EzyAgents documentation

EzyAgents is a platform of AI agents that automate your business operations: support, sales, finance, HR, marketing and more. An orchestrator, the Pilot, plans the work and distributes it across ten specialized agents, each equipped with its own tools and connectors.

Every sensitive action goes through human oversight (HITL) that you configure, and your data is hosted and encrypted in Europe.

Deploy your first agent in under 10 minutes:

• Create an account (14-day free trial, no credit card required).
• Choose a business agent (Support, Sales, Finance, HR…).
• Connect your tools in one click (Gmail, Outlook, Slack, HubSpot…).
• Define your approval rules (HITL), then go live.

A workspace ready to use in 20 minutes

The path we recommend to a pilot team, in the order where each step makes the next one useful:

• Knowledge base → Add a document → Link: paste a Notion page, a Confluence space, a GitHub repo, a Drive, SharePoint, Box or Dropbox folder. The source is recognised and stays in sync.
• Connectors → Slack: the bot replies in a thread, asks for approvals and questions where the team already works.
• My agents → activate a business agent; its tools, connectors and guardrails are ready; the Conversation tab is a real sandbox.
• Pilot → a plain-language request ("chase this month's unpaid invoices, with validation before each send"): Pilot plans, delegates, and every sensitive action goes through Approvals.
• On your phone: add ezyagents.fr to your Home Screen, enable notifications in My account — you approve from your phone.
• Settings → General: workspace instructions (tone, signature, rules) apply to every agent; Billing: monthly budget and per-run cap.

EzyAgents runs on the latest Claude models from Anthropic. The Pilot automatically selects the right model for each task, balancing intelligence, speed and cost. For organizations that require inference in a European region, an AWS Bedrock EU option is available from the Pro plan (see below).

Automatic selection (Auto)

By default, Auto mode lets the Pilot pick the right model: a fast model for triage and simple replies, a reasoning model for analysis and complex planning. You can also pin a specific model per agent.

Routing can also be set per agent: a "fast" model for certain tools, a "powerful" model for reasoning tasks.

Choosing your AI provider (from the Pro plan)

From the Pro plan, you choose your agents' primary provider — Anthropic (Claude, recommended), OpenAI (ChatGPT), Mistral or AWS Bedrock (Claude, inference within the EEA) — from Settings → Models & AI, with no API key to provide: requests go through EzyAgents' managed infrastructure. Each provider gives access to several models, selectable per agent. You can also define a fallback order: if the primary provider goes down, your agents automatically switch to the next one in the chain.

Your models, your keys (BYOK, from the Pro plan)

From the Pro plan (outside the trial period), you can use your own providers and models by bringing your API keys — including the latest models from each vendor. Two modes are available:

• Self-hosted (from Pro): point EzyAgents to your own compatible gateway (LiteLLM, Azure OpenAI, Bedrock, Ollama…) with a URL and a key you control.
• Hosted by EzyAgents (Enterprise): simply enter your key (OpenAI, Mistral…); we store it in isolation in our proxy and route your requests to the chosen model (e.g. GPT-5.6 Sol, Mistral Large 3).

Supported providers: Anthropic (Claude), OpenAI, Mistral, AWS Bedrock, Azure OpenAI and Ollama. A fallback chain can be configured to switch providers automatically. With your own keys, token billing happens directly with your provider.

By default, with no particular configuration, EzyAgents runs on the latest Claude models via the Anthropic API. No data is used to train models. To keep inference within the EEA, select the AWS Bedrock EU provider (from the Pro plan, using our keys) or connect Bedrock in your own AWS account (BYOK).

Each plan includes a monthly volume of conversations. A "conversation" is a mission entrusted to an agent (a series of exchanges and actions until it is closed).

Some actions consume dedicated credits, notably sales enrichment (verified email + phone) from the Sales agent. These credits can be purchased in packs.

The Pilot is the conductor agent. You describe the outcome you expect; it builds a plan, asks the right questions, then delegates each step to the relevant business agent — up to 50 tasks in parallel.

At the end of each mission, it produces a summary and submits any remaining sensitive actions for your approval.

Each agent ships with its tools, connectors and guardrails:

• Customer Support — email triage, KB search, approved replies, escalation.
• Sales / SDR — LinkedIn + SIRENE prospecting, enrichment, multi-channel sequences.
• Finance — invoice follow-ups, reconciliation, monthly accounting report.
• HR — onboarding, employee Q&A, leave management and scheduled reminders.
• Marketing — brand content, email campaigns, competitive intelligence.
• Communications — LinkedIn/X/Instagram posts, AI visuals, campaign plans, approved cross-posting.
• Tech — sandbox debugging, code reviews, runbooks and incidents.
• Analyst — real Excel and PowerPoint files, data analysis, reporting.
• Legal — contract review, NDAs/T&Cs, GDPR register, deadlines.
• Procurement — supplier sourcing, quotes, IBAN anti-fraud, renewals.

By default, no critical action is executed without your approval. You define, action by action, what an agent can do autonomously and what requires explicit approval.

• Approval queue: approve, edit or reject each action.
• Tool Guard: per-agent access scope and per-domain restrictions.
• Timestamped, exportable audit log for every action.

Your documents, procedures and FAQs feed every agent reply. Search is semantic and every answer cites its sources (document and page), so it stays verifiable.

• Ingest PDF, DOCX, XLSX, CSV, TXT, Markdown, HTML — files or whole folders.
• Synced sources: Google Drive, SharePoint / OneDrive, Notion, Confluence, GitHub, Slack channels, Box, Dropbox — one link is enough, the source is recognised.
• Semantic search per workspace, isolated; scoped per agent if needed.
• Sourced, traceable answers (clickable [n]).

Agents act inside your existing tools: Gmail, Outlook, Slack, Teams, Zendesk, HubSpot, Salesforce, Resend. You can also plug in your own tools via the API, webhooks or an MCP server.

The full list is available on the Marketplace.

AES-256 encryption at rest and TLS 1.3 in transit, secrets isolated per organization, data partitioned per tenant. GDPR compliance, DPA on request, hosting and inference in the European Union.

Enterprise customers can deploy on-premise or in their own VPC. See the Security page for details.

Four plans, from testing to enterprise. 14-day free trial without a card, then Solo at €39/month, Pro at €99/month (billed annually) and Enterprise on quote. No commitment, cancel anytime. Prices exclude VAT.

Every plan includes fair-use AI usage: the consumption gauge is always visible in the dashboard, an alert is sent at 80%, and beyond the included usage agents pause until the next month. Customers who bring their own keys (self-hosted BYOK) are not affected: their consumption is billed directly by their provider.

In short: from Pro, you choose your AI provider and fallback chain without managing any API key, with optional EU-region inference (Bedrock, via our keys or your own AWS account) and self-hosted all-provider BYOK (your keys, your bill). Enterprise adds the hosted-by-EzyAgents BYOK mode (your key, zero infrastructure), per-agent model tuning, SSO/SAML and private deployment. See the next section.

The Enterprise plan lets you choose where the platform and model inference run, based on your sovereignty requirements. Four modes are available and can be combined (for example: on-premise + Bedrock in your VPC).

What ships for deployment

• 3-step on-premise install via Docker Compose (automated setup script: generated secrets, Postgres/Redis/API/Worker/Dashboard, TLS reverse proxy).
• Helm chart for Kubernetes, with ready-to-use profiles (on-premise and AWS Bedrock EU values).
• Terraform modules to provision AWS Bedrock in Europe (production example included).
• Anthropic-compatible LiteLLM proxy: every model request goes through a gateway you control — no data leaves your infrastructure.
• Copy-paste-ready OpenAI and Mistral BYOK integration templates.

In the app, the provider, key and gateway are configured from Settings → Private cloud (Enterprise plan only). Once the provider is configured, its models become selectable on every agent. Our team supports the rollout (DPA, architecture review, dedicated Customer Success).

Using the Anthropic, OpenAI or Mistral API directly gives you access to a model, not a business automation platform. EzyAgents adds orchestration, guardrails, connectors and deployment choice, while staying compatible with those same providers.

In short: EzyAgents does not replace the models — it puts them to work in your processes, with the sovereignty, security and business depth the enterprise demands, and the freedom to deploy wherever you decide.