Retool
Also known as: Retool Agents, Retool Workflows, Retool AI
Internal tools platform extended into agent orchestration: agents pick their own tools, delegate to sub agents, link MCP servers, and inherit platform RBAC, with self hosting and built in evals.
Retool is an internal tools platform that has extended its low code builder and workflow engine into a full agent orchestration system. Retool Agents are configured with instructions, given tools, and left to decide which tools to call, in what order, and when the task is complete. They can delegate to sub agents and escalate, which makes them a multi agent system rather than a single assistant. Retool positions the distinction explicitly: AI workflows run LLMs inside a predefined process, while agents are given a goal and choose their own path.
Agents inherit the same governance the rest of the platform enforces, so agent specific tools are bound by existing role based access control and data level permissions rather than sitting outside them. Model choice is unusually open: multiple hosted models with routing, enterprise customers bringing their own LLM key, and a custom AI provider integration that accepts any OpenAI compatible endpoint including self hosted or private model deployments. Built in evaluations for tuning agent performance are a first class feature, and Retool Vectors gives agents a managed vector store over the customer's documents and web pages.
Deployment options are broad. Retool runs as multi tenant cloud on AWS, as a self hosted Docker image inside a customer virtual private cloud, or as a Retool managed self hosted instance running in a customer owned AWS account. Under the self hosted option Retool states that no Retool systems store customer data and no Retool personnel have logical access to it, with only usage information shared back.
The limits a buyer should weigh: no setting makes a person approve an agent's tool call before it runs, no memory kept across runs is documented, and only one agent template is named. Commercially, single sign on and several governance features sit behind higher tiers, and agents are billed by the hour separately from the AI credit pool, so agent cost scales with runtime rather than with seats.
Vendor details
Canonical URL
https://retool.com
Category
Agent builder
Subcategory
Agent orchestration on an internal tools platform
Funding status
Private and well capitalized. Named production customers reported at Fortune 500 scale including Amazon, Brex and Coinbase. Funding rounds are not stated on Retool's own pages.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Over 100 native connectors spanning Postgres, MySQL, MongoDB, Snowflake, Salesforce, Stripe and REST or GraphQL endpoints. Agents can be given any saved query or workflow as a tool, plus purpose built agent tools governed by the same platform permissions. Agents can link MCP servers or delegate to other agents. Extensible with JavaScript, Python and SQL, and a Secrets Manager with programmatic rotation via API.
In practice
A support team builds an agent that triages inbound tickets, delegates specialized questions to sub agents, and escalates only the cases it cannot close, with every step watchable in real time.
An operations team turns existing saved queries and APIs into governed agent tools so an agent can process chargeback disputes end to end without new integration work.
A regulated enterprise runs the whole platform self hosted inside its own AWS account so that no customer data reaches Retool systems while still using hosted or private models of its choice.
Sources & related URLs
Research sources
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool Calling | Full |
|---|---|
|
Agents act through core tools built by Retool (email, calendar, Google Docs and Slides, files, web search), custom tools, any saved query or workflow, other agents and connected MCP servers, over Retool's 100+ connectors. Sourcedocs.retool.com/agents/concepts/toolsread 2026-09-29 |
|
| Workflow Orchestration | Full |
|
Agents choose which tools to call and in what order, invoke other agents as tools and talk to external agents over A2A, and agentic workflows combine Retool Workflows with agent steps. Sourcedocs.retool.com/agents/concepts/agentic-workflowsread 2026-09-29 |
|
| Knowledge Grounding & RAG | Full |
|
Retool Vectors is a managed vector database for Retool AI: Retool extracts text from documents, splits it into chunks and computes embeddings with OpenAI's embeddings API, crawls URLs into new embeddings within published crawl limits (three concurrent crawls, 25 URLs, a 15 second timeout), and includes the most relevant content in the model request when a Vector is referenced in an AI action. Sourcedocs.retool.com Retool Vectors quickstartread 2026-09-30 |
|
| Human Oversight & Guardrails | Partial |
|
Agent tools run under Retool's role based access control and data level permissions, and anyone can watch an agent step by step as it works. The tools documentation describes timeouts and typing but no setting that makes a person approve a tool call before it runs. Sourcedocs.retool.com/agents/concepts/toolsread 2026-09-29 |
|
| Security, Identity & Governance | Full |
|
Retool documents role based access control through administrator permissions, enforced two factor authentication and detailed admin audit logs on Business and Enterprise, and names SOC 2 Type 2, with audit reports available through the Trust Center at trust.retool.com. Sourcedocs.retool.com/legal/securityread 2026-09-29 |
|
| Observability & Auditability | Full |
|
Each agent run shows token usage, estimated cost, total runtime and tool calls above a replay of the run with tool chips for each step, and any running agent can be watched step by step; admin audit logs sit on Business and Enterprise. Sourcedocs.retool.com/agents/guides/monitorread 2026-09-29 |
|
| Memory & State Persistence | Partial |
|
An agent keeps the context of its chat and run as it calls tools, which is state inside one session. The Agents documentation index (concepts, tools, triggers, evals, monitoring, reference) has no page on memory kept across runs, and the Agents FAQ says nothing on it. Sourcedocs.retool.com/agents/concepts/faqread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
Retool runs as multitenant cloud on AWS or as 'Self-hosted services in your VPC/VPN', and Agents are documented for both cloud and self hosted instances, including email triggers through Mailgun on self hosted. Sourcedocs.retool.com/legal/securityread 2026-09-29 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
Retool Agents 'offers several pre-defined templates' for specific use cases. Only one, the Competition Scanner, is named, so the set cannot be assessed, and the core tools are components, not agents. Sourcedocs.retool.com/agents/guides/create-agent-from-templateread 2026-09-29 |
|
| Triggers & Channel Coverage | Full |
|
Agents start from an email sent to their own unique agent address and from external agents over an A2A trigger, with no one at the buyer starting the run, beside chat and workflows that call them. Sourcedocs.retool.com/agents/guides/triggersread 2026-09-29 |
|
| Model Flexibility & Routing | Full |
|
Builders 'choose your favorite LLM' and 'Choose from multiple AI models to balance performance and cost', on Retool managed keys for certain providers or their own key with a model provider. Sourcedocs.retool.com/agents/concepts/faqread 2026-09-29 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Agents built in Retool are callable from outside over A2A, with an A2A trigger and a documented A2A endpoints reference, and the platform extends through custom tools, JavaScript, Python and SQL. Sourcedocs.retool.com/agents/reference/a2a-endpointsread 2026-09-29 |
|
| Testing, Debugging & Optimization | Full |
|
Evals test agents systematically: builders create datasets and test cases, run evals and compare runs side by side, and 'fine-tune with built-in evals'. Sourcedocs.retool.com/agents/guides/evalsread 2026-09-29 |
|
| Browser & Computer Use | Not documented |
|
Agents act through core tools, custom tools, queries, workflows, other agents and MCP servers; the web search core tool is a search, and no browser, desktop or computer control is documented. Sourcedocs.retool.com/agents/concepts/toolsread 2026-09-29 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented 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
Retool's app building agent can now use external MCP servers connected as resources, calling their tools while an app is being built or when it runs. People using a published app can only trigger the MCP tools they have permission for. It is live on cloud for all plans as a public beta.
Bears on: MCP / tool calling / API
View sourcePricing
Free tier; Team $10 per builder and $5 per internal user a month; Business $50 and $15; Enterprise custom; agent hours beyond the included 20 a month billed hourly by model
three user classes plus agent hours and AI credits
Included quota
Free includes up to 5 users, unlimited apps, a capped number of workflow runs per month, roughly 20 agent hours per month and a monthly AI prompting credit allowance per user. Paid tiers bundle larger AI credit allowances and agent hours by tier.
What is public
Every plan's seat prices for builders and internal users, external user tiers, workflow run and AI credit allowances, and the 20 included agent hours; the hourly agent rate by model is not stated on the page.
Billing mechanics
Users are classified for billing each cycle by activity. Builders create or edit apps, workflows and agents and carry the highest rate. Internal users only view and use published apps and are billed at a reduced rate, and Business plan admins can use permission groups to hold users at that lower rate. External users are volume tiered and only available on Business and Enterprise. Agents bill hourly and separately from the AI credit pool. Team and self serve Business pay by credit card; ACH and wire are available only to contracted Business and Enterprise customers.
Cost watchouts
Agent hours are the real exposure. Free agent hours are capped at roughly 20 per month and agent execution PAUSES once they are exhausted, so an agent workload can stop rather than degrade. Paid agent rates vary by model capability, so switching an agent to a stronger model changes the run rate. Workflow run overages are billed in blocks on Team and Business. Single sign on and several governance features sit behind higher tiers, which can force a jump to custom Enterprise pricing the moment a security review requires SSO. Self hosting shifts cost into infrastructure, upgrades and maintenance time.
Variable cost rationale
Three separate variable axes stack on top of the seat line: hourly agent runtime at model dependent rates, AI prompting credits, and workflow run overages. Agent billing by the hour means cost scales with how long autonomous work takes, which is the hardest quantity to forecast before deployment and is not bounded by headcount. The free tier pausing execution when agent hours run out is evidence that Retool treats agent time as a metered resource rather than a bundled feature.
Additional watchouts
Do not model Retool agent cost from seat count. Agent spend is a function of how long agents run and which model they run on, and it is ring fenced from the AI credit pool.
Overage / add-ons
Workflow runs beyond the included allowance are billed in blocks on Team and Business. Agent hours beyond the included allowance are billed hourly at model dependent rates; on the free tier agent execution pauses instead of billing.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan for up to 5 users with 500 workflow runs, 250 AI credits and 20 agent hours a month
Lowest paid plan
Team, $10 per builder and $5 per internal user a month
Commercial notes
Annual billing is advertised at around 20 percent below monthly. Inference, not stated by the vendor: volume discounts above roughly 10 builders and multi year prepayment may improve the rate, so list price may not be the floor for larger deals.
Key ambiguities
The hourly agent rate varies by model and is not stated on the pricing page, so agent cost at volume depends on model choice and runtime. Seat prices come from Retool's own pricing page, which may geo price by region.
Missing data
First party USD seat rates by region and the published hourly agent rate card by model.
Related vendors
- Lindy — AI teammate that lives in Slack, answers from your tools and…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No-code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
- Airia — Enterprise platform that unifies agent orchestration, security, and…
Alternatives to Retool
The closest documented capability profiles to Retool among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Moveo.AI12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- SnapLogic12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Vellum11.0 / 14A lighter documented profile than Retool
- Activepieces11.5 / 14Fuller documented coverage on Human Oversight & Guardrails
- OutSystems12.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Prebuilt Agents, Templates & Packs
- AgentX12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Prebuilt Agents, Templates & Packs
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded