auxfirst industry pillar · Retail

Retail already has the agents. Trust decides which ones you let act.

Twenty retail playbooks. Sixty agents. The build list is the easy part — every category, store-ops, and digital team can already name the agents they want.

The hard part, the part that decides whether any of them ever ships, is the one question a gallery never answers:

which of these can you let act without a human in the loop, and which would you never?

LOWauto-run
LOW-MEDsampled review
MEDIUMpropose + approve
HIGHnamed approver
CRITICALhuman executes
20 playbooks 60 agents 5 operating pillars 5 heat bands 1 control posture each

This is that gallery — the full sixty — but scored on the axis retail actually cares about: consequence. Every agent below carries a heat reading and the control posture it earns. Because in retail, "the agent did it autonomously" is a feature when it drafts a report and a liability when it rewrites a live price.

01Why a gallery of agents isn't a plan

A list of sixty retail agents is a wish, not a roadmap. Anyone can write it. What separates the teams that ship from the teams that pilot forever is not the model, the data, or the vendor — it's whether they've decided, action by action, who pulls the trigger.

Retail makes that question unusually sharp. The actions hiding inside these agents are some of the hottest in any industry. They move price. They move money. They touch live inventory. And they reach customers and suppliers by name. A "SKU diagnostics" agent that drafts a consolidation report and a "competitor price match" agent that rewrites your shelf-edge prices show up in the same paragraph of every vendor deck — and they could not be more different in what they cost you when they're wrong. One earns a shrug. The other earns a margin investigation and an angry call from a regional manager.

So auxfirst reads this gallery the way we read every agent system: not by what it can do, but by what it's allowed to do unsupervised. That reading is the product.

02How to read this gallery: the Action Heat Ladder

We score every agent action with auxfirst field model № 03, the Action Heat Ladder. Most teams argue about agent autonomy with vibes — "that one feels risky." The ladder replaces the vibe with five questions you can answer about any action, in any function.

Five dimensions decide the heat. Score each 0 (cool) to 4 (hot):

// The one rule

An action is as hot as its hottest dimension. No averaging. Four cool dials never buy back one hot one — a perfectly reversible, narrow, internal action that signs a contract is still a contract.

Heat decides who pulls the trigger

Each band maps to exactly one control posture:

LOWauto-runLet it run; audit on incident.
LOW-MEDsampled reviewRuns autonomously; a human audits a slice on cadence.
MEDIUMpropose + approveThe agent proposes; a named human approves before anything happens.
HIGHnamed approverA specific, accountable person signs off every time.
CRITICALhuman executesThe agent prepares; a human does the deed.

A retail worked example

"Push a 40% markdown to every store, live, tonight."

Reversibility 3 (you can re-price up, but the units sold at 40% are gone) · Blast radius 4 ("every store") · Exposure 3 (public shelf price, customers, a headline if it's an error) · Commitment 3 (margin given away) · Authority 4 (writes live pricing systems)

CRITICAL A human executes. Even if four dials were cool, "every store, live" is enough on its own.

MEDIUM Now the same verb, cooled by design: "draft a phased markdown schedule for the buyer to approve, capped at 40%, one category, staged." Reversibility, blast, and authority all drop — propose + approve. Same agent. Different design. The difference is the whole game.

The de-escalators are the real product

Forbidding hot actions is easy. Cooling them so you keep the leverage is the work. Five design moves do most of it in retail, and you'll see them named throughout the gallery:

Heat sets the posture. Trust sets the floor.

The heat band tells you how much oversight an action needs. But a safe agent isn't automatically a trusted one. Below the posture, every agent in this gallery — cool or critical — needs the same five things before a merchant, a manager, or a customer will rely on it:

  1. Visible intent — it says what it's about to do before it does it (Intent Handshake).
  2. Evidence — it shows the working, the sources, the confidence (Confidence Cues). "Sales are down 5%" is a claim; "down 5%, driven by traffic in the North region, here's the query" is trust.
  3. Autonomy boundaries — the heat band, written down, with no exceptions and no averaging.
  4. Escalation paths — an obvious human-in-the-loop handoff, and an Escape Hatch to undo or override.
  5. An audit trail — the answer to "can I prove what the agent did?" This is the TrustKit layer.

Map every agent up the Trust Architecture as it earns it — Functional → Contextual → Judgment → Advocacy. Promote the ones that earn trust; demote the ones that burn it.

03The five operating pillars

The twenty playbooks cover the full sweep of modern retail. They group into five operating pillars — and each pillar has its own trust signature, a characteristic shape of risk that tells you how aggressively you can automate it.

1 · Merchandising & Brand Strategy. Mostly analytical and proposal-shaped — diagnose, brief, simulate, recommend. The heat is low, which hides the real trap: not runaway action but quiet authority. A consolidation list nobody questions becomes policy. Keep these honest with Confidence Cues and an Escape Hatch on every recommendation. The one hot spot is co-op billing — the moment an invoice leaves the building, money and an outsider are in play.

2 · Pricing, Margin & Supplier Relationships. The hottest pillar in retail. Almost every action moves price or money, and most reach a customer or a supplier by name. This is where "the agent did it autonomously" becomes a chargeback dispute or a price-error headline. Default posture is high: propose-and-approve at minimum, a named approver for anything that writes a live price or issues a claim. Margin-floor caps, draft-only invoices, and sampled audits are non-negotiable here.

3 · Physical Stores & Workforce Operations. Heat splits cleanly. Anything pointed at SOPs, audits, training, and internal alerts is cool and ships fast. Anything pointed at people — building schedules, flagging staff for loss prevention — is hot for a reason no dashboard shows you: a false positive has a human cost. Never let an agent conclude guilt or finalize a roster alone. Loop In Experts; Clarify Before Commit.

4 · Omnichannel & Digital Experience. The deceptive pillar. Most actions are reversible — you can roll back a ranking, a banner, a synonym — which tempts teams to over-automate. But reversible isn't the same as low-stakes when the audience is every customer and the lever quietly steers margin. The move here is to embrace autonomy and engineer the cooling: allowlisted components, instant rollback, discount caps, sampled review. Reversibility is the thing you exploit, not the excuse you use.

5 · Governance & Performance Management. Almost entirely cool. These agents read, diagnose, draft, and chase; they never act on the outside world. Auto-run the lot. The only discipline that matters is Transparency, Tapered — show the reasoning behind every "why the KPI moved" before anyone trusts it to brief the executive room.

05From gallery to governed system

A gallery tells you what's possible. It doesn't tell you what to build first, what your data can actually support today, or who in your organization is accountable when an agent acts. That last part is where most retail AI programs stall — not on the model, on the operating posture. That's the work auxfirst does.

Blueprint Sprint

Map a real retail workflow as it runs today, then design where and how agents act within it: intent, autonomy levels, human handoffs, the interaction patterns the agents will follow. You leave with an agent interaction blueprint and an intent-and-autonomy map of what the agent owns versus what stays human.

Action Heat Ladder working session

Bring your real action inventory. We run every verb through the five dimensions, write the band and the posture next to each, and design the de-escalators that cool the hot ones — and you walk out with the rubric your team operates from.

Agent Experience Audit

Already shipping a retail copilot or agent? We diagnose it against the AUX framework — intent, memory, transparency, control — and hand back a Trust Scorecard, the failure modes, and a prioritized fix list.

Agent Validation Sprint

Stress-test a built agent against real cases, edge cases, and failure modes before it touches a live price or a live customer. Go / no-go, with the fixes ranked.

Advisory Retainer

Keep evolving the system as it scales and breaks: promote the agents that earn trust up the ladder, demote the ones that burn it, and re-score on every incident.

The discipline underneath all of it is one rule from the ladder: a heat model is only worth something when it changes what an agent is allowed to do unsupervised. List the verbs, score the five dials, read the band, design the cooling, review on incidents. The function changes; the shape of the ladder does not.

Ready to decide which of your retail agents can act?

You don't need sixty agents. You need the handful that move your numbers — designed so you can trust them to act, and cooled so the hot ones can still run. We'll map your real action inventory onto the ladder in a single working session and hand you the posture for every one.

Written by

Emil Krzemiński

Founder of auxfirst, the agentic experience design agency. He develops the AUX discipline and the Action Heat Ladder — the frameworks for designing trust and control into AI agents that act on people's behalf.

Cite this page

auxfirst (2026). The Retail Agent Gallery — 60 Agents, Scored on the Action Heat Ladder.
https://auxfirst.com/retail/agent-gallery.html