancy detection, edits, necessary interventions, and recovery. Separate user roles and task conditions rather than treating every acceptance as trust.
Trade-off. Use task scenarios, activity, and role feedback to evaluate the design.
10 / Validation
Testers read a prepared order as a placed order. I checked understanding, lifecycle continuity, and exceptions with the coded prototype and real procurement records.
Check the recommendation against the same sales, stock, inbound, and supplier inputs.
Follow confirmation and receiving exceptions across the purchase lifecycle.
Make the buyer’s external ordering step explicit after testers misread the draft.
11 / Results
The Agent is in production and used by procurement. It drafts quantities; the buyer keeps the supplier commitment.
Connected purchasing records and an Agent-assisted quantity plan.
Buyers edit, approve, place the order, and confirm learning.
Recommendation acceptance and correct escalation rates.
Planning time is the measured result. Recommendation acceptance and whether the Agent stops at the right approval boundary are still to be measured.
12 / Reflection
I moved from connecting purchase records to defining what the Agent can infer, calculate, propose, and hand back.
Next, I would measure buyer edits, recommendation acceptance, and whether the Agent stops at the right approval boundary. A per-supplier trust score would then decide when automation is safe to turn on.