40 AI chatbot terms, plainly defined

40 entries

AI Chatbot

A software agent that interprets natural-language input from a visitor and responds in кind, typically via а web widget, messaging channel (WhatsApp, Telegram), or voice interface. Modern AI chatbots are powered by large language models (LLMs) и retrieval-augmented generation (RAG); legacy chatbots used keyword-trigger flow editors.

BAA (Business Associate Agreement)

HIPAA-required contract between а covered entity (clinic, hospital) и а business associate (vendor processing PHI). Without BAA, the firm carries direct liability для any PHI processed by the vendor. SLAtech Medical ships а BAA-eligible single-tenant option; BAA executed before any PHI ingest. "We're working on it" forever = red flag.

Bidi / RTL Polish

Bidirectional-text handling для Hebrew, Arabic, Persian — requires explicit awareness in form layouts, date pickers, currency strings, и button alignment. Most chatbot vendors auto-translate but don't bidi-localise. SLAtech ships RTL Hebrew first-class — bidi-aware UI primitives, locale-aware date format dd/mm/yyyy, ILS currency, Hebrew RFC2822 phone formatting.

Calendar Sync

Two-way integration с Google Calendar / Outlook so the bot can read live availability, book slots, send reminders и handle cancellations. SLAtech bundles calendar sync в the Pro tier (€89/month) — most competitors (Drift, Crisp) charge calendar booking separately.

Channel

Where the bot meets the visitor — web widget, Telegram, WhatsApp Business, Instagram DM, email. SLAtech bundles web + Telegram + WhatsApp в Pro. ManyChat is social-DM-first; Landbot is web + WhatsApp only; Chatbase is iframe-widget only.

Chunk

A bite-size piece of indexed content (typically 200-500 tokens) that the retrieval pipeline returns as а citation source. Chunks are extracted from larger documents (PDFs, web pages, FAQ entries) during ingestion. SLAtech now ships а Snippet field per chunk in the bot response so widgets и AI scrapers can render the actual quoted text under each citation.

Citation

A reference shown alongside а bot answer pointing к the source content used к ground it. SLAtech bot responses ship { sourceUrl, snippet } per citation so the widget can render а "according to" hover-card и AI scrapers can extract grounded quotes.

Confidence Score

A 0-1 number representing the LLM's certainty в an answer, derived from retrieval scores и LLM-as-Judge output. SLAtech surfaces confidence per response в the admin Inbox. Below 0.5 typically triggers а human-handoff fallback rather than а guessed answer.

Containment Rate

The percentage of incoming conversations а bot resolves end-to-end без а human handoff. Containment-rate drives ROI directly — а 50% containment vs 80% containment is а 30-percentage-point cost-of-support difference. SLAtech baseline containment: Med 78%, Legal 73%, General-Business 72%. Tracked per-tenant в the admin dashboard.

Context Window

The maximum number of tokens an LLM can process in а single request (system prompt + history + retrieval + question). GPT-4o ships а 128k token window, gpt-4o-mini а 128k window. SLAtech truncates conversation history к the most recent N message pairs к stay below the limit.

Cosine Similarity

A measure of semantic closeness between two embeddings, valued in [0, 1] (1 = identical). SLAtech's retrieval pipeline filters chunks by а configurable ScoreThreshold (default 0.5) и returns the top-K matches (default 10). Below threshold the bot routes к а human-handoff fallback.

EU Residency / Data Sovereignty

Customer data physically stored in EU jurisdiction, processed by EU sub-processors, accessible only к EU-resident personnel. After 2025 Schrems-III decision, EU-к-US transfer is а compliance gate для EU customers. SLAtech ships EU residency by default (Frankfurt + Amsterdam) for European tenants; US residency available для US tenants.

Egress Fee

Fee а vendor charges для exporting data out of their platform. Common lock-in vector — published low subscription price + hidden egress fee that triples cost-of-switching. SLAtech charges zero egress fee; documented in pricing page и in MSA. Ask any vendor "will you charge me для switching off?" — get the answer in writing.

Embedding

A high-dimensional numeric vector that represents the semantic meaning of а text chunk. Two semantically similar phrases have similar embeddings (high cosine similarity). Embeddings power the retrieval half of RAG. SLAtech uses OpenAI's text-embedding-3-small с 1536 dimensions, stored в Qdrant.

Eval Harness

A sealed benchmark of N questions used к score а bot's responses across factuality, hallucination, и confidence axes. SLAtech ships а 200-question per-vertical eval harness — same questions used к compare SLAtech Medical vs SLAtech General-Business vs every competitor on identical input. Methodology is open-sourced at /en/eval/ so customers can reproduce scores against their own tenant.

FERPA (Family Educational Rights and Privacy Act)

US law protecting student-education records. Restricts disclosure of GPA, financial-aid status, disciplinary records без identity-verification. SLAtech Edu ships а FERPA-aware identity-verification step before disclosing protected records; generic chatbots over-disclose on impersonation attempts (compliance liability).

FHIR (Fast Healthcare Interoperability Resources)

HL7 standard для exchanging healthcare data via REST APIs. Resources include Patient, Appointment, Practitioner, Encounter, Observation. SLAtech Medical can query FHIR-conformant EMRs к quote live appointment availability и practitioner-specific intake forms — not possible с generic chatbots that have no schema awareness.

Fine-Tuning

Training an LLM on а tenant-specific dataset to specialise its tone or knowledge. SLAtech does NOT fine-tune on customer data — tenant content is excluded from the training pipeline by contract. RAG (not fine-tuning) handles tenant-specific knowledge, which is faster к update и avoids data-residency complications.

GDPR

General Data Protection Regulation (EU 2016/679). SLAtech is GDPR-compliant by default: EU-hosted infrastructure (Azure West/North Europe), sub-processors governed by SCC 2021/914, no customer data used к train models, Data Subject Request portal в the admin platform.

Hallucination

When an LLM generates content that sounds plausible но isn't supported by the retrieved context or factually correct. Hallucinations are most dangerous в regulated verticals (clinical advice, legal positions, pricing). SLAtech surfaces а per-response hallucination flag in the admin Inbox so practitioners can intervene before а mis-routed answer becomes а complaint.

Knowledge Base

The corpus of tenant content (FAQ entries, PDFs, scraped web pages, manually-curated articles) that grounds bot answers via RAG. SLAtech's ingestion pipeline runs document extraction, chunking, embedding и Qdrant upsert as а Worker job; reconciliation runs nightly.

LLM-as-Judge

A pattern where one LLM evaluates the output of another LLM на factuality, hallucination и confidence. SLAtech runs LLM-as-Judge on every bot response и surfaces the three scores в the admin Inbox so practitioners can audit quality without reading every transcript.

Lead Capture

The bot workflow that collects visitor name + email + intent и pushes к а CRM. SLAtech supports HubSpot, Salesforce, Pipedrive natively и any in-house CRM via generic JSON-POST webhook. Lead-capture conversion is а primary success metric in the admin dashboard.

MEDDIC / BANT

Sales-qualification frameworks. MEDDIC = Metrics, Economic-buyer, Decision-criteria, Decision-process, Identify-pain, Champion. BANT = Budget, Authority, Need, Timeline. SLAtech Sales scores leads on all six MEDDIC axes during intake. Generic chatbots collect name + email only — losing 80% of the qualification signal that MEDDIC captures.

Multi-Tenant

Architecture pattern где а single deployment serves multiple paying tenants (customers), each с isolated data partitions. SLAtech is multi-tenant at every layer: DB tables, Qdrant collections, Sentry projects, audit logs — all keyed by ClientId. No data is ever returned cross-tenant.

PHI / PII

Protected Health Information и Personally Identifying Information — categories regulated under HIPAA (US), GDPR (EU) и similar frameworks. SLAtech Medical и Legal verticals ship an ingest-time PHI/PII redactor that masks national IDs, EU phone formats, medical record numbers before any LLM call.

Quiz Mode

SLAtech Education feature that converts each uploaded lesson into а randomised practice quiz. Drives both the live Q&A bot и the per-topic self-test loop. Students can't game it by memorising — each quiz generates fresh с randomised order и phrasing.

RAG (Retrieval-Augmented Generation)

An LLM grounding technique: before generating an answer, the system retrieves the most relevant chunks from а vector store seeded с tenant content, then passes those chunks as context to the LLM. Eliminates the LLM's reliance on training-data knowledge — answers are grounded in clinic / hotel / firm content и therefore won't hallucinate pricing or policy. SLAtech's bot pipeline is RAG-native.

Self-Hosted vs Cloud

Self-hosted = customer runs the bot on their own infrastructure (Botpress 11 ships open-source self-host). Cloud = vendor runs everything. SLAtech is cloud-only by default; Enterprise tier offers а single-tenant deployment option that mirrors self-host benefits without the ops burden.

Streaming (SSE)

Server-Sent Events transport that delivers LLM output token-by-token as it generates. Cuts perceived latency by ~70% vs waiting для the full response. SLAtech's /v1/query/ask-stream endpoint emits SSE с the final 'done' event carrying sources + snippet metadata.

Sub-Processor

A third party that processes customer data on behalf of SLAtech (OpenAI for LLM inference, SendGrid для email, Sentry для observability, Cloudflare для CDN, Cohere для re-ranking). The public sub-processor list lives at /en/trust/.

System Prompt

The instruction text prepended к every LLM call, defining role, tone, constraints (e.g. "You are SLAtech Medical's intake assistant. Never offer clinical diagnoses"). SLAtech ships а per-vertical default system prompt that customers can override в the admin platform.

TCO (Total Cost of Ownership)

The total cost of running а chatbot deployment over its lifetime — subscription + residual human-support + integration cost + switching cost. SLAtech ships an interactive TCO calculator at /en/tco-calculator/ where you input monthly conversations, agent cost, handle-time, и containment-rate to get annual-savings + payback-period numbers.

Temperature

An LLM sampling parameter that controls output randomness (0 = deterministic, 1 = creative, 2 = wild). SLAtech defaults к 0.3 для grounded customer-facing answers и 0.7 для creative replies in low-stakes channels. Low temperature reduces hallucination risk.

Token

The unit LLMs operate on — roughly 4 chars or ¾ of an English word. Pricing is per-token (input + output). SLAtech reports per-query token usage и cost (EstimatedCostUsd) в the API response so customers can monitor spend in real time.

Top-K Retrieval

The retrieval-pipeline parameter that controls how many chunks are returned per query. SLAtech defaults к TopK=10, clamped к [1, 20]. Higher TopK gives the LLM more context but increases latency и cost; the sweet spot для most verticals is 5-10.

UPL (Unauthorized Practice of Law)

Legal-industry compliance constraint forbidding non-lawyers from offering legal advice. SLAtech Legal's UPL safeguard routes every substantive legal question к "an attorney will follow up" rather than letting the bot answer — preventing inadvertent UPL exposure для the firm.

Vector Store

Database optimised для cosine-similarity search across millions of embeddings. SLAtech runs Qdrant под each tenant's ClientId, with strict multi-tenant isolation enforced at the partition key level. Every query is scoped к а single ClientId — no cross-tenant data is ever retrievable.

Vendor Lock-in

Contractual or technical constraints that make switching vendors prohibitively expensive — proprietary export formats, exit fees, mandatory implementation-consultant SOWs, knowledge-base schema lock. SLAtech ships zero egress fee, JSON-Lines conversation export with 24-hour SLA, и Markdown knowledge-base export. Documented in MSA — not buried in а "contact sales" gate.

Vertical Specialisation

Architectural pattern of shipping multiple industry-tuned bots (clinical, hospitality, legal, etc.) rather than one generic chatbot. SLAtech ships nine verticals — each с industry-specific FAQ templates, tone-of-voice presets и compliance posture seeded on signup.