Seller context
Turn messy source material into claims the agent can trust.
Seller context is the base layer for every journey. Vera accepts notes, URLs, and files, then turns them into knowledge claims with source, trust, evidence, and coverage metadata.
Multipart request
Add notes, URLs, and files.
Upload the operator's raw material before asking Vera to prospect or draft. Agents should treat uploads as source material, not copy-ready truth.
$ curl -X POST https://api-vera.symph.ai/v1/projects/proj_01hx6x9v2r/context \
> -H "Authorization: Bearer vwk_live_..." \
> -F "notes=Positioning notes, ICP notes, objection handling..." \
> -F "urls=https://example.com/pricing" \
> -F "urls=https://example.com/case-study" \
> -F "files=@./product-one-pager.pdf"notesstringOptional free-form context.
urlsstring[]Helpful URLs to crawl or summarize.
filesFile[]PDF, text, markdown, office files, and supported media.
Discovery
Convert context into reviewable knowledge.
Business discovery extracts seller claims and source evidence. It should run before the agent searches for prospects or writes email.
$ curl -X POST https://api-vera.symph.ai/v1/projects/proj_01hx6x9v2r/runs \
> -H "Authorization: Bearer vwk_live_..." \
> -H "Content-Type: application/json" \
> -d '{
> "operation": "discover_business",
> "inputs": {
> "refresh": false,
> "source_types": ["company_website", "external_search"]
> }
> }'Claims
Read and edit extracted knowledge.
External agents should reuse approved claims and source evidence. If a claim is disputed, rejected, or missing evidence, stop and ask for review before using it downstream.
$ curl https://api-vera.symph.ai/v1/projects/proj_01hx6x9v2r/knowledge \
> -H "Authorization: Bearer vwk_live_..."
$ curl -X PATCH https://api-vera.symph.ai/v1/knowledge-claims/claim_01hx81mk2q \
> -H "Authorization: Bearer vwk_live_..." \
> -H "Content-Type: application/json" \
> -d '{ "status": "approved", "trust_level": "user_confirmed" }'