The ClickToAutomate glossary defines the words used in a fitted AI build — retrieval, RAG, guardrails, hand-off, and model-agnostic keys — in plain language, the same way we use them on a 30-minute discovery call.
31 terms · Jump a letter, filter a theme, or search
A
An AI layer is the retrieval, routing, guardrails and hand-off assembled around a workflow — not a chatbot dropped on a page.
See alsoFitted buildGuardrailHand-off
A way for software to talk to another system. We use your APIs — and model APIs such as Sarvam, OpenAI, Claude or Gemini — so the layer sits on the stack you already run.
See alsoIntegrationKeysWebhook
A reviewable record of what the layer did: retrieved sources, replies sent, actions queued, and who approved a high-stakes step.
See alsoHuman-in-the-loopGuardrail
A workflow that runs without a person repeating the same clicks — for example a form submit that writes a CRM record and sends a follow-up. In our builds, high-stakes steps still wait for a person.
See alsoTriggerWorkflowHuman-in-the-loop
B
An AI widget that sits on top of a site without reading your documents, CRM, or policy. It sounds fluent and still fails the first real question. The opposite of a fitted layer.
See alsoAI layerFitted buildRAG (retrieval-augmented generation)
C
A pointer back to the document, ticket, or catalogue row the answer used. If we cannot cite it, we should not invent it — we hand off instead.
See alsoRAG (retrieval-augmented generation)RetrievalHand-off
The system of record for leads, contacts and deals. A fitted build writes qualified conversations into it with the fields sales actually uses — not a side spreadsheet.
D
Where the data lives — your cloud region, your infrastructure, your retention rules. We can build entirely on what you already run.
A discovery call is a 30-minute, no-obligation conversation. ClickToAutomate walks through how the work actually runs. You leave with a written plan: scope, approach, and trade-offs. We will say if a platform already fits better.
See alsoFitted buildEvaluation harness
E
A numeric representation of a chunk of your knowledge, used to find the closest matches at answer time. Useful machinery — not something you should have to think about on the call.
F
A fitted build is researched software scoped to one workflow on the tools you already pay for — shipped live, not a chatbot to configure.
See alsoAI layerStackDiscovery call
G
Forcing the reply to come from retrieved sources instead of the model's memory. Grounded answers can be cited. Ungrounded ones are where hallucinations start.
See alsoCitationRetrievalRAG (retrieval-augmented generation)
A guardrail is a hard boundary: what the AI may answer, what it must confirm, and what it must never attempt — clinical advice, unsupervised refunds, inventing a policy, and so on.
H
Hand-off is escalation to a person with the transcript, detected intent, and the relevant CRM or helpdesk record already loaded — so nobody is asked to start over.
I
A connection to a system you already pay for — CRM, helpdesk, WhatsApp, catalogue, calendar — so the AI layer does not become another login.
What the person is actually trying to do, read from the full message rather than a keyword. Intent is what we route on: answer, qualify, or hand off.
K
The model-provider accounts used to run the product. We pick OpenAI, Claude, Gemini, Sarvam or open models for the task; the design stays swappable as models improve.
See alsoModel-agnosticSarvam AI
L
M
P
The stages a lead or deal moves through. A fitted layer can update stage from real conversation signals, not only form fills.
See alsoCRMLead qualificationWorkflow
R
RAG (retrieval-augmented generation) is when a model answers from your documents and systems, with citations back to the source, instead of improvising from memory.
Finding the right chunks of your knowledge at answer time — help centre, policies, catalogue, past tickets — then grounding the reply in them.
See alsoRAG (retrieval-augmented generation)EmbeddingCitation
S
An India-first model lab. Click To Automate is in the Sarvam.ai Startup Program and can call their voice and language APIs alongside OpenAI, Claude and Gemini when the work needs them.
See alsoModel-agnosticKeys
The tools you already pay for: CRM, helpdesk, WhatsApp, catalogue, calendar, internal docs. We wire the layer into that stack instead of asking the team to live in a new product.
See alsoIntegrationFitted build
T
The full conversation so far. On hand-off it travels with the detected intent and the relevant record, so the person picking it up does not re-ask what was already said.
An event that starts a workflow — a form submission, a new CRM record, a webhook, a WhatsApp message.
See alsoWebhookWorkflowAutomation
W
An HTTP callback that sends data when something happens. Used to connect the AI layer to tools that do not share a native API path.
See alsoAPITriggerIntegration
A sequence of steps — trigger, actions, conditions, hand-off — scoped to how your team actually works. First builds are one workflow, in production, in weeks.
FAQ
A plain-language list of the words we use for a fitted AI build: retrieval, RAG, guardrails, hand-off, stack, and discovery call. Definitions match how we talk on a 30-minute discovery call — not a marketing jargon dump.
A fitted AI layer is researched against how your company already works and wired into the CRM, helpdesk, WhatsApp, and docs you already pay for. A bolt-on chatbot sits on a page, guesses from memory, and fails the first real question. ClickToAutomate builds the former.
Hand-off is escalation to a person with the transcript, detected intent, and the relevant CRM or helpdesk record already loaded, so the customer is not asked to start over. High-stakes actions wait for that person.
The design stays swappable across OpenAI, Claude, Gemini, Sarvam, and open models. ClickToAutomate benchmarks for the task; the client keeps the API keys. Costs and the off switch stay under the client's control.
No. The call is where we map the workflow in your words. This glossary is for when a page on the site uses a term you want pinned down. Thirty minutes, written plan, no obligation.
Thirty minutes. Bring the workflow. We will use these words the same way — and send a written plan afterwards. No obligation.
We’ll tell you if a platform already fits better.
A 30-minute discovery call to research the use case together. You leave with a written plan — we'll tell you if a platform already fits better.
