Lyzr for AI agents
Agents read Lyzr at once. Changes and sends are held for a person's approval by default.
About Lyzr
Build, run, evaluate, and manage AI agents and related Lyzr Studio services, including voice, responsible AI, simulation, memory, scheduling, workflows, and knowledge bases.
What an agent can do in Lyzr
Every Lyzr action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.
Runs at once (reads)
Looks things up in Lyzr without asking first. 13 actions.
- Get AgentReturn the current configuration and status of one Agent Studio agent by ID.
- Get Knowledge BaseReturn one Lyzr Knowledge Base configuration by its known RAG configuration ID.
- Get Simulation OverviewReturn aggregate Agent Simulation counts and average evaluation pass rate for the connected workspace.
- List AgentsReturn all Agent Studio agents owned by the connected API key, including IDs needed by lifecycle and inference tools.
- List Agent SchedulesReturn one page of agent cron schedules, optionally filtered by user, agent, or active state.
- List Agent Simulation IssuesReturn recent performance, error, and Responsible AI issues across monitored agents, optionally filtered by resolution and severity.
- List RAI PoliciesReturn Responsible AI policies owned by the authenticated user, including policy IDs and enabled guardrail configuration.
- List SuperFlow ExecutionsReturn one page of SuperFlow execution records, optionally filtered by workflow and execution status.
- List SuperFlow WorkflowsReturn all SuperFlow workflow definitions accessible to the connected API key, including workflow IDs and graph data.
- List Voice AgentsReturn saved Voice agents accessible to the connected organization, including IDs used to filter transcripts.
- List Voice TranscriptsReturn one page of accessible Voice call transcripts, optionally filtered by agent, session, organization, or date range.
- Retrieve KnowledgeRetrieve relevant documents from a known Lyzr Knowledge Base using configurable basic, MMR, hypothetical-document, or time-aware retrieval.
Show all 13
- Search MemoriesSemantically search stored memories for one owner, within one session or across that owner's sessions, using Lyzr's hybrid vector and BM25 retrieval.
Held for approval by default (changes and sends)
Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 9 actions.
- Add Memory MessagesStore a batch of conversation messages in Lyzr Memory for an owner, session, and optional agent, with optional synchronous fact extraction.
- Chat With AgentSend a message or message history to an active Agent Studio agent and return its synchronous inference response for a session.
- Clear Memory SessionPermanently clear messages and memories for one explicit owner and session in Lyzr Memory. Cross-session deletion is always disabled.
- Create AgentCreate a single-task Agent Studio agent with an LLM provider, model, instructions, and optional tool configuration.
- Create Agent ScheduleCreate a cron schedule that runs one Agent Studio agent with a message in a specified timezone.
- Delete AgentPermanently delete one Agent Studio agent by ID.
- Delete Agent SchedulePermanently delete one agent cron schedule and remove its associated scheduler job.
- Evaluate Text With RAI PolicyApply one owned Responsible AI policy to text and return processed text, block decisions, warnings, detections, and redactions.
- Set Agent StatusActivate or deactivate an Agent Studio agent. Deactivated agents reject inference until reactivated.
Changes wait in Needs you
Changes and sends in Lyzr are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
Lyzr questions
Can an agent change data in Lyzr on its own?
Not by default. Changes and sends in Lyzr are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
What can an agent read in Lyzr?
This connector lists 13 read actions. Reads run at once, without waiting for approval.
How does Lyzr connect?
It connects with API key. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.