// cs specialist

AI that answers customer email and live chat.

Magistry replies to your Shopify inbox — it does not just draft and wait. Every answer is grounded in the real order (matched even from a typo-ridden message), cites your actual policies, and has to pass a Reply Judge score before it sends. Refunds, replacements, address changes and gift cards execute inside limits you set. Email over IMAP/SMTP or Gmail and Microsoft OAuth, plus an embeddable live-chat widget.

Wire up your inbox

See the decision plane

Email · IMAP / Gmail / Microsoft Live-chat widget Reply Judge Proactive Outbound

thread · example

from        : klant@protonmail.com
subject     : Bestelling 88421 niet aangekomen
lang        : nl-NL (in allowed list ✓)

order_match : o_88421 (cosine 0.98)
product     : Brushed Linen Throw — Sand
ship_status : in transit, NL (carrier ping 6h ago)
supplier    : on-time batch, no flags

policy_cite : cs_policy_chunks#214
              "EU shipping ETA — 5–8 business days"

draft       : "Hoi! Goed nieuws — je throw is
              onderweg en zou tussen vrijdag en
              maandag aankomen. Hier is de track-link…"

judge_score : 0.91 → APPROVED → sent
cycle_time  : 11s · 1 LLM call · €0.004

// eight skills

Every reply has a reasoning trail.

Eight specialist skills compose every reply, every refund, every escalation. Each skill is independently observable in cs_thread_evaluations — you can read why the agent thought it knew the answer, not just what it said.

order_detective

Heuristic + embedding match from inbound message → exact Shopify order. Resolves typos, partial names, hashed identifiers, multilingual subject lines.

// output

order_match

catalog_xref

Pulls the product context — variant, fulfillment status, shipment trail, supplier — so the reply is grounded in what the customer actually bought.

// output

context_payload

supplier_reality

Cross-checks supplier ETA, batch quality flags, and lane delay history. If the supplier is the cause, the reply says so honestly, not generically.

// output

supplier_signal

policy_grounder

pgvector RAG over cs_policy_chunks — your shipping, refund, returns, warranty pages. Every reply cites the chunk that justifies its decision.

// output

policy_citation

reply_drafter

Language-gated by languages_allowed_for_send. Brand-voice embeddings hold tone. Drafts only — until Reply Judge clears them for send.

// output

cs_outbound_drafts

refund_ev

Expected-value math: refund cost vs replacement cost vs escalation risk vs lifetime value. The cheapest right answer, never the easiest.

// output

ev_recommendation

action_executor

issue_refund · issue_replacement · cancel_order · change_shipping_address · issue_gift_card. Idempotent. Rate-limited. Every action a row.

// output

shopify_mutation

escalate

When confidence < threshold or risk class = high, hand off cleanly to a human inbox with the full reasoning trail attached — never a cold ticket.

// output

human_handoff

// channels & memory

One brain, every channel.

The same eight skills answer wherever the customer shows up — and the system around them keeps learning from every resolved thread.

Email

Connect any mailbox over IMAP/SMTP, or one-click OAuth for Gmail and Microsoft. Threads sync in, replies send from your own address.

Live-chat widget

An embeddable chat widget on your storefront, backed by the same order-grounded, policy-cited reply pipeline as email.

CSAT surveys

Post-resolution satisfaction surveys close the loop — scores feed back into how the agent and its drafts are evaluated.

Knowledge base

Your articles, policies, and product knowledge, indexed and cited. The agent answers from what you've written, not what it guesses.

Resolution memory

Every resolved thread becomes a retrievable precedent — the same issue next month gets the answer that worked, faster.

Hard constraints

Refund caps, a fraud gate, a language gate, and policy grounding are enforced as constraints — not suggestions the model can talk itself out of.

// the real product

The inbox, with the judge's scores visible.

A real screenshot of the dashboard — demo store data. Threads on the left, AI drafts on the right, each scored by the Reply Judge before anything sends.

// reply judge

A second pass before any reply ships.

Reply Judge is a second model that scores every draft on policy adherence, factual grounding, and brand-voice alignment. Below the score floor: the draft is bounced back to the drafter; above the kill ceiling: the thread escalates instead of replies.

policy

Does the draft only promise things your published policy actually allows?

e.g. Promised return window matches the cited cs_policy_chunk.

fact

Does every claim trace back to the order data, supplier signal, or catalog?

e.g. Tracking ETA cited from the actual carrier event, not invented.

brand_voice

Does the draft sound like you, scored against your brand-voice embeddings?

e.g. Tone within 0.15 cosine distance of brand_voice_centroid.

risk

Is the request inside the trust window, or does it need a human?

e.g. Refund >$500 → auto-escalate regardless of draft quality.

cs_thread_evaluations · example

thread_id   : t_4912
draft_id    : d_1180
language    : nl-NL (allowed ✓)

judge_score : 0.91
  ├─ policy      : 0.94
  ├─ fact        : 0.92
  ├─ brand_voice : 0.88
  └─ risk        : low (refund €18.50)

policy_cite : cs_policy_chunks#214
              "EU returns — 30d, prepaid label"
fact_cite   : order_payload#o_88421
              tracking: 'in transit, NL'

verdict     : APPROVE_SEND
sent_at     : 2026-05-25T11:02:18Z

// brand voice embeddings

Tone is a tensor, not a prompt.

Upload 20–50 examples of replies you would write — Magistry generates cs_brand_voice_embeddings, a vector representation of your voice. The drafter steers toward it; the judge measures distance from it; new operators can hire against it.

Seed it once

Drag in 20–50 of your best CS replies — historic emails work fine. We strip identifiers and embed the prose.

20–50 examples

Steer every draft

reply_drafter conditions on the brand-voice centroid, never freestyles tone. Even a new policy sounds like you.

drafter conditioning

Measure every send

Reply Judge scores cosine distance to the centroid. Drifts above 0.15: send is held, you review the variance.

cosine 0.15 threshold

// refund_ev

The math behind every yes.

refund_ev computes the expected value of every possible action — refund, replace, gift card, escalate, deny — given the order, the customer's lifetime value, the supplier reality, and the policy. Picks the cheapest right answer.

// example scenario

Customer received the wrong color throw. €89 order. LTV €642 (high decile). Supplier swap-batch flag = true (root cause acknowledged).

issue_refund−€89.00 (loss + lost LTV: −€71)
issue_replacement−€34.20 (supplier covers, retains LTV)
gift_card 120%+€18.40 (retention model: +0.22 repurchase)
escalate−€42.80 (handle time + churn risk)
deny−€612.00 (policy breach, public review risk)

Magistry picks gift_card 120% — positive EV, retains the relationship, supplier swap-batch covers the cost.

LTV-aware

Top-decile customers get more flex; first-order customers get the policy default.

Supplier-aware

If the batch is the root cause, the EV credits the supplier-recovery line.

Risk-aware

Public review risk, repeat-complaint history, dispute history — all priced in.

Bounded

Magistry never resolves above the per-action ceiling without an escalation row.

// proactive outbound

Replies before the customer asks.

When fulfillment stalls, a batch ships late, or a payment fails — Magistry drafts the outbound message before the customer writes in. Sits in cs_outbound_drafts until your trust mode says send.

cs_outbound_drafts · example

trigger     : fulfillment_stall (>96h carrier silence)
customer    : jane.k@***.com (LTV €312)
order       : o_88421 — 'Brushed Linen Throw'

draft_subj  : "Quick update on your order #88421"
draft_body  : Hi Jane — your throw shipped on the 20th
              and the carrier hasn't pinged us in 4 days,
              which is unusual. We've already opened a
              trace with the courier and will refund the
              full amount on the 28th if it hasn't moved.
              No action needed on your side.

judge_score : 0.93 (policy ✓ fact ✓ voice 0.91)
status      : PENDING_OPERATOR_APPROVAL
auto_send   : 2026-05-25T18:00Z (if no override)

trust_mode  : assisted (proactive sends require approval)

Switch to autonomous trust mode in /workspace/cs/settings

// cs specialist

Reply faster than the customer can finish typing.

Connect your inbox in OAuth, paste your policy pages, drop in 20 brand-voice examples — first dry-run drafts arrive within the day, ready for you to approve or watch run.

Wire up your inbox

Read the FAQ

Language-gated · Brand-voice scored · Append-only