Industry deploymentSalesforce Agentforce (service agent and SDR agent)Salesforce Data 360 (zero-copy federation from Snowflake)Salesforce Service Cloud, Sales Cloud, Experience CloudSlack employee agentTwilio Segment (real-time activation and self-optimising content agent)Previous stack: Coveo-powered generative search over Salesforce Knowledge

Xero put an Agentforce service agent in front of 5 million customers and now resolves 62% of support cases autonomously

Xero Limited· New Zealand / Australia (global operations)· Customer support deflection and conversational case resolution, plus agentic sales development and real-time onboarding intervention
Share
Xero Limited logo
Xero Limited
Salesforce Agentforce (service agent and SDR agent) logo
Salesforce Agentforce (service agent and SDR agent)
AI deployment

Xero rolled a conversational AI service agent into the in-product help menu for all five million of its customers. Salesforce reports 62% of support cases now resolved autonomously across 800,000+ cases a year. The transferable lesson is not the model — it is the seven-year-old knowledge base and zero-copy data layer underneath it, and the figures Xero has not published.

Results at a glance · every figure cited

62%Support cases resolved autonomously by the Agentforce service agent
More than 800,000 cases a yearAnnual case volume the service agent operates across
~500kService agent conversations since launch
65%+Online queries resolved autonomously (vendor stat card, different unit to the 62% figure)
3xOpen rate increase on agent-generated partner emails, first six weeks
~97%Help sessions resolved with personalised content by the pre-agent Coveo-powered stack
5 millionCustomers with access to the service agent
3 to 6 percentage pointsConversion lift from shifting abandonment communications from 24-hour batch to real time
~50Live real-time activations running on Twilio Segment
1 million, with monthly users up ninefold year-on-yearCustomers who used Xero generative AI features in 12 months

The challenge

Xero serves five million small businesses and their advisors across more than 180 countries, with a support load that grows with subscribers rather than with headcount budgets. Its questions are high-consequence (bank feeds, payroll, tax, account security) and asked largely by non-specialists — tradespeople, contractors and hospitality owners. Its existing self-service stack already worked well, resolving roughly 97% of help sessions with personalised content, so the problem was not a broken function but a retrieval-shaped experience that could not hold a multi-turn conversation, take action, or hand off cleanly to a human at the right moment.

What was deployed

Xero deployed an Agentforce-powered conversational service agent across the in-product help menu for all five million customers, routing to specialised sub-agents for banking, payroll and security and escalating via chat, callback or a logged case. Context comes from customer experience data held in Snowflake and federated into Data 360 with a zero-copy approach, avoiding duplicated records. In parallel it runs an SDR agent for accountant and bookkeeper partner outreach, a Slack employee agent for account executives, and roughly 50 real-time activations on Twilio Segment that intervene when onboarding stalls.

The results

Salesforce reports the service agent resolves 62% of support cases autonomously across more than 800,000 cases a year. The Xero customer story page shows ~500k service agent conversations since launch, 65%+ of online queries resolved autonomously, and a 3x open rate on agent-generated partner sales emails in the first six weeks. Separately, Xero's engagement team reported a three-to-six percentage point conversion lift from moving abandonment communications from a 24-hour batch to real time. At company level, Xero's CEO said one million customers used its generative AI features over 12 months, with monthly users up ninefold year-on-year.
TL;DR

Xero, the New Zealand-founded small business accounting platform, rolled a conversational AI service agent into the in-product help menu for all five million of its customers. Salesforce reports the agent now resolves 62% of support cases autonomously across more than 800,000 cases a year. The interesting part is not the model: it is the seven-year-old knowledge base and the zero-copy data layer underneath it. What the public record does not give us is a CSAT number, a cost-per-contact number, or a precise definition of ‘resolved’.

The company and the problem

Xero is a cloud accounting platform used by small businesses, accountants and bookkeepers. Salesforce’s customer story describes a company that has grown to serve five million small businesses and their advisors across more than 180 countries — a support surface area that scales with subscriber growth, not with headcount budgets.

Two things make Xero’s support load unusual. First, the questions are consequential: bank feeds, payroll runs, tax filings and account security are not casual retail queries, and a confidently wrong answer about a payroll cutoff has real financial consequences for the person asking. Second, the user is rarely a finance professional. Many are tradespeople or hospitality owners doing bookkeeping at 10pm, and the help they need is procedural rather than conceptual.

Xero’s answer since 2019 has been Xero Central, a consolidated self-service knowledge base. By the time agentic AI arrived, that estate was already doing heavy lifting: the pre-agent stack, built on Experience Cloud, Salesforce Knowledge and a Coveo-powered generative model, resolved roughly 97% of help sessions with personalised content. That is a crucial piece of context that most write-ups skip. Xero was not automating a broken support function. It was replacing a search-and-retrieve experience that already worked with a conversational one that could hold a multi-turn thread and hand off cleanly.

Providing customers with a digital experience that connects them to a human at the right time helps them unlock value from Xero faster.

— Nigel Piper, Executive General Manager, Customer Experience, Xero, Salesforce customer story

What was actually built

Three distinct systems are in production, and they are worth separating because they have different risk profiles and different evidence behind them.

1. The customer-facing service agent

Salesforce describes a conversational service agent deployed across the in-product help menu for Xero’s five million customers, built on Agentforce. It holds natural, multi-turn conversations, and when the customer needs a person it hands off via chat, callback or a logged case. Salesforce’s Agentforce metrics page adds a structural detail: the agent coordinates specialised agents for banking, payroll and security. In other words this is not one monolithic prompt with a knowledge base bolted on; it is a routing layer over domain-scoped sub-agents.

2. The SDR agent

On the commercial side, Xero built an agent that behaves like a sales development rep for accountant and bookkeeper partners. Per Salesforce, it uses firmographic data captured at sign-up, writes personalised outreach, answers product questions, books meetings with human SDRs, and keeps CRM fields current — lead classification, assignment, prioritisation, outreach and follow-up.

so people can spend more time in conversations that actually move the needle

— Ben Gilmore, Head of Customer AI, Xero, Salesforce customer story

3. The real-time engagement layer

Separately from the Salesforce estate, Xero’s customer engagement team rebuilt onboarding intervention on Twilio Segment. Speaking at Twilio’s SIGNAL 2026 event in Sydney and reported by CXFOCUS, Xero’s Vladka Kazda described roughly 50 live real-time activations triggered off product behaviour and models including churn propensity and next best action, plus a self-optimising content agent built in 90 days that generates email variations and scores them against downstream product adoption rather than opens and clicks.

simply shifting our abandonment comms from a 24-hour delay to real time delivered an immediate three to six percentage point lift in conversion

— Vladka Kazda, Global EGM and SVP Customer Engagement, Xero, CXFOCUS

How the support path runs

1
Customer opens in-product help

The entry point is the help menu inside the Xero product, not a separate chat website, so the user is already authenticated and in context.

↓
2
Service agent holds a multi-turn conversation

Grounded in the Xero Central knowledge estate built since 2019.

↓
3
Routing to domain sub-agents

Salesforce describes specialised agents for banking, payroll and security coordinated by the service agent.

↓
4
Context from the data layer

Xero aggregates customer experience data in Snowflake and federates it into Data 360 with a zero-copy approach, giving agents a unified customer view without duplicating records.

↓
5
Escalation

When the customer needs a person, the agent hands off by chat, callback or a logged case rather than dead-ending.

The measured outcome

62%of support cases resolved autonomously by the service agentSource: Salesforce, 2026
800,000+cases a year across which the agent operatesSource: Salesforce, 2026
~500kservice agent conversations since launchSource: Salesforce customer story, 2026
3xopen rate on agent-generated partner sales emailsSource: Salesforce customer story, 2026
3–6 ptsconversion lift from moving abandonment comms to real timeSource: CXFOCUS, 2026
1 millioncustomers used Xero generative AI features in 12 months, with monthly users up ninefoldSource: diginomica, 2026

Two of those numbers deserve scrutiny rather than applause. The 62% figure appears on Salesforce’s Agentforce metrics page; the Xero customer story page carries a differently-worded stat card reading 65%+ online queries resolved autonomously. Those are almost certainly different denominators — cases versus online queries — measured at different dates. Anyone citing ‘62%’ as a benchmark should note that the vendor itself publishes two adjacent figures with different definitions.

The second is the comparison with the old system. A naive reading says Xero went from 97% to 62% and got worse. It did not. The 97% described help sessions resolved with personalised content in a self-service knowledge experience; the 62% describes support cases resolved autonomously in a conversational agent that can take actions and escalate. Different funnel stage, different unit, different bar.

DimensionPre-agent stackAgentforce service agent
Interaction modelSearch and retrieve, generated answers over knowledge baseMulti-turn conversation inside the product help menu
Reported outcome~97% of help sessions resolved with personalised content62% of support cases resolved autonomously
ArchitectureExperience Cloud, Salesforce Knowledge, Coveo-powered generative modelAgentforce with domain sub-agents, grounded via Data 360
EscalationCustomer finds a contact pathHandoff via chat, callback or logged case

What the public record does not establish

This is a vendor-published deployment. Salesforce has a commercial interest in the numbers, Xero has approved them, and no independent audit exists. Specifically:

No CSAT or quality figure is published for the service agent. Salesforce’s story says the handoff is seamless; it does not say what customers scored the experience, or how often an ‘autonomous resolution’ was followed by the same customer opening a case about the same problem a day later. Resolution rate without a reopen rate is half a metric.

No cost, headcount or handle-time figure appears anywhere in the public record. Xero has not said the agent saved X dollars or Y FTE-equivalents, and it would be irresponsible to infer one from 800,000 cases.

The 3x open rate is an early experiment. Salesforce frames it as the first six weeks of experimenting with the SDR agent. Open rates are the weakest signal in email marketing, inflated by image-proxy prefetching, and no downstream figure — meetings booked, partners onboarded, revenue — has been published.

The engagement-layer gains are not obviously LLM gains. Kazda attributes the three-to-six-point conversion lift to latency: moving abandonment comms from a 24-hour batch to real time. That is an event-streaming and orchestration win, which any team could bank without generative AI in the loop.

The model stack is undisclosed. Agentforce is the platform; which underlying foundation models serve which turns is not stated. Xero separately ships customer-facing AI with other partners, so the vendor landscape inside the company is plural.

What an integration team should learn

!

Buying the agent before you own the knowledge

The single most transferable fact in this case is chronological. Xero Central launched in 2019. The agent arrived in 2026. Salesforce explicitly credits years of investment in a centralised knowledge base as the repository of trusted proprietary content the agents now draw on. Teams that skip that step ship an agent that hallucinates confidently over a fragmented wiki.

Fix: audit answer coverage before procurement. If a competent human cannot resolve a ticket class from your documented knowledge, an agent will not either. Consolidate and curate first, then automate.
!

Copying customer data into the agent platform

Xero keeps its customer experience data in Snowflake and federates it into Data 360 with a zero-copy approach, so the agent reads a single source of truth rather than a stale replica. The common failure is the opposite: a nightly ETL into the CRM, which guarantees that the agent occasionally tells a customer something that stopped being true yesterday.

Fix: treat the data layer as part of the agent, not as a prerequisite project. Federate or stream; do not duplicate.
!

One giant agent instead of a routed team

Salesforce describes Xero’s agent coordinating specialised sub-agents for banking, payroll and security. Those domains have different data, different compliance exposure and different escalation rules. A single prompt trying to cover all three gets long, gets contradictory, and becomes impossible to regression-test.

Fix: scope agents to a domain with its own evaluation set, and put a thin router in front. You can then change payroll logic without re-testing security answers.

The sequencing is the strategy

Salesforce’s account of how Xero did it is a test-and-learn pattern: targeted experiments to validate agent performance before wider rollouts, and internal pilots — an employee assistant in Slack — before customer-facing use cases like the SDR agent. That order matters. Internal users tolerate a bad answer and report it; five million small businesses asking about payroll do not. Teams building similar workflow automation or agentic support systems should read the Slack assistant as the dress rehearsal that made the customer-facing rollout defensible.

2019

Xero Central launches as the consolidated self-service knowledge base.

2023–2025

Generative answers on Experience Cloud, Salesforce Knowledge and a Coveo-powered model resolve about 97% of help sessions with personalised content.

Mid 2026

Salesforce publishes the Xero customer story: SDR agent, Slack employee agent, and a conversational service agent rolled out across the in-product help menu for five million customers.

Late 2026

Salesforce reports 62% of support cases resolved autonomously across more than 800,000 cases a year; Xero’s CEO tells analysts one million customers used its generative AI features over 12 months, with monthly users up ninefold.

The wider context at Xero

The support agent is one slice of a much larger AI programme. On the product side, Xero ships JAX, its AI companion, and has been running XeroForce, a natural-language agent builder for accounting practices, in alpha. CEO Sukhinder Cassidy put adoption numbers on the record in November 2026.

One million customers have used our generative AI features over the last 12 months and monthly users are up ninefold year-on-year

— Sukhinder Cassidy, CEO, Xero, diginomica

For an integration team the relevant read is that Xero is running the same playbook in two directions at once: agents that reduce the cost of serving customers, and agents sold as product capability to those same customers. The internal deployment is the proving ground for the external one. If your own roadmap has an AI product on it, the support function is the cheapest place to learn what grounding, routing and escalation actually cost you. More deployment write-ups of this kind are collected in our case studies, and the model-selection trade-offs behind them in our models notes.

Autonomous resolution

Definition

A conversation closed by the agent without a human joining or a case being routed to a queue. Note what it does not guarantee: that the customer was satisfied, that the answer was correct, or that they did not return through another channel. Vendors rarely publish the reopen-rate denominator, and Xero’s published figures are no exception.

Frequently Asked Questions

What did Xero actually deploy?

Three things. A conversational service agent in the in-product help menu for its five million customers, built on Agentforce and coordinating sub-agents for banking, payroll and security. An SDR agent that nurtures accountant and bookkeeper leads and books meetings. And a real-time engagement layer on Twilio Segment that triggers onboarding interventions off live product behaviour rather than batched exports.

How many support cases does the agent resolve on its own?

Salesforce reports 62% of support cases resolved autonomously, across more than 800,000 cases a year. The Xero customer story page separately shows 65%+ of online queries resolved autonomously and roughly 500,000 service agent conversations since launch. The two percentages use different units and were likely measured at different times, so treat them as indicative rather than precise.

Did the agent replace support staff?

Nothing in the public record says so. No headcount, cost-saving or handle-time figure has been published by Xero or Salesforce. The stated framing is channel optionality and immediacy, with escalation to a human by chat, callback or logged case. Any claim that the deployment cut jobs or saved a specific sum would be invention, not reporting.

Why did the resolution rate appear to fall from 97% to 62%?

It did not fall; the units changed. The 97% referred to help sessions resolved with personalised content in the previous self-service search experience. The 62% refers to support cases resolved autonomously by a conversational agent that handles multi-turn problems and escalates. Comparing them directly is a category error, and it is a common one when reading vendor stat cards.

What is the most transferable lesson?

The knowledge base predates the agent by seven years. Xero’s agents are grounded in a curated repository the company had already invested in heavily, with a zero-copy data layer supplying live customer context. Most organisations attempting the same deployment are actually attempting two projects: a content consolidation project and an agent project. Budget for both.

Twarx analysis

Original interpretation

The agent is the last 10% of the project. Xero Central launched in 2019; the conversational agent arrived in 2026 and is grounded in that curated knowledge estate plus a zero-copy live data layer. Organisations attempting the same deployment are usually attempting two projects — content consolidation and agent build — and only budgeting for one.

Three design decisions are worth copying. First, domain-scoped sub-agents (banking, payroll, security) behind a thin router, which keeps prompts testable and lets one domain change without regression-testing the others. Second, zero-copy federation from Snowflake into Data 360 instead of nightly ETL into the CRM, so the agent reads a single source of truth rather than yesterday's replica. Third, sequencing: internal Slack pilots before customer-facing agents, and targeted experiments before wider rollout. Internal users tolerate a bad answer and report it; five million small businesses asking about payroll cutoffs do not. The honest caution is that the published evidence is resolution-rate-only. Without a reopen rate or CSAT, a 62% autonomous resolution figure tells you how often the conversation ended, not how often the problem did — and any team citing it internally as a benchmark should say so out loud.

Read the numbers honestly

Every service-agent figure comes from Salesforce, a vendor with a commercial interest, and none has been independently audited. Salesforce publishes two adjacent and differently-defined numbers — 62% of support cases on its metrics page, 65%+ of online queries on the Xero story page — so the headline should be read as indicative. No CSAT score, reopen rate, answer-accuracy measure, handle-time, cost-per-contact or headcount figure for the service agent appears anywhere in the public record; Xero has not published these. The 97% figure for the previous system uses a different unit (help sessions) and cannot be compared directly with 62% (cases). The 3x email open rate is a six-week experiment on the weakest metric in email marketing, with no downstream meetings, pipeline or revenue disclosed. The three-to-six point conversion lift is attributed to latency — real-time triggering versus a 24-hour batch — not to generative AI as such. The underlying foundation models serving the agent are not disclosed. Twarx had no involvement in this deployment; this is third-party analysis of published material.
agentic AIcustomer support automationSalesforce AgentforceSaaScase studyknowledge groundingmulti-agent architectureXerodata federationenterprise AI deployment
RS

Analysis by

Rushil Shah · AI Systems Builder & Founder, Twarx

Agentic AIMulti-Agent SystemsAI Workflow Automationn8nLangGraphAI Integration

From evidence to deployment

Want accounting & financial software (saas) results you can measure — and defend?

We deploy and audit AI agents the way we research them: real baselines, cited outcomes, and no inflated ROI. Twarx maps where an agent actually pays off for your team — and, just as honestly, where it won't.

  • A utility audit before you build — so budget goes where it moves the metric
  • Source-grounded benchmarks, not vendor marketing numbers
  • Deployed with measurement baked in, so ROI is provable later
Book a utility audit

The teams that win with AI agents aren't the ones with the boldest claims — they're the ones who measured honestly and deployed where the evidence actually pointed.

— Twarx Research