Grounded AI with your company knowledge, on by default.
dolv prepends your company profile, your playbooks and your crawled knowledge base to every AI call, so agents answer from your business instead of the open web's average — then turn that context into real work.
14 days free · no card · grounding on by default · opt out explicitly, one call at a time
- Company profile
- Playbooks
- Knowledge base
- Live connector data
The AI knowledge base for go-to-market.
The grounding block is built from three real sources — your saved company profile, your playbooks and a crawled knowledge base — and grounded chat reads live data on top. Set them once; every grounded answer draws from them after that.
-
Your company profile
Who you are, what you sell, your ICP and your positioning — saved once in Settings and read on every call, by every agent.
Connect → execute → measure -
Your playbooks
How you actually run: the offers, the sequences and the rules your team already follows, so agents work your way instead of a generic way.
AI marketing automation -
Your knowledge base
Your site and your docs, crawled into knowledge. The crawl4ai-powered engine ingests your pages with a BFS fallback, and the Settings "Website" field auto-saves each crawl.
How to ground AI in company knowledge -
Your live data
Grounded chat does not stop at what it was told. It reads live through 30 read-and-write connectors, so the context is current instead of a snapshot.
All 30 integrations
Point dolv at your site once and the same block reaches chat, agents and campaigns — nobody attaches context by hand again.
The same brief, answered twice.
If you have pasted your positioning into a prompt for the third time in a day, or rewritten an AI draft so it stops sounding like everyone else, grounding is the fix. Connect your stack once and the same context reaches AI agents, marketing automation and sales & CRM.
A generic model guesses.
An off-the-shelf LLM knows the internet's average answer — plausible copy you rewrite until it sounds like your company.
Grounded AI knows you.
The same brief, read against your product, your ICP, your voice and your rules — so the draft already fits before you edit a word.
Both panels are illustrative — no customer data, no figures we cannot show you in the product. Because the content tools draft from your grounding block, emails, LinkedIn posts and WordPress drafts inherit your voice: read how to keep AI on brand, then see the same grounding feed funnel intelligence.
How dolv grounds every AI call.
Under the hood, getOperatingContext assembles your company profile, playbooks and knowledge into one grounding block and prepends it to every callLLM and callLLMStream. It is not a feature you remember to enable — it is the default, which is why dolv reads as context-aware, grounded AI across the whole product.
Assemble
getOperatingContext pulls your company profile, your playbooks and your knowledge base into one consistent grounding block — the same block, every time.
Prepend
That block is prepended to the call before the model ever sees your request, so it reasons from your business first and not from the open-web average.
Reason
The model answers in your context — your product, your ICP, your voice and your rules — so the output already fits your company instead of needing a rewrite.
Act
Grounded chat then calls real tools to draft, prepare and queue work in the Approvals inbox: grounded reasoning that turns into grounded action.
Grounded AI vs RAG vs prompt-stuffing.
"Grounded AI" gets used loosely. Here is the plain-language difference between dolv's always-on grounding, bolt-on RAG for business, and the old habit of pasting context into a prompt by hand.
| Dimension | dolv grounded AI | Bolt-on RAG | Prompt-stuffing |
|---|---|---|---|
| When context is added | On every call, by default. Opting out is the explicit choice. | Only when a retrieval step is wired in and runs successfully. | Only when a person remembers to paste it into the prompt. |
| What gets included | Company profile + playbooks + knowledge as one assembled block. | Top-matching snippets from a vector store, for that one query. | Whatever fits in the box that day — easy to forget half of it. |
| Consistency across the team | The same grounding for chat, agents and campaigns. Nobody opts in. | Varies by how each query retrieves; tuning lives in the pipeline. | Depends on the person — output drifts off-brand fast. |
| Does it also act? | Yes — grounded chat calls 91 tools to do real work, in the loop. | No — retrieval improves an answer; it does not execute work. | No — it is a one-off message, not an operating system. |
Want the deep dive? Read how to ground AI in company knowledge, or the grounded AI definition in the glossary.
Grounding, everywhere the work happens.
The same block for chat, agents and campaigns. Nobody opts in, nobody forgets the context, and the output does not drift off-brand.
On by default
getOperatingContext assembles your context and prepends it to every callLLM and callLLMStream. Standard behaviour, not a mode.
Three sources, one block
Company profile, playbooks and a crawled knowledge base assemble into one block — chat, agents and campaigns all share it.
On-brand by design
compose_content and the prepare_* tools draft from that block, so emails, posts and WordPress drafts sound like you.
Grounded and agentic
Grounded chat also acts: it calls 91 tools to read live data and prepare real work, all reasoned from your business.
Same block for agents
Configurable agents and multi-agent campaigns inherit the same block — every run logged, capped to a $250/mo budget.
Explicit opt-out
Default-on, never trapped: grounded:false returns a raw, ungrounded response for that one call. The default never moves.
Grounded AI, answered
What grounding means, which sources feed it, how it differs from RAG, and how to opt out of it.
What does "grounded AI" mean?
Grounded AI means the model's answers are anchored to your company's own knowledge — your company profile, your playbooks and your knowledge base — instead of the open web's generic average. In dolv, grounding isn't a mode you switch on for special tasks: getOperatingContext assembles that company context and prepends it to every AI call, so chat, agents and campaigns all reason from your business by default.
How does dolv keep AI on-brand and on-context?
Every callLLM and callLLMStream in dolv prepends the same grounding block — company profile, playbooks and knowledge — before the model ever sees your request. Because the content tools (compose_content and the prepare_* outreach tools) draft from that block, emails, LinkedIn posts and WordPress drafts come out sounding like your company, not like generic AI. On-brand is the default state, not a checklist step.
Is grounding on by default, or do I have to turn it on?
Grounding is on by default. You don't enable it per task or remember to attach context — it is the standard behaviour for every LLM call across chat, configurable agents and multi-agent campaigns. Opting out is the explicit choice ({grounded:false}) for the rare case where you want a raw, ungrounded response. That default-on design is the core difference from bolt-on retrieval you have to wire up.
What sources feed dolv's company knowledge base?
Three sources form the grounding block: your saved company profile, your playbooks, and a knowledge base. The knowledge base is built by crawling your website — the crawl4ai-powered engine ingests your pages (with a BFS fallback), and the Settings "Website" field auto-saves those crawls into knowledge. Point dolv at your site and your docs once, and every grounded answer draws from them after that.
Is grounded AI the same as RAG?
They are related but not identical. RAG (retrieval-augmented generation) bolts a retrieval step onto a query — it fetches matching snippets when the pipeline runs. dolv's grounding is default-on: it always assembles your company profile, playbooks and knowledge for every call, the same way for chat, agents and campaigns, and that grounded context also feeds tools that execute real work.
Can I stop the AI from using my company context for a specific task?
Yes. Grounding is default-on, but it is also explicitly optional — passing {grounded:false} produces an ungrounded response for that single call without changing the default everywhere else. So you keep on-brand, on-context output by default and still have a clean escape hatch when you genuinely want a raw answer.
Does grounded AI work for a whole go-to-market team?
The grounding is the same for one person or a whole team — nobody opts in, nobody forgets the context, and output doesn't drift off-brand. Point dolv at your site, connect your stack, and the same company knowledge reaches AI agents, marketing automation and sales & CRM. Every plan includes every feature, starting with a 14-day free trial.
Don't rewrite it. dolv it.
Point dolv at your website, connect your stack, and see grounded AI run on your own data. From $79 a month after the free 14 days. Every plan includes every feature.