Voker

Voker wraps the OpenAI, Anthropic, Gemini and Vercel AI SDK clients and works with LangChain and CrewAI to capture a customer's agent calls and tool calls, and its people API ties events to user data the customer already holds. These bring the customer's agent data in; the agent calls its own tools, and no integration through which an agent reads or writes a real system is described.

SourceVoker, docs.voker.ai overview, provider guides and people conceptread 2026-09-21

Customers build and run the agents Voker measures in their own code or in frameworks such as LangChain and CrewAI. No sequencing, branching, retries or routing of agent steps run by Voker is documented.

SourceVoker, docs.voker.ai overview and voker.ai homepageread 2026-09-21

Voker identifies knowledge gaps in a customer's agents from their conversations. No document ingestion, index, retrieval layer or knowledge API that grounds an agent in company data is documented.

SourceVoker, voker.ai homepage and docs.voker.ai overviewread 2026-09-21

Agents are measured after the fact, through annotations, rates and session summaries, and Voker's human reviewer settings govern whether it removes a Smart Skill without review. No approval step, checkpoint, guardrail or pause on the customer's agent's actions is documented.

SourceVoker, docs.voker.ai Smart Skills and agent analyticsread 2026-09-21

SSO comes with the Enterprise plan, and the homepage states customers retain full ownership of their data with custom retention on Enterprise. No security attestation is published.

SourceVoker, voker.ai homepage and pricingread 2026-09-21

Every LLM call or wrapped execution becomes an event tied to an agent version and a person, and Voker stores the ordered messages including user inputs, system prompts and model responses along with the agent's tool calls, groups events into sessions for a whole conversation or workflow, and lets teams drill from the dashboard into individual sessions to debug them. Data is kept 30 days on the free plan, 90 days on Starter, one year on Agent First and a custom period on Enterprise.

SourceVoker, docs.voker.ai events and sessions, agent analytics, and voker.ai pricingread 2026-09-21

For analytics, Voker stores events, sessions and person profiles, and it tracks long-running conversations as sessions. No session, workflow or long-term memory that a customer's agent reads and writes through Voker is documented.

SourceVoker, docs.voker.ai events and sessions and long-running conversations cookbookread 2026-09-21

Voker runs as a hosted platform, states that self hosting is available, and lists self-hosted deployment and custom data retention on its Enterprise plan.

SourceVoker, voker.ai homepage and pricingread 2026-09-21

The docs include cookbooks that show how to instrument customer support and long-running agents. No ready-made agents, templates or packaged workflows a buyer adopts for its own work are documented.

SourceVoker, docs.voker.ai cookbook overviewread 2026-09-21

Annotation runs automatically on every event Voker receives, tagging intents, corrections and resolutions, and Voker generates a Smart Skill for an agent on its own once it reaches a confidence threshold that the prompt is not handling a set of tasks, based on user corrections and logged errors. Both start on an incoming event or a threshold, without a person asking.

SourceVoker, docs.voker.ai auto annotations and Smart Skillsread 2026-09-21

Each agent version's model is recorded and versions are compared, but the customer's code chooses and calls the model, and Voker offers no model selection, routing, fallback policy or provider configuration of its own.

SourceVoker, docs.voker.ai overview and agents conceptread 2026-09-21

Voker publishes Python and TypeScript SDKs that wrap the OpenAI, Anthropic, Gemini and Vercel AI SDK clients, and a REST API with OpenAPI specs to create events, people, agents, agent versions and fingerprints, for languages and frameworks the SDKs do not cover.

SourceVoker, docs.voker.ai Python SDK, TypeScript SDK and API referenceread 2026-09-21

Each event is labeled with the user's intent, any correction and whether the intent was resolved, and Voker reports resolution and correction rates per intent category, filters them by agent version so teams compare how a prompt or model change affected each intent, and its Smart Skills generate prompt amendments from corrections and errors, flag skills that raise cost or correction rate, and version the agent each time. Comparing those rates across versions tracks quality over time and after each deployment.

SourceVoker, docs.voker.ai categorization, auto annotations and Smart Skillsread 2026-09-21

The documentation covers analytics, annotations, Smart Skills and SDK instrumentation for AI agents, and no browser, desktop or computer control by an agent is documented.

SourceVoker, docs.voker.ai overview and llms.txtread 2026-09-21