Features

Built AI-first, not AI-bolted-on.

One customer brain that answers, acts, and learns — across the whole relationship. Here's what it does, in detail.

3 seats, 500 credits/month, no credit card.

AI support inbox

Every reply, drafted in seconds — with full context.

Inbound lands from every channel. The AI retrieves the customer's history, their ARR, your roadmap and last quarter's commitments, drafts a cited reply with a self-rated confidence score, then sends or queues against per-channel floors. Risky topics always go to a human.

Context retrieval

200K of customer context per draft

KB, customer history, ARR, renewal date, roadmap and the last 20 messages of the thread — assembled into one prompt before the AI writes a word.

Confidence gate

Auto-send with a bar you set

Per-channel confidence floors (App Store + Instagram require 0.95, email 0.85). Public channels need 100+ human-approved drafts before auto-send unlocks.

Reply rules

Plain-English guidance, no prompts

Anyone writes natural-language rules the AI follows on every draft — scoped to a channel, lens, customer tag, or workspace-wide. Conditional on thread history.

Multilingual

Any language the customer writes

Auto-detected and tone-matched, native to the model — not a bolt-on translation layer.

Self-learning KB

Every approved reply grows the brain

The AI cites your team's actual answers, not a generic FAQ — and gets sharper with every draft you approve.

Hard blocks

Some things always go to a human

Refund, cancel, password, lock/unlock, money, percentages, contracts, and “talk to a human” are blocked from auto-send regardless of confidence.

AI Actions · the full catalog

AI that acts, not just drafts.

Most AI support tools stop at a suggested reply. PilotPM's brain can take the action the reply promises — and then prove it worked. Every action is human-approved, metered, and gated: the AI proposes, you confirm.

Issue refunds

Refund in Stripe, in one click

Approve and the brain issues the refund in Stripe, then posts the confirmation back into the thread — no swivel-chair to the billing dashboard.

Save churns

Catch the cancel before it lands

Cancellation intent is scored on open threads. The rep sends a retention offer without leaving the conversation — and PilotPM tracks whether the customer actually stayed.

Bulk-resolve

Clear a whole cluster at once

When fifty tickets are the same issue, resolve the cluster together with one approved, consistent reply — instead of fifty copy-pastes.

Account-fix

Take the fix action, not just describe it

Unlock the account, reset the state, apply the change — the action the customer needs, behind the same approval gate as everything else.

Deep-triage / RCA

Root-cause from Sentry + your code

It ties the complaint to the Sentry error and the lines that broke it. The engineering handoff arrives pre-triaged — clustered, impact-ranked, root cause noted.

Code-grounded answers

Answer from your codebase, cited

Technical questions get answered from how your product actually behaves — with the source citation attached, not a guess from a generic doc.

KB drafting

Turn resolved tickets into docs

Resolved tickets become drafted knowledge-base articles, so the next customer self-serves the answer instead of opening another thread.

Every action is gated

Human-approved, metered against your credit pool, and logged in the audit trail. The AI proposes; you confirm. Nothing irreversible happens on its own.

Human-approved Metered Audit-logged

Branded help sites

A public help site at /help/yourcompany — the same AI on every page.

Import your docs, point your DNS, and customers self-serve before they ever email. AI-only chats are free; only escalations count against your credits.

Branded & on your domain

Your logo, your colors, your DNS. The help site reads from the same KB the inbox AI cites, so answers never diverge.

Audience scoping

Scope what each audience sees — consumer vs enterprise, free vs paid — so the right docs and the right tone reach the right reader.

Self-serve deflection

The AI answers in the help widget first. Only when it escalates does a conversation land in your team's inbox.

Roadmap intelligence

Your roadmap builds itself. From every channel.

Every customer mention — Slack, HubSpot, App Store, support tickets, Snowflake usage — flows into one signal stream. The AI clusters them into themes, themes pin to initiatives, initiatives carry real ARR. The roadmap stops lying.

Signals in

Every channel, automatic

The intake agent reads everywhere your customers talk and turns it into one signal stream — nothing imported by hand.

Themes, clustered nightly

Deduped and named

“Locked out of app” said three different ways collapses into one theme, carrying the customers who raised it and their combined ARR.

Initiatives, ranked by ARR

Pinned to real impact

Promote a theme to an initiative and it inherits the customer list and the ARR — so “rebuild onboarding” sits next to its real $230K, not a guess from the room.

It doesn't just report — it closes the loop. Notice what changed (changepoints pin the week a spike began), explain why from the actual conversations, draft the fix (a draft PR, human-owned, in pilot), then verify it worked in the signal. The Impact Ledger keeps the receipt — “fixed” means fixed, not merged.
AI-readiness scorecard

See exactly where the AI is ready — and where it isn't yet.

A per-category automation funnel shows what share of each topic the AI can already handle end-to-end, what's queued for a human, and where your knowledge base has a gap to close. Honest numbers, not a vanity dashboard.

Per-category automation funnel

Drafted → approved → auto-sent, broken out by topic. You see which categories are safe to turn loose and which need more calibration.

Readiness scoring

Each category carries a readiness score driven by real resolution data, so you flip on auto-send where the evidence supports it — category by category.

KB gap surfacing

Where the AI keeps escalating, the scorecard flags the missing knowledge — turning “the AI can't answer this” into a concrete article to write.

CS operations

Run the team, not just the inbox.

Routing, SLA, scorecards and coaching — built into the same platform. The work the CS Director used to do manually now happens automatically.

Auto-assignment

Tickets route themselves

Round-robin with VIP-first priority, language-matched routing to native-speaker agents, and per-agent queue caps so nobody drowns.

SLA tracking

Promise tighter SLAs to your biggest accounts

Per-inbox SLA targets with VIP-tiered escalation; overdue and due-soon flags surface in the inbox — and you can prove it in the QBR.

Agent scorecards

Performance you can pay on

SLA compliance, CSAT percent-positive, reopen rate — per-agent and per-team rollups, exportable for HR review cycles.

Weekly AI coaching

Coach every rep without reading 1,000 tickets

Every Monday, team leads get an AI coaching summary per agent: strengths, gaps, and a one-pager to take into the 1:1.

Five lenses, one signal stream

Pick the lens for the seat you're in today.

Same data, different view — switch when the work changes. The substrate compounds: every approved reply, promoted theme and corrected draft trains your tenant's AI.

Support

Inbox · AI drafts · Auto-pilot

Success

Call prep · Renewals · QBR

Sales

Buying signals · Pipeline intel

Product

Themes · Roadmap from real signal

Compliance

Audit trail · Controls · DPA terms

See it on your data

30 minutes with us, you'll know if we're it.

We show the dashboard on your actual tools, and what we'd have resolved last week. No slides.