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.
The platform depth is what separates Retool from the no code agent builder field. 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, which is rare in this category.
Deployment is the strongest in its lane. 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 honest limits are commercial rather than technical. 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 capitalised. Named production customers reported at Fortune 500 scale including Amazon, Brex and Coinbase. Funding rounds were not retrieved from first party sources in this pass.
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 specialised 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 CallingOver 100 native connectors including Postgres, MySQL, MongoDB, Snowflake, Salesforce, Stripe and REST or GraphQL; agents can be given any saved query or workflow as a tool plus purpose built agent tools, and can link MCP servers or other agents. Retool agents product page and integrations catalogue 2026-08-07 | Full |
|---|---|
| Workflow OrchestrationAgents are given a goal and decide which tools to use, in what order, and when work is complete; they delegate to sub agents and escalate. Built on a Temporal based workflow engine extended into agent orchestration, supporting event driven multi step tasks that loop until complete. Retool agents documentation and Temporal case study 2026-08-07 | Full |
| Knowledge Grounding & RAGAgents ground in customer systems through saved queries, resources and connected databases and APIs rather than a documented vector store or retrieval layer; no RAG or embedding product surface was retrieved in this pass. Retool agents documentation 2026-08-07 | Partial |
| Human Oversight & GuardrailsAgent specific tools are governed by the same platform rules enforcing role based access control and data level permissions, and any agent can be watched in real time step by step, but no approval gate or human confirmation step on individual agent actions was retrieved. Retool agents product page and enterprise page 2026-08-07 | Partial |
| Security, Identity & GovernanceSOC 2 Type 2 with reports downloadable from a self serve trust centre alongside SIG Lite, DPA and subprocessor disclosures; SAML and OIDC SSO, SCIM role mapping, role based access control with data level permissions, Secrets Manager with API rotation, encryption at rest and in transit, external penetration audits and continuous scanning; HIPAA available with a BAA on Enterprise. Retool security documentation and trust centre 2026-08-07 | Full |
| Observability & AuditabilityBuilt in audit logs tracking every user action, streamable to external SIEM tooling such as Splunk or Datadog, plus in depth usage analytics, agent cost monitoring, performance tracking and real time step by step observation of any running agent. Retool enterprise page and agents product page 2026-08-07 | Full |
| Memory & State PersistenceRetool documents memory as a core agent concept and describes agents retaining context across multiple steps rather than handling one exchange at a time, but no persistence model, memory store or cross session retention detail was retrieved. Retool agents and workflows resource collection 2026-08-07 | Partial |
| Deployment & Data ResidencyMulti tenant cloud on AWS, self hosted Docker inside a customer virtual private cloud, and a Retool managed self hosted option running in a customer owned AWS account; under self hosted Retool states no Retool systems store customer data and no Retool personnel have logical access, with only usage information shared. Retool security documentation and trust guide 2026-08-07 | Full |
| Prebuilt Agents, Templates & PacksAgents can be started from a template or built from scratch and reach production from a short prompt or a few clicks; an extensive template library and published customer agent patterns including support triage, chargeback disputes and logistics routing back it. Retool agents product page and use case library 2026-08-07 | Full |
| Triggers & Channel CoverageWorkflows trigger actions across connected tools on an event driven basis with scheduled runs demonstrated in first party tutorials, and agents are reachable from apps, workflows and external user portals. A full trigger and channel inventory was not retrieved, hence reduced confidence. Retool workflows and agents documentation 2026-08-07 | Full |
| Model Flexibility & RoutingChoice of multiple models to balance performance against cost with provider and model routing syntax, enterprise customers bringing their own LLM key, and a custom AI provider integration accepting any OpenAI compatible endpoint including self hosted or private model deployments with credentials held as encrypted resources. Retool agents and custom AI provider pages 2026-08-07 | Full |
| APIs, SDKs & MCP ExtensibilityAgents link MCP servers and other agents as tools; the platform extends with JavaScript, Python and SQL, exposes a public API, programmatic secrets rotation and custom components, and supports Git source control on higher tiers. Retool agents product page, enterprise page and documentation 2026-08-07 | Full |
| Testing, Debugging & OptimizationBuilt in evaluations are stated first party as a core capability for tuning agents, alongside cost monitoring, performance tracking and real time step by step inspection of agent execution for debugging. Rare in this category. Retool agents product page 2026-08-07 | Full |
| Browser & Computer UseAgents act through APIs, database queries, saved workflows and MCP servers; no browser control, page navigation or computer use capability is documented anywhere on the product surface. Retool agents documentation 2026-08-07 | Unable to verify |
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
Pricing
Free tier; Team from roughly 10 to 12 USD per builder per month, with agent time billed hourly on top
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
Plan structure, user classes and the hourly agent billing rule are stated on the Retool pricing page and billing documentation. Specific USD seat rates vary by region because the page geo prices, and the sources reporting exact figures are largely competitors selling against Retool.
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 unlimited apps, capped workflow runs and roughly 20 agent hours per month
Lowest paid plan
Team
Commercial notes
Annual billing is advertised at around 20 percent below monthly. Volume discounting is common above roughly 10 builders and multi year prepayment typically improves the rate, so list price is not the floor for larger deals.
Key ambiguities
Exact USD seat rates could not be pinned from first party retrieval. The Retool pricing page geo prices in EUR so USD figures vary by region, and third party sources report the builder seat at 10, 12 and 15 USD and the Business tier at both 50 billed annually and 65 month to month. Published hourly agent rates by model were not retrieved at all, which is the single biggest gap for cost modelling.
Missing data
First party USD seat rates by region and the published hourly agent rate card by model.
Related vendors
- Lindy — No-code AI agent builder focused on automating repetitive business…
- Activepieces — Open-source automation platform with a self-hosted Community Edition…
- Adopt AI — No code agent builder that turns existing applications and manual…
- Agent.ai — A marketplace and network of hundreds of prebuilt AI agents plus a…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code enterprise AI platform to build and run AI agents across the…
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.
- AutoGPT10.5 / 14A lighter documented profile than Retool
- Gumloop11.5 / 14Fuller documented coverage on Human Oversight & Guardrails
- Airtable11.0 / 14Fuller documented coverage on Knowledge Grounding & RAG
- OutSystems12.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Human Oversight & Guardrails
- Replit Agent11.0 / 14Fuller documented coverage on Memory & State Persistence
- SnapLogic12.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Human Oversight & Guardrails
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded