How much does Jet Admin cost?

Free plan with limited AI credits and unlimited apps, users and workflows. Pro is $20 a month or $16 billed yearly, adding custom domain, GitHub sync, environments, version control and API access. Business is $100 or $80 yearly with granular permissions, SSO and audit logs. Enterprise is custom with on premise deployment, self hosted AI models, credit rollover and top ups. Plans are priced by the AI credits each needs, with no per user or per app fees.

Can Jet Admin be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Jet Admin publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: Customers can deploy on Jet Cloud, in their own cloud account or fully on premise, with self hosted AI models on Enterprise. Region selection on Jet Cloud is not documented. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can you bring your own model or route between providers with Jet Admin?

Full under the Agentic Index verification standard. Jet Admin publishes public evidence of bring your own model and bring your own key (BYOK), and of routing tasks between models or providers rather than being locked to one. Evidence basis: Customers choose the model. The plan comparison lists "Choose your AI model", the agent page promises every model out of the box with no vendor lock in, OpenAI, Anthropic, Google Gemini and Groq are connectable, and Enterprise can run self. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Jet Admin support MCP and tool calling?

Partial under the Agentic Index verification standard. Jet Admin publishes some public evidence of tool calling and API or SDK extensibility, but narrower than full Model Context Protocol (MCP) support as defined by the Agentic Index taxonomy. Evidence basis: Thin interface evidence: the Pro plan lists API access and two way GitHub sync, workflows can be started by API calls, and the open source Jet Bridge connects databases. No reference covering the vendor's own agents or platform objects is d. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Jet Admin

Q: Who is Jet Admin for?

operations teams, SMB, mid-market, agencies, data teams

Also known as: Jet Admin, JetAdmin, Jet, jetadmin.io, Jet Admin AI Agent Builder

Visit site

Agent builderindependentVerified 2026-10-02

Entry price$20/mo ($16 yearly), Pro · free planFull pricing detail

No code app platform whose AI Agent Builder runs tool using agents over 200+ data sources and apps, inside workflows, app chat or Slack, Teams and email, with a template gallery, model choice and on premise deployment.

Jet Admin is a no code platform for admin panels, portals and internal tools that added an AI Agent Builder alongside its app generator. An agent is defined by instructions and a set of tools drawn from the customer's data sources and integrations, and it decides each next step itself rather than following a fixed script. When a task needs structured execution, the agent can call a workflow, and a workflow can in turn contain an agent as a trigger or a step.

Agents live in three places: as a chat component inside an app, as a step in a workflow that starts on a button click, an API call, a schedule or a webhook, or in the Agents section of the workspace. Teams can also reach them in Slack, Teams or email by tagging @Jet. A gallery of ready made agent templates covers meeting prep, standups, support triage, lead enrichment, Snowflake and BigQuery analysis, CRM pipeline reports, inbox management and recruiting, each listing the tools it uses.

Governance comes from the app platform: row and column level permissions, SSO and audit logs on the Business plan, and deployment on Jet Cloud, in the customer's own cloud account or fully on premise. Customers choose the AI model, and Enterprise can run self hosted models.

Confirmation before risky actions is handled in the agent's instructions rather than by a dedicated approval step, and the testing guidance is a manual checklist: run safe tasks, inspect tool calls and parameters, keep write tools scoped to test records, then revise and repeat.

Vendor details

Canonical URL

https://www.jetadmin.io

Subcategory

AI agent builder on an internal tools platform

Funding status

Private and backed by Y Combinator. Round sizes are not established from first party sources.

Company status

independent

Use cases & customers

Primary use cases

tool using agents over databases and business appsagents embedded in internal apps as chat componentsagents as steps inside scheduled or webhook workflowsSlack, Teams and email assistants tagged with @Jetdata analysis agents over Snowflake, BigQuery and Postgres

Target customers

operations teamsSMBmid-marketagenciesdata teams

Deployment options

Jet Cloudcustomer's own cloud accounton premise (Enterprise)self hosted AI models (Enterprise)

Integrations

Agents use data sources and integrations as tools: Postgres, MySQL, MongoDB, Snowflake, BigQuery, Supabase, Airtable, Google Sheets, Salesforce, HubSpot, Zendesk, Stripe, Gmail, Outlook, Slack, Jira, GitHub, Google Calendar, Firecrawl, Tavily and 200+ more, plus MCP servers and REST or GraphQL APIs. Models from OpenAI, Anthropic, Google Gemini and Groq are available, and Slack, Teams and email reach agents by tagging @Jet.

In practice

An operations team builds a data manager agent over Supabase that retrieves, creates and updates records from a chat component inside their admin app.

A sales team installs the CRM Pipeline Reporter template so a scheduled workflow produces a weekly Salesforce pipeline summary.

A support lead tags @Jet in Slack to have an agent pull account info, open tickets and recent activity for a customer.

Sources & related URLs

Related / legacy domains

https://docs.jetadmin.io https://www.jetadmin.io/agent-templates https://github.com/jet-admin/jet-bridge

Research sources

https://www.jetadmin.io/build-custom-ai https://www.jetadmin.io/use-cases/ai-agents-automation https://docs.jetadmin.io/ai-agents/overview/agents.md https://docs.jetadmin.io/ai-agents/test-an-agent-safely.md https://www.jetadmin.io/pricing-copy

Agentic Index coverage score

9.5 / 14 capabilities · 68%

Integrations & Tool Calling	Full
Agents take authenticated action through tools the builder connects: data sources (Airtable, Supabase, internal tables), integrations and external APIs, plus workflows. The vendor lists 200+ sources including Salesforce, HubSpot, Gmail, Slack, Stripe and MCP servers, and says agents act through governed connections. Sourcedocs.jetadmin.io/ai-agents/overview/agents.mdread 2026-10-02
Workflow Orchestration	Full
Agents and workflows compose both ways. An agent can be created inside a workflow as a trigger or step, and agents can call workflows when structured execution is needed. The workflow builder offers branching, switch, if/else and iterator steps across APIs, databases and CRMs. Multi agent coordination is not documented. Sourcedocs.jetadmin.io/ai-agents/overview/agents.mdread 2026-10-02
Knowledge Grounding & RAG	Partial
Grounding comes through live tools rather than a maintained retrieval layer. Agents query connected databases, APIs and CRMs, and the Internal Knowledge Agent template searches company docs and wikis through an MCP server with citations. No vendor maintained knowledge base, index or embeddings store for agents is documented. Sourcejetadmin.io/build-custom-airead 2026-10-02
Human Oversight & Guardrails	Partial
Oversight runs through instructions and scoping rather than a vendor shipped approval gate. The docs' example agent is told to delete records only after explicit user approval and to confirm before changes, the testing guide says to keep write tools disabled or scoped to test records, and the marketing page says builders scope permissions and review every action. No pause and approve step before an action commits is documented. Sourcedocs.jetadmin.io/ai-agents/overview/agents.mdread 2026-10-02
Security, Identity & Governance	Partial
The access half is documented: row and column level permissions, SSO and audit logs (Business plan), with granular permissions on agents' connections. The compliance half is missing. No SOC 2, ISO 27001 or comparable attestation is documented, and the site says only that it is designed to meet complex compliance requirements. Sourcejetadmin.io/use-cases/ai-agents-automationread 2026-10-02
Observability & Auditability	Partial
Agent work is only partly recorded. Builders can inspect which tools an agent uses, the parameters it sends and the data it reads, and audit logs record user activity on Business. The testing guide points to audit logs and run history only when available, so a retained per run trace of agent actions is not established. Sourcedocs.jetadmin.io/ai-agents/test-an-agent-safely.mdread 2026-10-02
Memory & State Persistence	Partial
Memory is conversation context only. The docs say agents use instructions and past input to guide behavior, and no memory layer with a stated scope and lifetime across runs is documented. Sourcedocs.jetadmin.io/ai-agents/overview/agents.mdread 2026-10-02
Deployment & Data Residency	Full
Customers can deploy on Jet Cloud, in their own cloud account or fully on premise, with self hosted AI models on Enterprise. Region selection on Jet Cloud is not documented. Sourcejetadmin.io/use-cases/ai-agents-automationread 2026-10-02
Prebuilt Agents, Templates & Packs	Full
A gallery of roughly forty customer adoptable agent templates, each with its own page and listed tools, includes Meeting Prep, Daily Standup, Customer Support, Lead Enrichment, Snowflake and BigQuery Data Analyst, CRM Pipeline Reporter, Inbox Manager, Recruiting Sourcer and PostgreSQL Query Agent. The docs add an Agent templates section. Sourcejetadmin.io/build-custom-airead 2026-10-02
Triggers & Channel Coverage	Full
Agents wake on their own and reach several surfaces. Agents placed in workflows start on button clicks, API calls, scheduled jobs (every minute, hour, day or week) and webhooks. Users reach agents through an in app chat component and by tagging @Jet in Slack, Teams or email. Sourcejetadmin.io/build-custom-airead 2026-10-02
Model Flexibility & Routing	Full
Customers choose the model. The plan comparison lists "Choose your AI model", the agent page promises every model out of the box with no vendor lock in, OpenAI, Anthropic, Google Gemini and Groq are connectable, and Enterprise can run self hosted AI models. Sourcejetadmin.io/pricing-copyread 2026-10-02
APIs, SDKs & MCP Extensibility	Partial
Thin interface evidence: the Pro plan lists API access and two way GitHub sync, workflows can be started by API calls, and the open source Jet Bridge connects databases. No reference covering the vendor's own agents or platform objects is documented, and MCP appears as a connection agents consume rather than a server the vendor exposes. Sourcejetadmin.io/pricing-copyread 2026-10-02
Testing, Debugging & Optimization	Partial
Testing is a manual method, not a harness. The guide says to run a normal request, then missing context, irrelevant and out of scope requests, inspect tool calls and parameters, record prompt, outcome and tool calls, and repeat after revising. Workflows have a native debugger. No stored, scored test cases or regression runs are documented. Sourcedocs.jetadmin.io/ai-agents/test-an-agent-safely.mdread 2026-10-02
Browser & Computer Use	Unable to verify
No browser, desktop or remote computer control by agents is documented. The nearest thing is Firecrawl and Tavily, available as tools for crawling and web search, which fetch pages rather than operate an interface. Sourcejetadmin.io/build-custom-airead 2026-10-02

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-09-29·Agent capabilityVerified

When asked to build an app on an existing database or API, Jet Admin's AI App Builder now asks for access, inspects the real data structure and proposes a plan first. The user reviews and confirms that plan before anything is generated.

Bears on: Human approval / guardrails

View source

View all 1 change for Jet Admin →Tracked since Sep 2026 · Verified from public vendor sources

Pricing

$20/mo ($16 yearly), Pro · free plan

flat plan tier sized by included AI credits; no per user or per app fees

Free tierTrial available

Included quota

Credit allowances per plan are not stated; Free includes limited credits to build an app. All plans include unlimited apps, users and workflows.

What is public

Plan names, monthly and yearly prices, feature lists and a feature comparison table are published. Credit quantities and Enterprise pricing are not.

Billing mechanics

Flat monthly or yearly plan fee (20 percent off yearly), with AI credits included per plan rather than per user.

Cost watchouts

The page prices plans by the AI credits each needs but does not state how many credits a plan includes or what a credit buys. Credit rollover and on demand top ups are Enterprise features, so lower plans may hit a hard monthly ceiling. SSO and audit logs require Business.

Variable cost rationale

Plan fees are fixed and unlimited users remove seat growth, but agent work draws an unstated credit allowance and top ups exist only on Enterprise.

Additional watchouts

Seat cost is not the constraint here; agent usage is, and the credit allowance is the number to ask for.

Overage / add-ons

On demand credit top ups and rollover are listed for Enterprise only; no overage rule is published for Free, Pro or Business.

Sales call required

Mixed (some tiers require a call)

Free / trial

Free plan with limited AI credits, unlimited apps, users and workflows

Lowest paid plan

Pro at $20 a month ($16 billed yearly)

Commercial notes

Self serve on Free, Pro and Business; Enterprise through sales with an uptime SLA and a dedicated success manager.

Key ambiguities

Credit quantities per plan are unpublished.

Missing data

Credits included per plan, credit unit cost, and the Enterprise floor.

Agentic Index verified 2026-10-02

Official pricing page

Data confidence: medium