Agents Makers
Capability of Support AgentDefault at launch

FAQ & Knowledge-Base Resolution

Answers recurring policy, product, and onboarding questions from approved knowledge.

  • Activation complexity

    Low

  • Time to activate

    3-7 days

  • Volume share

    30-45% of role volume

  • Impact range

    40-60% of FAQ-eligible volume

Inherited pricing

€0.30 – €0.90 per ticket handled

This capability inherits the Support Agent's pricing model. The role's launch fee + monthly retainer + role-level usage cover every capability under the role. Adding this capability to an active deployment does not change the price.

What this capability handles

How it works in detail.

FAQ and Knowledge-Base Resolution handles the long tail of repetitive questions that clog a support queue: the same policy, product, onboarding, and how-to questions a team answers dozens of times a day. Left to people, these are low-value but high-volume, and they push first-response time up for everyone else in the queue. This capability clears them at the source. It recognizes when an incoming message is a known question, retrieves the right approved article, answers in plain language, confirms the customer is satisfied, and only involves a person when the knowledge is missing or the request turns account-specific. It works across the surfaces customers actually use: the help desk, your knowledge base, and website chat. On each question it runs five stages: question-detect (is this a known theme?), retrieve (pull the approved article), answer (respond clearly, in context), confirm (check the answer resolved it), and escalate (hand off cleanly when it cannot). Its inputs are the question text, your article corpus, product terminology, and the customer's tier, so the answer fits both the question and who is asking. The decision logic is deliberately narrow: it matches the question against known themes and serves only approved answer paths, and only when confidence is high. It does not improvise on policy. When there is no strong match, or the request becomes account-specific (a particular invoice, a specific account state), it stops and routes to a person rather than guessing. That keeps answers safe and on-message, and every interaction is logged, so gaps in the knowledge base surface quickly and your team can close them. Typical fit: teams with reasonable knowledge-base coverage, approved wording for sensitive topics, and a clear gap-review process. FAQ-type questions are usually 30-45% of a support role's volume, and this capability resolves 40-60% of the eligible questions without a human touch, which is often the single biggest driver of the role's overall deflection. The main maintenance task is keeping the knowledge base current: the better your articles, the more it deflects.

Workflow summary

Recognizes common questions, retrieves approved knowledge, answers clearly, confirms resolution, and escalates when knowledge is missing.

Stages

  1. 01question-detect
  2. 02retrieve
  3. 03answer
  4. 04confirm
  5. 05escalate

Decision logic

Matches the question against known themes and serves only approved answer paths when confidence is high.

Systems and data

{"knowledge base","help desk","website chat"}

{"question text","article corpus","product terminology","customer tier"}

Exceptions & human handoff

When no strong answer exists or the request becomes account-specific, the agent stops and routes to a person.

Missing knowledge coverage, account-specific ambiguity, or policy-sensitive request.

Readiness

Good knowledge-base coverage, approved wording for sensitive topics, clear gap-review process.

Owner on client side · Knowledge Manager

Impact contribution

25-40% of deflected volume typically comes through the FAQ capability.

Primary KPI · Resolution rate without human touch · 40-60% of FAQ-eligible volume

When this capability shows up

Real-shape scenarios.

Patterns where faq & knowledge-base resolution is part of the launch set, with volume and pricing anchored to each company profile.

  • 40-person SaaS, steady support volume

    SaaS · 40-80

    2,000 / mo

    A 40-person SaaS company with 2,000 monthly tickets usually runs with one senior support lead plus one junior handling queue volume. Around 60% of that volume is repetitive: plan questions, password resets, onboarding walkthroughs, basic integration help. The team already has a decent knowledge base, but it is scattered and nobody has time to reshape it.

    Support Agent activates the three capabilities that match this company's repetitive core, triage, FAQ resolution, and billing questions, operating inside the existing help desk. Routing preserves team ownership of the 15% of tickets that still need judgement. Knowledge gaps surface automatically so the team finally gets to reshape the KB.

    Expected outcomes at this volume: 35-45% of tickets handled without human touch, first response under 2 minutes on the automated paths, queue load on the two humans roughly halved. Sentiment and CSAT hold because the escalation path stays clean and context-rich.

    Monthly cost

    €600€1.8k

    vs human anchor

    €4.5k€12k

    Savings

    03%

  • Mid-market eCommerce, peak seasonality

    eCommerce · 80-200

    8,000 / mo

    A mid-market commerce brand with 8,000 monthly tickets typically runs 5-7 agents. Repetitive order-status, shipping, and refund inquiries dominate, especially through peak periods where volume can double in two weeks. Temporary agent hiring is slow and rarely matches quality.

    Support Agent activates four capabilities, triage, order status, refunds, FAQ, all tied to real order and carrier data. During peaks, the agent absorbs the volume spike without the lead time of hiring seasonal staff. Complex refund disputes and fraud-flagged cases still route to humans with full context.

    Expected outcomes at this volume: 40-55% deflection on the repetitive core, peak-period backlog held flat rather than growing, existing humans reallocated to high-value cases, SLA compliance protected. Payback measured in weeks once peak hits.

    Monthly cost

    €2.4k€7.2k

    vs human anchor

    €19k€48k

    Savings

    02%

  • Marketplace at scale, multilingual

    Marketplaces · 200-500

    20,000 / mo

    A 300-person marketplace serving multiple EU languages handles 20,000 monthly tickets across 5-7 queues, with escalation obligations to operators on both sides of the marketplace. Language distribution creates staffing inefficiency: either the team over-hires to cover less-common languages or response quality suffers outside peak hours.

    Support Agent runs full multilingual coverage, triage, and escalation routing. Routing respects the dual-sided operator obligations. Human team focus shifts to operator relationships and complex adjudication while sub-minute response is maintained across 30+ languages.

    Expected outcomes at this volume: 30-50% deflection across languages, 24/7 response coverage without night-shift staffing, consistent quality across languages tracked per language so drift never goes silent. Senior team focus returns to complex adjudication.

    Monthly cost

    €6.0k€18k

    vs human anchor

    €47k€121k

    Savings

    02%

All scenarios and cost ranges come from the Support Agent role page.

Prerequisites

Activate these first.

Activating FAQ & Knowledge-Base Resolution in production requires the following capabilities to be live first. Ordering matters, routing and classification quality propagate.

Capability-specific integrations

Additional systems for FAQ & Knowledge-Base Resolution.

Beyond the Support Agent's base stack, this capability plugs into:

Last reviewed

Activate FAQ & Knowledge-Base Resolution as part of a Support Agent deployment.

Your free Agent Opportunity Audit opens with Support Agent and FAQ & Knowledge-Base Resolution pre-selected. We map the fit and the cost against the equivalent hire, with no obligation.