Enterprise

Your Models. Your Cloud.
Your Infrastructure.

The enterprise platform for banking, insurance, financial services, and single-family rentals. Bring the API keys you already pay for, your own cloud, or open models on your own GPUs — deployed inside your environment, with the deepest support tier we offer.

The Enterprise Experience

Multi-user AI platform with SSO, compliance, and live-checked integrations

ContextuAI Enterprise — AI Chat Dashboard

Enterprise AI Chat — multi-model, multi-persona, streaming responses

ContextuAI — AI Team Workspace

AI Team Workspace — multi-agent orchestration

ContextuAI — AI Automations

Automations — scheduled AI workflows

ContextuAI — Code Studio

Code Studio — five governed job modes

Bring Your Own Everything

Already Have a Model Vendor?
Keep Them. Add the Rest.

Under contract with Anthropic or OpenAI? Standardised on Azure or Google Cloud? Want open weights on your own GPUs? All three are first-class here — configured from the UI in minutes, mixed freely inside one deployment.

vpn_key

Bring Your Own API Keys

Already have an agreement with Anthropic or OpenAI? The integration is already built. Paste your key and it works — you keep the relationship, the rates and the terms you negotiated, and you stay the customer of record. We never sit between you and your vendor.

cloud_done

Your Own Cloud

Azure OpenAI, Google Vertex AI, or AWS Bedrock — the model runs inside your cloud account, under the enterprise agreement, region, and data-residency terms your procurement team already signed off.

memory

Your Own Weights

Open models on hardware you own, through the runtime we ship in the box or any OpenAI-compatible server. Keyless — a base URL, not a credential. No meter, no vendor, no egress.

Live in under five minutes

Providers are configured per organization, from the admin UI — no code changes, no redeploy, and no environment variables to talk an ops team into. Add the provider, test the connection before you commit it, save, and your model catalog populates itself.

1

Add the provider

Pick from eight, paste the credential or base URL

2

Test the connection

Verified before it is ever saved — no silent misconfiguration

3

Save — the catalog fills itself

Available models are discovered and seeded for your org

all_inclusive

Unlimited, When You Want It

Run an open model on your own hardware and nobody is metering it. Every chat, every crew, every scheduled workflow — and the invoice doesn't move. Put the frontier model where it earns its price and the open one everywhere else.

lock_person

Private Stays Private

The platform is self-hosted, so your data sits in databases you control. Choose a self-hosted model and prompts never leave your perimeter at all — there is no outside to leave to. Even Knowledge Base embeddings default to running locally.

tune

Per Agent, Not Per Platform

This isn't one global switch. Each agent resolves its own model, falling back to its team's default — so a sensitive workflow can stay on local weights while the one beside it calls a frontier model.

Point It at Anything

Eight providers behind one dispatcher — mix them in a single deployment

Frontier, Direct

Your contract, your keys, your rates

Anthropic — Claude OpenAI Google — Gemini

Through Your Cloud

Under the agreement you already signed

AWS Bedrock Azure OpenAI Google Vertex AI

Self-Hosted

Bundled runtime, or any OpenAI-compatible server

Ollama — in the box vLLM & friends Your GPU cluster

Leading US Open Models

Open weights from the labs your board already recognises

Llama — Meta gpt-oss — OpenAI Gemma — Google Phi — Microsoft

Top Open Models from China

The frontier-class open weights teams keep asking for

DeepSeek Qwen — Alibaba Kimi — Moonshot
8
Providers behind one dispatcher — mix open and frontier models in the same deployment
0
Silent fallbacks — a model you didn't ask for never quietly serves your request
1
Governance path — every model obeys the same policies, budgets, and audit trail, whoever serves it

Whichever door you come through, the rules are the same: a model has to be enabled in your organization's catalog before a single token flows, and that check runs before any credential is read. Reasoning models are handled properly too — on the gateway, chain-of-thought is stripped by default and returned only when you ask for it.

Agentic Event Bridge

Real-Time Events Across
Every Channel

Connect AI outputs to the outside world with a 3-layer event architecture — subscriptions, distribution channels, and messaging bots.

1 webhook

Event Subscriptions

persona.message.created Webhook (https://api.ex...)
crew.run.completed Slack (#ai-alerts)
automation.executed Email (ops@...)
2 campaign

Distribution Channels

LinkedIn Twitter Email Slack
3 smart_toy

Channel Bots

groups
Teams Bot
Bot Framework v4
forum
Discord Bot
Ed25519 verification
tag
Slack Bot
Bolt — triggers workflows end to end
Control Center

One Dashboard to
Rule Them All

Integrations, security, compliance, and provisioning across four tabs — each card a live check, not a static badge, all run in parallel every time the page loads.

chat Slack Bot
groups Microsoft Teams
forum Discord
http Webhooks
notifications_active Event Subscriptions
campaign Distribution Channels
mail Email / SMTP
memory Agent Runtime
verified Connector Certification
https TLS Encryption
security MFA / 2FA
login SSO / SAML
vpn_key API Key Auth
speed Rate Limiting
policy ABAC Policies
inventory_2 Dependency Scanning
bug_report Vulnerability Tracking
history Audit Trail
gavel AI Governance
fingerprint PII Detection
auto_delete Data Retention
podcasts Audit Forwarding (SIEM)
timeline Distributed Traces
monitoring Span Capture
person_add SCIM Users
group_add SCIM Groups
28
Integrations — every one a live check, run in parallel on load
9
Configurable in place — inline slide-out editors
7
Admin editors — governance, MCP gateway, evidence, certifications, screen access, coding providers, cost

The page renders what your role can actually use. Every card and every editor tab mirrors the gate on the route behind it, so an operator is never handed a form that 403s on save — and a stat tile reads blank rather than zero when a role wasn't shown the cards it would have counted.

Code Studio

Five Ways to Put
Agents on a Codebase

Point Code Studio at a repository and pick the job. Each mode brings its own phase pipeline, its own suggested agent team, and its own deliverable — a pull request, a report, or a documentation bundle.

upgrade

Migrate

Move a codebase to a named target version — Java, Spring Boot, Python, Node.js, .NET. Ends in a pull request on your target repo.

swap_horiz

Convert

Translate between languages. You name the source and target language pair; the run ends in a pull request.

auto_fix_high

Enhance

Describe a feature and have the team implement it against the existing code. Ends in a pull request.

policy

Audit

Analysis that cannot write. There is no commit, push or PR phase to re-enable — the pipeline simply doesn't contain one. Even the build and test phases are absent. You get a written report.

menu_book

Document

Tick what you want — user guide, manual, implementation details, API docs — and get a downloadable bundle that is exactly what you ticked. Nothing is committed to the repo being documented.

groups_2

A Team Per Mode

Every mode suggests its own roster — migration engineer, security reviewer, technical writer, API cartographer — and the editor can only offer a member the tools that mode actually grants.

compare_arrows

Re-Run, Then Compare

A re-run joins its parent's lineage. Put the whole line side by side — cost, tokens, duration, outcome — and pick the model and price you actually want. Adopt the winner as the project default and every later job that names no model inherits it.

rule

Admin-Curated Models

Admins curate the provider/model combos jobs may run on. Curation only ever narrows governance — every entry is re-checked against the org's model policy on each read, and a job naming anything off the list is refused at save time, not at run time.

how_to_reg

Checkpoints That Leave a Record

Where a human gates the run, the decision is written down — who released it and when — and it lands on the run receipt alongside every step the agents took.

Observability

See How AI Is Used.
Not What Was Said.

Every model call and every agent run emits a span. Leadership gets real adoption data — which teams use AI, which agents earn their keep, where the spend goes — while conversation content never enters the analytics tier at all.

visibility

What Leadership Sees

Cost and usage attribution sliced by module, model, user, agent, or the whole org. Token counts, latency, success and failure rates, and dollars — per team, per period.

lock

What Stays Private

Prompt and response text is never written to the analytics tier. Spans carry ids, timings, tokens, cost, and status. The audit record carries whitelisted summary fields. Neither stores what anyone typed.

school

What You Do With It

Find the teams AI hasn't reached yet and train them. Find the agents that get used daily and buy more of that. Target enablement with evidence instead of a survey.

payments

Cost Attribution Dashboard

Group spend by module, model, user, or agent over any period. Answers "where did the AI budget actually go" — and which investments are paying off.

account_tree

Trace Explorer

Walk any run span by span — every model call, every tool, every handoff between agents, with timing and cost at each step. When something misbehaves, you can see exactly where.

0
Prompts or responses stored in analytics — by design, in both tiers
730
Days of immutable audit retention — with a hard 180-day floor
5
Attribution dimensions — module, model, user, agent, org

Telemetry and compliance are separate tiers on purpose. The audit trail fails closed — nothing is served without a record. Operational traces fail open, so a telemetry hiccup never blocks real work. And when a PII policy is active, a scanner failure captures nothing at all — there is no raw fallback.

Questions

What Leadership Asks
Before Rolling Out AI

Can leadership see how AI is being used across the organization without reading employee conversations?

Yes. ContextuAI Enterprise separates operational telemetry from conversation content by design. The Observability module attributes cost and usage by module, model, user, agent, or organization, so leaders can see which teams use AI, which agents are used, and what it costs. Prompt and response text is never written to the analytics tier — spans carry only ids, timings, tokens, cost, and status, and audit records carry whitelisted summary fields.

What data does ContextuAI Enterprise store about AI usage?

Two separate tiers. Operational traces store span and trace records containing ids, timings, token counts, cost, and status, retained on a TTL of 90 days by default. The compliance audit trail stores whitelisted summary fields describing what was served and what was refused, retained 730 days by default with a hard 180-day floor. Neither tier stores prompt or response text.

How can executives use AI analytics to plan training and enablement?

Because usage and cost are attributed by team, user, agent, and model, leaders can identify which parts of the organization have not adopted AI yet and target training there, see which agents are used daily and invest in similar capabilities, and measure whether an enablement program actually changed usage — using observed data rather than surveys.

Is employee privacy protected in ContextuAI Enterprise analytics?

Yes. Conversation content never enters the analytics tier. In addition, when an organization has an active PII policy and PII scanning fails, nothing is captured at all — there is no raw fallback. The compliance audit trail fails closed so nothing is served without a record, while operational traces fail open so a telemetry issue never blocks real work.

Where does ContextuAI Enterprise run and who controls the data?

ContextuAI Enterprise is self-hosted. You deploy and operate it on your own infrastructure, and all data — including observability and audit data — stays in databases you control. ContextuAI has no access to your deployment or its contents.

Run Receipts

The Page You Forward
to Security

One governed timeline per run: what the agents did, which external systems they touched, which model ran each step, what it cost, where a human gated it, and how it ended. Export it as markdown and hand it over.

receipt_long

Four Kinds of Run

Workspace projects, crews, agentic workflows, and Code Studio jobs each get a receipt. It joins stores that already existed — spans, checkpoints, approvals, audit, artifacts — so it is one accounting, not a second one.

cleaning_services

Safe to Send Outside

The export exists to be forwarded, so every string on it is a disclosure decision. Failure text is credential-scrubbed, span attributes are a fixed allowlist, and tool arguments, tool results and prompt bodies never appear.

shield_lock

Scoped to the Reader

Admins see any run in their own org; everyone else is pinned to runs they started. Missing, cross-org, and not-yours all return the same 404 — the run-id space isn't probeable by watching status codes diverge.

Connector Certification

A Connector List
You Can Re-Verify

Instead of a connector count on a slide, every enterprise connector sits in an explicit tier, and a scripted, re-runnable harness produces a record an admin — or a customer's auditor — can read.

workspace_premium

A Tier, Not a Logo

Every connector sits in an explicit tier that records how it is really served — vendor-hosted with per-user OAuth, a native API connector, or this deployment's own data plane. No logo wall pretending they're all equivalent.

replay

Re-Runnable On Demand

A fixed harness runs the same checks against every connector — is the target actually registered, does auth resolve, did the activity produce audit events — and writes a record an admin can re-run the day before an audit.

no_accounts

Records Carry No Secrets

A certification record never contains an endpoint, a credential, or a token, and a check that fails is sanitized rather than leaking the underlying exception. It's designed to be forwarded.

Every check is always present in a record. One that doesn't apply reads skip — a first-class outcome, never a quietly omitted line. Which of your systems sit in which tier is a conversation we'd rather have with you directly than publish on a page.

Knowledge Base

Grounded Answers,
From Your Own Docs

Enterprise ships a self-hosted Knowledge Base with vector search (Qdrant) — upload your organization's documents and chat gets grounded, cited answers. A built-in Starter Assistant gallery gives every new org a running start instead of a blank page.

1

Pick a Starter Assistant

Browse a gallery of ready-made company assistants spanning HR, IT, Operations, Finance, Go-to-Market, and Engineering

2

Add It — Org-Wide or Just for You

Admins add a starter assistant for the whole team; any user can add one to their own workspace

3

Chat with Citations

Ask questions and get answers grounded in your uploaded documents, with sources cited

13
Ready-to-use knowledge templates in the Starter Assistant gallery
9
Come preloaded with a sample document — grounded, cited chat works on the very first click
badge

People & HR

Employee handbook, benefits, onboarding, time-off policy

support_agent

IT & Support

IT helpdesk, security & acceptable-use policy

settings

Operations

Standard operating procedures (SOPs)

account_balance

Finance & Legal

Expense & travel policy

campaign

Go-to-Market

Sales enablement

code

Engineering & Product

Team assistants for product and engineering documentation

The gallery also includes live-data connector cards for teams that want to ground chat in a live system instead of uploaded files.

Domains

Built Around
How Your Industry Works

A domain isn't a theme — it's your systems connected, your vocabulary understood, and the workflows your team actually runs, all under one governed record. We build deep in four.

account_balance

Banking

Core systems, operations, and supervision — with the workflows that cannot deliver anything until a named human releases them.

umbrella

Insurance

Claims, underwriting, and policy servicing — assembled from the systems of record you already run.

trending_up

Financial Services

Research, reporting, and supervision, where an assistant that states what it cannot source is worth more than one that improvises.

home_work

Single-Family Rentals

Leasing, maintenance, rent roll, and portfolio reporting across scattered-site doors — the operational reporting nobody has time to assemble by hand.

cable

Bound to Your Systems

Nothing arrives pre-wired to somewhere else. A bundle declares slots; you bind each one to your own database, API, knowledge base, or MCP server, inside your own network.

shield

Ask in Plain English, Safely

Question your own Postgres, MySQL, SQL Server, Snowflake, or MongoDB in plain language, over pooled async connections — with injection guards and column masking sitting between the model and your data.

bookmark_added

Then It Becomes Yours

Save any working project as an org-scoped template and your whole team starts from it — applied server-side, so it behaves the same from the API as it does in the browser.

Some of these arrive with a ready-made library and a seeded environment you can drive on the first call, rather than a slide deck. Ask us what's waiting in yours.

Governed Access

One Governed Door
to Every Model

Eight providers behind one dispatcher, one OpenAI-compatible endpoint in front of it, and an admin-editable matrix deciding who sees which screen. Nobody needs a raw provider key.

electrical_services

OpenAI-Compatible Gateway

Anything that speaks the OpenAI API — the official SDKs, Aider, Continue.dev, IDE plugins, a shell script — points at /v1 and works. Every call is authenticated with a scoped platform key, rate-limited per key, and recorded against org, key, and model.

hub

Eight Providers, One Path

AWS Bedrock, Anthropic, OpenAI, Google, Ollama, Vertex AI, Azure OpenAI, and any OpenAI-compatible endpoint — all dispatched through one chain on your org's own encrypted credentials. An unknown model is a clean 404, never a silent fallback to something else.

table_chart

Role → Screen Matrix

Which roles reach which screens is one org-scoped matrix an admin edits — not a hardcoded list in the code. It's enforced on the server before a page renders, and the navigation is filtered through the very same matrix, so the menu can't offer a door that won't open.

savings

Policies and Budgets

Model-access policies, spend budgets, and per-org rate limits are admin-set and checked at both save time and run time. Both fail closed.

podcasts

Audit Forwarding

Stream audit events to your SIEM over HMAC-signed webhook batches. Each sink keeps its own cursor with exponential backoff, and the signing secret is encrypted at rest and never handed back.

vpn_lock

Outbound Calls Are Guarded

Every URL that comes from a user, persona, or config — API tools, webhooks, MCP targets — goes through an always-on, DNS-pinned SSRF guard that refuses loopback, link-local, private-range, and cloud-metadata destinations.

Built for Every Industry

See how enterprise teams use ContextuAI to transform their workflows

account_balance

Financial Services

Connect trading databases, compliance systems, and risk models. Query portfolio performance, generate regulatory reports, and detect anomalies in real-time.

Snowflake PostgreSQL REST APIs
local_hospital

Healthcare & Life Sciences

Securely query patient databases, research repositories, and clinical trial data. AI personas enforce HIPAA compliance while delivering instant insights.

MySQL MSSQL Data Masking
rocket_launch

Technology & SaaS

Connect GitHub repos, manage issues and PRs through chat, migrate and document codebases with Code Studio, and orchestrate multi-agent pipelines. From sprint planning to deployment monitoring.

GitHub Code Studio Slack AWS
Enterprise

Need More Power?
Go Enterprise

Everything in Solo, plus managed deployment, team collaboration, SSO, compliance, and dedicated support.

Solo Free

For individuals and small projects

  • AI Chat with multi-model support
  • 96 business agents across 12 departments
  • 10 persona types (DB, MongoDB, MCP, REST API, web search, files, etc.)
  • Multi-agent crews (4 execution modes)
  • Local models via Ollama — bring your own, no API key needed
  • 3 platform connections (Telegram, Discord, LinkedIn)
  • BYOK — Anthropic, OpenAI, Google, AWS Bedrock
  • 100% local SQLite — your data stays on your machine
  • Apache 2.0 open source
Download Free

Enterprise Custom

For teams and organizations

  • Everything in Solo
  • Multi-user with an admin-editable role → screen matrix
  • SSO, MFA, SCIM 2.0
  • 14 connector types (59 built-in tools) + managed MCP registry
  • Code Studio — 5 job modes with run lineage
  • Scheduled automations & multi-agent crews
  • Control Center — live integration checks
  • Run receipts — one exportable timeline per run
  • Connector certification — an explicit tier per connector
  • PII detection, audit trail, SIEM forwarding
  • OpenAI-compatible gateway at /v1
  • Bundled local runtime — open models, no per-token bill
  • Domain depth for your industry
  • Agentic Event Bridge
  • Dedicated support & SLA

Ready to Scale Your
AI Operations?

Enterprise-grade security, compliance, and collaboration for your entire organization.

Download Solo Free