Evoriqa

One Postgres for data and vectors

Tenants, billing and vector search all live in PostgreSQL with pgvector, so a tenant's documents and their embeddings fall under the same isolation. The trade-off is one database to scale instead of a dedicated vector store.

Knowledge processed off the request path

Uploads are processed by a background worker with retries, so a large upload never slows the app, and an edit made while a source is being processed is never lost.

Hybrid search, ranked together

Each question combines semantic and keyword search, scoped to one workspace and one agent, so exact terms and product names are found as well as paraphrases, and questions in Arabic or Chinese are not silently ignored.

Grounded, or a fixed fallback

When the knowledge base holds no good answer, the agent gives a fixed reply instead of guessing, and spends nothing on the model to do it.

Safe across embedding changes

Switching embedding providers does not scramble search results while the knowledge base is being re-indexed.

Measured quality, not assumed

Test cases can be run against the live agent and scored by a model judge, and individual replies can be scored in the background. Each answer stores what it was based on (the chunks, scores and prompt) so a team can see why it said what it said.

One credit balance for every AI action

Chat, voice, actions and knowledge ingestion all draw from a single credit balance, so a workspace can see exactly what its AI use costs.

Caps and warnings, not surprise bills

Workspaces can set a monthly spend cap and owners are emailed as usage crosses thresholds. When credits run out, customer messages still reach a person instead of being lost.

Shadow mode before autonomy

Between human-only and fully automatic, the agent can draft every reply into the team inbox, and nothing reaches the customer until a person sends it. Per-channel numbers (drafts, approvals and how much people edit) show when a channel is ready to run on its own.

Live human takeover

A teammate can claim any conversation and reply in real time, with every open inbox kept up to date.

Secrets encrypted, staff kept apart

Integration credentials and sign-in secrets are encrypted at rest, users can turn on two-factor sign-in, and platform staff use their own accounts, separate from customers.

One agent on every channel

The web widget, WhatsApp, Messenger, Instagram, Slack, SMS, email and a phone line all feed one workspace, with business hours and human handoff per agent.

Agencies resell under their own brand

Agencies hold a pooled credit balance, allocate it to client workspaces, connect their own Stripe account to bill those clients at their own prices, and can send email through their own provider.

A working agent with no sign-up

A visitor pastes a website address and gets a live, shareable agent built from that site, which can be claimed into a real workspace with its knowledge intact.