TicketIQ
Triage, duplicate folding and grounded answers for the service desk. Rules decide first, and a model is asked only when they are unsure.
- ServiceNow
- Jira
- Zendesk
- Freshservice
- Microsoft Teams
Agents that
take on the work
AI agents you can see, trace, approve and stop · For IT, HR, SAP, Salesforce, finance and any other system
Session
service-desk · ServiceNow-style ITSMFix the highest-priority ticket
Working in the ServiceNow-style ITSM
- service-desk / query Incident4 Incident records
- service-desk / get record ConfigurationItem CI-2001vpn-gw-01
- service-desk / read policy “VPN down for all remote staff: tunnel drops at sign-in”3 articles
- service-desk / propose change Incident INC0010041held for your approval
Waiting for your approval
Incident INC0010041
- AssignmentGroup
Service Desk→ Network Operations- State
New→ In Progress
- Web People sign in to the Liyagent app in any browser and talk to the agents they may use. The Liyagent app
- Teams Build the Liya app package in the console and upload it for your tenant in the Teams admin center. Then people open Teams and start talking. Set up Teams
- Google Chat Create a Chat app in your Google Cloud project and point it at Liyagent. Then people message Liya from your Workspace domains. Set up Google Chat
- Terminal Install the liya CLI with one command and run liya try on the sample systems, or sign in to your own instance. Download liya
- Mobile People open the Liyagent app on their phone and add it to the home screen. Approvals reach them there too. The app on a phone
01 · Pre-built agents
Start with five. Build any other.
Each product is a set of agents for one part of the business and the systems behind it. They share one control plane with the agents you build, so every agent is governed, budgeted and audited the same way.
HR agents
Answers on leave and policy from the HR record itself, and onboarding tasks followed through for each new starter.
- Workday
- BambooHR
- SAP SuccessFactors
- Greenhouse
Agents for SAP
Maintenance, purchasing, sales, stock and supplier invoices in S/4HANA, people and time off in SuccessFactors, and Field Service dispatch. Within SAP’s API Policy.
- SAP S/4HANA
- SAP SuccessFactors
- SAP Field Service Management
- SAP Integration Suite
Liya for Salesforce
Answers from Salesforce records with the asking person’s own access, runs your Flows and Prompt Builder templates, and searches Knowledge. Every write waits for a person’s approval by default.
- Salesforce
- Salesforce hosted MCP
- Data 360
- Tableau Next
Liya Finance
Matches supplier invoices to their purchase orders, flags price and quantity variances beyond your tolerance, holds a mismatched invoice for AP approval, and answers spend questions.
- NetSuite
- Dynamics 365
- Ramp
- DocuSign
Liyagent platform
Build agents for any other system, or register the ones you have. Connect them through the built-in connectors, vendors’ own MCP servers, or anything over MCP, OpenAPI, OData, SQL or agent-to-agent.
Build your own50 built-in connectors
ServiceNowJiraZendeskFreshservicePylonincident.ioGrafanaWorkdayBambooHRSAP SuccessFactorsGreenhouseSAP S/4HANASAP Field Service ManagementSAP products (published APIs)NetSuiteDynamics 365Dynamics 365 Finance & OperationsDynamics 365 Business CentralRampDocuSignSalesforceMicrosoft TeamsSlackDiscordSharePointGmailGoogle DriveGoogle CalendarMicrosoft Entra IDOktaSQL databasesMongoDBMongoDB AtlasNeo4jNeo4j AuraRedisRedis CloudElasticsearchQdrantMetabaseAmazon RedshiftAmazon S3Amazon SNSAmazon SQSGoogle Cloud Pub/SubNATSAmazon BedrockOpenAICohereText chunker
Plus presets for vendors’ own MCP servers, among them GitHub, Confluence, Notion, PagerDuty, Salesforce, Dynamics 365 and SAP Integration Suite. Anything else connects over MCP, OpenAPI, OData, SQL or agent-to-agent. All connectors
02 · Control
See it, approve it, stop it
You can see every agent, follow every run and stop any of them. Every system an agent reaches has a setting for its writes, and each tool can have its own. A new connection starts at approval required. Open it up as trust grows, and close it the moment you need to.
Example: a tool that closes ServiceNow incidents
Approval required
The call is held with its arguments exactly as they would be sent. A person approves, edits or rejects it, and the decision is audited. New connections start here.
Rules on the arguments only tighten it
- Close 3 incidentsruns
- Close 300 at oncewaits for a person
- Name a production hostdenied
Every agent in one list
The agents we supply, the ones you build and the ones you run elsewhere and register sit in one fleet list, with an inventory you can export. A caller nobody registered is flagged.
A trace for every run
Follow any run step by step: each model call, tool call and guardrail check, with its tokens and timing. The run’s record shows what it cost and any write held for approval.
Kill switches
Stop one agent, a group of agents or every agent at once. Calls already running are cut off, and one tool or one connected server can be paused alone.
Autonomy ladder
Give each agent a level: shadow, draft, exceptions or autonomous. A person raises it on measured evidence, and it drops by itself when the evidence turns bad.
Policies as code
Cedar policies decide which person or agent may do what.
Budgets
Spend is reserved before each model call and capped per agent, per team and per tenant.
Guardrails
PII redaction, prompt-injection blocking and denied topics, on inputs, outputs and tool calls, wherever you switch them on.
Red-team release gate
Built-in attack runs score each agent. Turn the gate on, and a new version ships only after a fresh run passes.
Hash-chained audit
Every step, approval and cost on a chain you can verify. Change or delete a row and the chain breaks.
Receipts you can verify
Each write an agent makes through a connected system leaves a receipt on a hash-chained ledger, tied to the approval it ran under. Export the ledger as a signed bundle and an auditor can check it offline.
Any model, with fallbacks
Gemini (Gemini API or Vertex AI on Google Cloud), Anthropic, OpenAI, Bedrock, or any OpenAI-compatible endpoint, with a chain of fallbacks for each agent.
Grounded answers
Answers from your knowledge base carry a confidence band, so a weak match is shown as one.
03 · Where it runs
Three ways to run it
The same control layer each way. Use the service we host, run the whole platform in your own environment, or keep the agents you already run and put Liyagent over them. Postgres is the system of record, with a Qdrant vector index beside it.
SaaSHosted by LiyagentWe run it for you on AWS, in the region you need. The Team plan is priced per deployed agent per month with runs included, and Business covers larger rollouts. See pricing.
Self-hostedIn your own environmentUnder the annual Enterprise licence: Docker Compose or Kubernetes with the Helm chart, in your cloud account (AWS, Azure, Google Cloud) or data centre. Your records stay there, with the models you choose.
Control layerOver agents you already runKeep agents built with any framework where they are. Register each one and send its model calls through the Liyagent gateway, and it gets an identity, guardrails, a budget, a kill switch and an audit trail.
ResidencyModel calls stay in regionWhen a tenant names a region, a model call that is not known to stay there is refused.
IdentitySSO and SCIMOIDC sign-in with Entra ID, Okta, Google Workspace, Keycloak or Auth0, and SCIM 2.0 provisioning from your directory.
ChannelsWhere people already askMicrosoft Teams, Slack, Google Chat, email, web chat and the workspace app, plus webhooks, schedules and agent-to-agent.
04 · Agents for SAP
SAP, by SAP’s rules
SAP’s API Policy limits how AI agents may call SAP’s APIs. Liyagent works within it in two ways, so you can start with the SAP you already run.
Directly to SAP’s APIs
An agent never calls SAP on its own. It proposes each call in plain words, the person who asked confirms it in Teams or web chat, and fixed code makes that one call. Creating documents stays off until your SAP Digital Access licence is acknowledged.
Through your SAP MCP gateway
Agents read through the MCP servers you deploy in SAP Integration Suite, the route SAP provides for AI agents. Anything that can change SAP is still confirmed.
Planner Is pump P-101 OK? Raise a notification if it needs one.
Liyain Microsoft Teams
Run this in SAP?
Create an SAP maintenance notification for equipment 10004711: “Inspect P-101 bearing. Vibration 7.1 mm/s, limit 9.0”
- Priority
- 2 · High
- Ticket
- P-101
This creates an SAP service and maintenance document, which may count toward your organisation’s SAP Digital Access licence.
Nothing is sent to SAP until you confirm. This expires in 15 minutes.
ConfirmCancel
05 · For builders
Build an agent for any system
The five products are starting points. In the console, an admin, or anyone your roles allow, builds an agent in one form, then connects it where people already work.
- InstructionsWhat it does, in plain words
- ModelAny provider, with fallbacks and a context window up to 2,000,000 tokens
- ToolsFrom the catalogue, or any MCP server
- Sub-agentsEach with its own instructions, context budget and limits
- LimitsBudgets, write settings and the guardrails you attach
- ChannelsTeams, Slack, Google Chat, email, web chat or the workspace
For developers
> liya apply -f ./agents --dry-run
Agents, policies, guardrails and triggers as YAML, applied with the liya command line. Also an MCP server, OpenAI- and Anthropic-compatible gateways, and a REST API.
06 · Get started
Start free. Pay per agent when it works.
A free trial, then the Team plan per deployed agent per month, or Business and the Enterprise licence for your own environment through our sales team. See pricing.
- 01
Start free
A 14-day trial on a hosted workspace of your own: the five solutions, up to 3 agents of yours and 1,000 runs. No card needed.
- 02
Try it live
Ask Liya to work in five sample systems right now, with no sign-up.
- 03
Book a demo
Thirty minutes on your use case, with the systems you run.
07 · Questions
Frequently asked questions
What is Liyagent?
Liyagent is a software platform for governed AI agents. You can use the service Liyagent hosts, run it in your own environment under an annual licence, or put it over agents you already run. Agents reach the systems you already have through each system’s own APIs. Agents for IT service, HR, SAP, Salesforce and finance are ready to use as starting points, and you can build agents for any other system. Every agent shares one control plane for policies, budgets, approvals and audit.
Where does Liyagent run?
Three ways. As a service that Liyagent hosts on AWS, in the region you need, on the Team and Business plans. In your own environment under the annual Enterprise licence: Docker Compose or Kubernetes with the Helm chart, in your own cloud account (AWS, Azure or Google Cloud) or data centre, with PostgreSQL as its system of record. Or over agents you already run: register each one and send its model calls through the Liyagent gateway, so it gets the same identity, guardrails, budget, kill switch and audit.
Which AI models does it work with?
Google Gemini (with a Gemini API key, or on Vertex AI in your own Google Cloud project), Anthropic, OpenAI and Amazon Bedrock, or any OpenAI-compatible endpoint such as Ollama, vLLM, OpenRouter, Groq or Azure OpenAI, including models on your own GPUs. Each agent has its own model chain, fallbacks and spend budget.
How does an agent decide what it may change?
Each connected system is read-only or not, and each write tool is allowed, held for a person’s approval or denied. A new connection starts at approval required. Rules on a call’s arguments can only tighten it, so closing three tickets runs while closing three hundred waits for a person.
How do we see what an agent did?
Every agent you register is in one fleet list, and every run has a trace: each model call, tool call and guardrail check, step by step, with what the run cost and any write held for approval on its record. Each write an agent makes through a connected system also leaves a receipt on a hash-chained ledger, which exports as a signed bundle an auditor can verify offline.
Can we stop an agent straight away?
Yes. A kill switch stops one agent, a group of agents or every agent, and calls already running are cut off. Engaging it takes a reason and its own permission, and it stays on until a person lifts it.
How does Liyagent work with SAP?
Two ways, both built to work within SAP’s API Policy. Directly over SAP’s APIs, an agent never calls SAP on its own: the person who asked confirms each call in Teams or web chat. With SAP Integration Suite, agents can work through your own SAP MCP gateway. You remain responsible for your SAP licences.
How do we get started?
Start a 14-day free trial on a hosted workspace of your own, or try Liya on the sample systems on this site with no sign-up. Then choose a plan: Team is priced per deployed agent per month on liyagent.com/pricing, and Business and the self-hosted Enterprise licence are priced with our sales team.