Back to vendors
S

Serval

Visit site
Entry priceNo public pricing. Serval quotes one platform fee through a demo.Full pricing detail

AI native IT service management platform that deploys a workforce of AI agents to resolve help desk requests, provision access, and run operational workflows.

Serval is an AI native IT service management platform. The company was founded in 2024 in San Francisco by Jake Stauch and Alex McLeod, both previously at Verkada. It is built to be the system of record for IT. Ticketing, access management, asset management and workflow automation sit in a single platform, with AI agents running on top of them.

Three agents do the work. A Help Desk Agent takes requests in Slack, Teams, email, by phone or through a portal and resolves what it can. An Automation Agent turns a plain language description of a process into a TypeScript workflow. An Insights Agent watches ticket patterns and proposes new automations. The workflows they run are deterministic and versioned, managed as code in Git with diffs, and shipped as installable bundles for common estates such as Okta, LDAP and Google Workspace.

The agents provision and revoke access, grant just in time permissions that expire on their own, onboard and offboard employees, act on managed devices, and answer from a knowledge base that syncs both ways with Notion, Confluence and the customer's existing ticketing system. The connector estate runs to 164 integrations, and Serval works bidirectionally with ServiceNow, Jira and Zendesk so a team can migrate in stages.

Workflows pause for approval, approvals can be delegated or overridden by a manager, access grants are recorded with the approver and the justification attached, and every workflow run is logged with its inputs, outputs, status and duration and exported as CSV or JSON for auditors. Role based access, SAML single sign on, SCIM provisioning and scoped API keys control who can do what, and the help desk agent is deliberately walled off from editing workflows or integration scopes. Serval holds SOC 2 Type II and offers a BAA for HIPAA workloads.

It can run as a managed cloud service, as a hybrid where only a worker sits inside the customer's network holding the integration credentials, or fully self hosted and single tenant in the customer's own AWS account or Kubernetes cluster, in which case the customer supplies the AWS account and the AI provider keys. Organizations can opt in to EU data residency. The platform is sold through a demo, and teams beyond IT run their own isolated environments on it.

Vendor details

Canonical URL

https://www.serval.com

Category

Enterprise operations agent

Subcategory

IT service management — help desk, access management and workflow automation

Funding status

Independent, headquartered in San Francisco, founded in 2024 by Jake Stauch and Alex McLeod, both formerly of Verkada. Raised a forty seven million dollar Series A in 2025 led by Redpoint Ventures with First Round, General Catalyst, Box Group, and Bessemer participating, then a seventy five million dollar Series B led by Sequoia in December 2025 at a one billion dollar valuation, with Meritech, First Round, General Catalyst, Evantic, Sound Ventures, and Radical Ventures also joining, for one hundred twenty seven million dollars raised in total. Reports five hundred percent revenue growth since its Series A, with customers including Perplexity, Together AI, Clay, Mercor, BILT, and Verkada.

Company status

independent

Use cases & customers

Primary use cases

help desk automationjust in time access provisioningemployee onboarding and offboardingAI native ITSM and workflow automation

Target customers

mid-marketenterprise

Deployment options

Serval Cloud — fully managed, 99.9% uptime SLAHybrid Self-Hosted — only the Serval worker runs in the customer's network, holding integration credentialsManaged in Your AWS — full application single-tenant in the customer's own AWS account, operated by the customer or by ServalSelf-Managed on Your Kubernetes — Terraform and Helm bundle on the customer's clusterEU data residency available as an opt-in; Microsoft GCC High supported

Integrations

Serval's catalog covers 164 connectors. Ticketing runs bidirectionally with ServiceNow, Jira, Zendesk and Freshservice so a customer can migrate gradually. Identity covers Okta, Microsoft Entra, LDAP and Active Directory, with SailPoint for governance and RSA SecurID for multi factor flows. Endpoints cover Jamf and Tanium, and HR covers Workday. Knowledge syncs bidirectionally with Notion, Confluence, Slab, Google Drive and the ticketing systems, so approved corrections publish back out. Collaboration covers Slack, Microsoft Teams and Google Workspace, and the estate extends to Salesforce, Coupa, LaunchDarkly, Vanta and Presidio. Connectors store credentials encrypted and attach them to every call made on the customer's behalf, on demand when a workflow runs, with no background sync. Provisioning and deprovisioning run via SCIM, direct API or custom workflows, with just in time grants revoked automatically when the window closes. Outside callers reach Serval through an API reference of 252 pages with two published OpenAPI specifications, scoped API keys, an approvals API, a CLI and an MCP server.

In practice

Your IT team drowns in repetitive tickets like password resets, access requests, and new hire setup. Serval's AI agents finish password resets, access grants and onboarding steps in the same conversation, and customers such as Perplexity report more than half of incoming requests handled automatically.

Building automations in a legacy ITSM tool means wrestling with drag and drop builders no one enjoys. In Serval you describe the workflow in natural language and the agent assembles the access flows, approvals, and provisioning for you.

You want AI automation but security and audit cannot be an afterthought. Serval provisions just in time access, keeps auditor friendly logs with SIEM integration, and can run cloud, hybrid, or fully self hosted to fit your controls.

Agentic Index coverage score

11.0 / 14 capabilities · 79%

Integrations & Tool Calling Full

The integration catalog runs to 164 documentation pages, indexed at docs.serval.com/llms.txt, with a page per connector. Ticketing covers ServiceNow, Jira, Zendesk and Freshservice, bidirectionally, so a customer can keep existing tooling during migration. Identity covers Okta, Microsoft Entra, LDAP and Active Directory, plus SailPoint for governance and RSA SecurID for MFA. Endpoints run through Jamf and Tanium and HR through Workday.

Knowledge comes from Notion, Confluence, Google Drive and Slab, collaboration from Slack, Microsoft Teams and Google Workspace, and finance and operations connectors include Coupa, Salesforce, LaunchDarkly, Vanta and Presidio. Connectors take authenticated action rather than mirroring data.

For RSA SecurID, Serval stores the client key encrypted and attaches it automatically to every call it makes on the customer's behalf, and workflows drive a full MFA flow, starting, verifying, checking and canceling attempts on demand. For Presidio, Serval exchanges credentials for a short lived JWT and reads asset records on the customer's behalf whenever a Serval workflow runs, with the regional endpoint chosen by the workflow.

Both happen at execution rather than by background sync. Provisioning is the heaviest write path, with automated provisioning and deprovisioning via SCIM, direct API or custom workflows, and just in time access grants revoked automatically when the window ends. Access can also be revoked via API. Serval's AI knows the endpoint catalog and can help build workflows against it. Connector maturity is labeled, with RSA marked Beta in the integrations UI.

Sourcedocs.serval.com RSA SecurID and Presidio integration pages, with the integrations indexread 2026-09-12

Workflow Orchestration Full

A workflow can call another as a step through child workflow composition, workflow journeys can be viewed as dependency graphs, and workflows can be organized into folders, shared across teams, tagged, searched semantically and versioned with diffs. Temporal is listed among the required datastores as the workflow orchestration component. It is a durable execution engine, so a run survives process restarts and resumes, which holds long running, multi step work together when people interrupt it.

Workflows can pause for approval, and Serval also has conditional forms in Slack, criteria based assignment rules, a default triage team for ambiguous requests and ITIL aligned change management. The Automation Agent turns natural language descriptions into TypeScript, so automations build themselves from a description. Serval markets deterministic workflows rather than execution the model improvises, since the model writes the workflow and the workflow then runs the same way every time. Workflows and skills are managed as code in Git with version diffs.

The participants include the employee raising a request, three named agents with different jobs, approvers who can be delegated to or overridden by a team manager, assignment groups and external ticket subscribers. Work spans ticketing, just in time access, asset management, onboarding and offboarding, compliance workflows and campaigns, with Security, IT, HR, Finance and Operations each able to run isolated environments on the same platform.

Sourcedocs.serval.com release notes index and self-hosting prerequisitesread 2026-09-12

Knowledge Grounding & RAG Full

A native knowledge base, in beta, sits alongside the synced stores and is maintained in Serval, with knowledge base management, knowledge tagging within guidance, lexical and keyword search alongside semantic retrieval, cross team KB sharing, and a tag catalog with owners set for teams, resources and roles. Answers ground in help docs built in Serval or synced from Notion, Google Drive, Confluence and Slab, and reviewers can publish approved knowledge updates into Notion, Slab, Confluence, Freshservice and ServiceNow, so corrections flow back out to the systems of record.

Retrieval respects permissions at read time through knowledge source permission enforcement, so an employee cannot be answered from a document they are not entitled to see. The Help Desk Agent can also search the web, tickets, assets and access history are queryable alongside, and the Insights Agent analyzes ticket patterns. Serval's asset estate tracks hardware, software licenses, SaaS subscriptions and cloud costs in one schema the agent reasons over.

Sourcedocs.serval.com release notes indexread 2026-09-12

Human Oversight & Guardrails Full

Workflows can pause for approval, so execution halts mid flow and waits for a person, and customers author these gates in a redesigned approval flow builder. Around them sit custom approval workflows, natural language workflow approvals, approval delegation, team managers able to override approvals from a ticket, and an approvals API for custom follow up logic. Multi step approvals apply to workflows and access requests alike.

Access requests route through approval before a grant is made, just in time access is time bound and revoked automatically when the window ends, and the access history export records the approver and the justification against every grant. Where approval is not requested, guardrails apply. Serval markets deterministic workflows with security layers, namely RBAC, approval gates, API scope limits and an air gap between help desk and builder.

That air gap means the agent that talks to employees cannot edit workflows or integration scopes, so a compromised conversation cannot widen the agent's own authority. Skills and runbooks hold agent behavior to the team's written procedures, with a diff view for reviewing changes the AI suggests before they take effect.

Sourcedocs.serval.com release notes index and serval.com/insights buyer's guideread 2026-09-12

Security, Identity & Governance Full

Serval holds SOC 2 Type II, states adherence to HIPAA and GDPR, and documents HIPAA-oriented deployment and data controls. It points customers to its Trust Center for the current Type II attestation report, and a written BAA covers HIPAA workloads and a DPA covers GDPR. Access management is centralized, with SAML and SCIM for SSO and user provisioning, role based access control for least privilege permissions, customizable API scopes for app integrations, and multi step approvals for workflows and access requests.

Further controls include custom roles, scoped API keys, knowledge source permission enforcement, ticket visibility groups for access controlled routing, a read only agent role, default access profiles and app owners, skills gated by access profile, and sharable access reviews. Separation of duties takes the form of an air gap between help desk and builder, so the help desk agent that talks to employees cannot edit workflows or integration scopes or change what agents are allowed to do.

Sourceserval.com/updates/soc2, /insights/hipaa-compliant-itsm and the serval.com platform pageread 2026-09-12

Observability & Auditability Full

Every workflow run is logged step by step with inputs, outputs, status and duration. Serval offers a sample workflow run export with per-step detail and timestamps and an access history export with approver, justification, start/end and revocation reason, and its governance guidance tells customers to confirm that logs include per-step inputs and outputs, precise timestamps and CSV/JSON export for GRC integration.

An access record carrying the approver and the justification is an audit trail of a consequential agent action with the human decision attached. SIEM integration carries it into the customer's security estate, so evidence is generated when work happens rather than reconstructed before an audit.

Alongside sit agent powered run debugging, version diffs for workflows and skills, a guidance diff view for reviewing AI suggestions, automation suggestion history and workflow journeys viewable as dependency graphs, so a reader can see what ran, what changed and what the agent proposed.

Dashboards on request volume, time to resolution and SLA compliance measure the help desk operation, AI resolution rates show what the agent itself did, and the Insights Agent reports on ticket patterns and automation opportunities. Analytics dashboards are in public beta, with a refreshed home.

Sourceserval.com/insights SOC 2 governance page, with docs.serval.com release notesread 2026-09-12

Memory & State Persistence Not documented

Per team guidance, knowledge sources and configuration persist in Serval, but none of these is a memory that learns per user over time, and no agent memory is described. Guidance, now called Skills, is a set of written procedures and runbooks the customer authors so agents follow internal practice, with a diff view for suggested changes and version history. It persists because a person wrote it down, not because the agent retained anything.

The native knowledge base and the corpora synced from Notion, Confluence, Google Drive and Slab are the knowledge layer, and workflows, skills and settings managed as code in Git are authored artifacts. The runtime stack uses PostgreSQL as the primary application database, Redis for caching and ephemeral state, and Temporal for workflow orchestration.

Temporal keeps a workflow run alive through restarts, but that is state within one execution, and no component in the stack holds what an agent learned. There is no named memory layer, no retained preference the agents reapply for a user or requester, no decision trace carried between tickets, no stated scope or lifetime for anything held, and no customer surface to inspect, edit, export or purge agent state apart from tickets, skills and knowledge. Ticket history is a record of work.

Sourcedocs.serval.com self-hosting prerequisites and release notes indexread 2026-09-12

Deployment & Data Residency Full

Serval comes in four delivery models. Fully managed Serval Cloud has no infrastructure to manage, automatic updates and a 99.9% uptime SLA. In Hybrid Self-Hosted, the customer runs only the Serval worker inside its own infrastructure while Serval operates the backend, control plane, web app and database, so the worker is the only Serval component that ever touches the internal network or handles integration credentials.

Fully self hosted comes in two operating modes, Managed in Your AWS and Self-Managed on Your Kubernetes. It is single tenant in an AWS account the customer owns, the application runtime and all customer data remain in that account, and the customer's AWS credentials never leave its environment. Either the customer's team or Serval operates it, and the deployment is identical either way.

The deployment bundle holds Terraform, Kubernetes and Helm configuration and setup scripts, and the AWS stack is EKS, Aurora PostgreSQL, ElastiCache, OpenSearch, S3 and Secrets Manager. Customers can point at their own PostgreSQL, Redis, Temporal, OpenSearch or S3 compatible storage, with the upgrade cost of doing so spelled out, and DNS requirements go down to the app and API hostnames.

Private network patterns include Site-to-Site VPN, Direct Connect, Transit Gateway and private DNS resolution. The cloud product also offers a region choice, with EU data residency available to organizations, and Microsoft GCC High is supported for US government workloads. Installation and day two operations sit in a password protected area shared with customers and evaluators, while everything needed to evaluate the models is public.

Sourcedocs.serval.com self-hosting section and release notesread 2026-09-12

Prebuilt Agents, Templates & Packs Full

Three named agents ship, each doing a different job. The Help Desk Agent handles intake and resolution across Slack, Teams, email, phone and portal, the Automation Agent turns natural language descriptions into TypeScript, and the Insights Agent detects patterns and suggests automations. Without the Insights Agent the help desk still resolves tickets, and without the Automation Agent the other two still work.

A browsable catalog of installable workflow bundles sits alongside them, with packs for specific estates such as LDAP/AD, Okta and Google Workspace, plus workflow backed catalog items and service catalog ingestion. An installable Okta workflow does work when selected, and removing it leaves the others whole. Workflows can be organized into folders, shared across teams, searched semantically and tagged. A native knowledge base and Skills add reusable content, though the customer writes those. The catalog comes from Serval, with no third party or community contribution path and no marketplace of externally built agents.

Sourceserval.com/insights buyer's guide, first party about Serval, with docs.serval.com release notesread 2026-09-12

Triggers & Channel Coverage Full

Workflows can be triggered by events and by webhooks, which let any external system act as an event source, as well as by Slack reactions, SLAs and ticket assignment, and campaigns can be triggered directly from a workflow. Child workflow composition lets one flow start another, and tickets, access requests and onboarding events all start work. Schedules are a separate mechanism, covering recurring campaigns, assignment schedules, SLAs with business hours and pause conditions, and automatic ticket bumps for unresponsive requesters, a time based trigger acting without a person.

The Help Desk Agent covers intake and resolution across Slack, Teams, email, phone and portal. Further channels include an embedded widget with a live agent and multiple email intake addresses per team, along with Microsoft Teams notifications and reply routing improvements, conditional forms in Slack, dynamically rendered forms, a Serval Inbox consolidating notifications, and white label Slack bot customization. The UI ships in nine languages with on demand ticket translation.

Sourcedocs.serval.com release notes index and serval.com/insights buyer's guideread 2026-09-12

Model Flexibility & Routing Partial

Serval uses two model providers and splits the work between them, and the customer does not choose. In self hosted deployments, the customer provides its own keys for the providers Serval uses at runtime, an Anthropic API key as the primary provider for AI agents and help desk functionality and an OpenAI API key for embeddings, image description and specific model tasks. In Managed in Your AWS, the customer owns the AI provider keys and any customer-owned credentials supplied during onboarding, and an in product surface manages Anthropic usage.

The customer therefore owns the provider relationship, sees the spend and controls the data path to the model, but that is control over credentials, cost and data path, not model selection. Serval decides which provider handles which task, and there is no model picker, per agent model assignment, version pin or way to substitute another provider for either role. The key arrangement applies to the self hosted and hybrid models, and nothing says a Serval Cloud customer supplies keys.

Sourcedocs.serval.com self-hosting overview and prerequisitesread 2026-09-12

APIs, SDKs & MCP Extensibility Full

A large API lets outside callers reach Serval. The documentation index at docs.serval.com/llms.txt lists three sections, Documentation at 142 pages, Integrations at 164 pages and an API reference at 252 pages, and two OpenAPI documents, auth-openapi-spec.yaml and openapi-spec-v2.yaml, are served from the API reference section. Scoped API keys and customizable API scopes for app integrations grant access per integration rather than all or nothing.

An approvals API handles custom follow up logic, and access can be revoked via API and workflows, so an outside caller can drive a consequential action inside Serval. Beyond the REST API there is a CLI, which can raise access requests, and user MCP, which puts Serval inside the customer's own assistant. Webhook triggered workflows cover the event side, and workflows, guidance and configuration are managed as code in Git repositories.

Sourcedocs.serval.com llms.txt index, OpenAPI spec listings and release notesread 2026-09-12

Testing, Debugging & Optimization Partial

Help Desk Agent evaluations are in beta, a harness aimed at the agent's own behavior. What an evaluation produces is not stated, with no score, pass rate, judge verdict or comparison format. Workflows and skills are managed as code in Git with version diffs, so a change can be reviewed before it lands.

Agent powered run debugging lets a failed run be inspected, and a guidance diff view for reviewing AI suggestions gates the agent's own proposed changes to its instructions. Serval markets deterministic workflows, so behavior repeats between runs.

Its commercial claim is a guaranteed automation rate, citing customer automation percentages, which measures how much of the customer's ticket volume the agent cleared.

Sourcedocs.serval.com release notes indexread 2026-09-12

Browser & Computer Use Not documented

Integrations and APIs are how Serval acts, not driving a browser or a computer interface, and every connector works through an API. For RSA SecurID, Serval stores a client key and attaches it automatically to every call it makes on the customer's behalf, and for Presidio it exchanges credentials for a short lived JWT and sends it as a bearer token on every request. Provisioning runs via SCIM, direct API or custom workflows. Across 164 connectors the pattern is authenticated service to service calls, and the self hosted worker exists to reach internal APIs, LDAP and Active Directory over the network, not to operate a desktop.

Serval markets deterministic workflows compiled to TypeScript. It integrates Jamf and Tanium and runs device actions across managed endpoints, with every grant, device action and workflow run exportable, and those actions go through the MDM and endpoint platforms' own APIs. The CLI, which can raise access requests, is a way for people to reach Serval, not Serval operating anything. There is no hosted or local browser, desktop session, remote control, RPA or recorder.

Sourcedocs.serval.com RSA SecurID and Presidio integration pages, with the release notes indexread 2026-09-12

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

Product updates

·Human approval / guardrailsVerified

Approvals in Serval no longer need a workflow behind them. Whoever is working a ticket can open an approval card on it, name who the approval is for, choose one or more approvers, add context and decide whether a justification is required. Approvers are notified as with any other Serval approval, and the decision is logged on the ticket thread.

Bears on: Human approval / guardrails

View source
·Workflow orchestrationVerified

Serval workflows can now classify data and evaluate a condition written in plain language as built in steps, without wiring up a separate model. The workflow branches on the answer, for example deciding whether a ticket describes a security incident and routing it to the right queue.

Bears on: Agent capability

View source
·Agent capabilityVerified

Serval announced the general availability of Catalyst, an AI agent designed to build enterprise automations. Catalyst is now enabled by default for all organizations, allowing them to instantly generate automations from ticket history, natural language instructions, or existing standard operating procedures.

Bears on: Agent capability

View source
View all 6 Serval updates →Tracked since Aug 2026 · Verified from public vendor sources

Pricing

No public pricing. Serval quotes one platform fee through a demo.

Not published. The pricing page describes "One platform fee, no surprises" but gives no billing unit, rate or tier structure.

What is public

No figures are published. The pricing page at serval.com/pricing carries the headline "Serval ITSM software pricing: One platform fee, no surprises", a Book a demo call to action and a pilot in four phases (Meet, Build, Deploy, Optimize) with "a dedicated deployed engineering team on the ground." Its one commercial claim reads "50% of your tickets automated. Guaranteed." Serval positions that guarantee as a differentiator against incumbent ITSM. No plan name, figure, unit or trial length appears. The product is sold through a demo with a named customer success and account executive path. The deployment models are documented in detail and are the one published variable that bears on cost, since the self hosted models move infrastructure and AI provider spend onto the customer's own accounts.

Billing mechanics

Not published. Every commercial path routes to a demo or a contact form. Book a demo is offered from the documentation host, serval.com/contact and support@serval.com handle self hosted evaluations, and existing customers have an account executive or a shared Slack Connect channel. Deployment model is the one variable a customer can see in advance, and it materially affects total cost. Serval Cloud is fully managed with a 99.9% uptime SLA. Hybrid puts only the worker in the customer's infrastructure. The two fully self hosted models run the whole application single tenant in the customer's own AWS account or Kubernetes cluster, where the customer provides the infrastructure and the AI provider keys.

Cost watchouts

No seat price or billing unit is published, and the pricing page describes one platform fee. On the self hosted models, AI model usage is billed to the customer's own Anthropic and OpenAI accounts, so very high automation volumes raise cost outside the subscription, and self hosted deployment carries its own infrastructure overhead.

Variable cost rationale

Nothing published says Serval meters its own fee, and its pricing page promises one platform fee. The variable cost sits in the deployment model. On the self hosted models the customer supplies an AWS account it owns and its own Anthropic and OpenAI API keys, with Anthropic as the primary provider for the AI agents and help desk and OpenAI used for embeddings and image description. There the customer pays for inference and infrastructure directly, and inference scales with ticket volume, which is the thing the product is bought to increase. No published rate card or cap bounds that spend, which sits outside whatever Serval charges. On Serval Cloud, Serval runs the infrastructure and inference, and nothing states whether heavy volume changes the fee.

Additional watchouts

The deployment choice is a cost decision, not only a security one. On Serval Cloud, Serval runs the infrastructure and model inference. On Managed in Your AWS or Self-Managed on Your Kubernetes the customer brings the AWS account and supplies Anthropic and OpenAI keys, so cloud spend and token spend land on the customer's own bills and scale with ticket volume independently of the subscription. Serval leads commercially with its guarantee of 50% of tickets automated, and what is measured, over what window and what happens if it is missed are not published. Whether expansion beyond IT into HR, finance, legal or security is inside the platform fee or priced as additional is not stated, and the product is sold as a horizontal platform with isolated environments for each team. Self hosting carries an operational cost too. Serval warns that deviating from its standard Terraform and Helm bundle adds work on the customer's side and makes upgrades harder to apply.

Sales call required

Yes, required for paid access

Free / trial

None published. The pilot is a sales engagement, not a trial.

Lowest paid plan

Not published

Key ambiguities

Serval's pricing page at serval.com/pricing publishes no figure. It promises "One platform fee, no surprises", a pilot run in four phases (Meet, Build, Deploy, Optimize) with "a dedicated deployed engineering team on the ground", and the guarantee "50% of your tickets automated. Guaranteed." No billing unit, pilot length or definition of the guarantee is published, and every commercial path routes to Book a demo or Contact. The cost structure changes with the deployment model. On the fully self hosted models the customer owns the AWS account and supplies the Anthropic and OpenAI keys, so infrastructure and model inference are billed to the customer directly, outside whatever Serval charges. Serval Cloud and Managed in Your AWS are not like for like on price. No free trial or self serve access appears. The scoped pilot is a sales engagement rather than a trial.

Cancellation / refund

Not published. The guarantee of 50% of tickets automated has no published payout or period.

Missing data

Everything numeric. No list price, tier structure, billing unit, seat minimum, contract length, implementation fee or discount structure is published. Also unpublished are whether the deployment models are priced differently, what the guarantee of 50% of tickets automated pays out and over what period, how long the pilot runs, whether the horizontal modules beyond IT (HR, finance, legal, security) carry separate charges, and whether onboarding for a self hosted deployment is billed.

Agentic Index verified 2026-09-12

Alternatives to Serval

The closest documented capability profiles to Serval among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Auditoria10.5 / 14A lighter documented profile than Serval
  • Moveworks10.5 / 14A lighter documented profile than ServalServal vs Moveworks →
  • Adopt AI12.0 / 14Adds documented Browser & Computer Use
  • Beam AI12.0 / 14Fuller documented coverage on Model Flexibility & Routing and Testing, Debugging & Optimization
  • Glean12.0 / 14Adds documented Memory & State Persistence
  • Instabase11.0 / 14Fuller documented coverage on Testing, Debugging & Optimization

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.