Product updates

Changelog

What’s new in Prefactor. Features, improvements, and fixes shipped to the platform and SDKs.

TL;DR

The changelog lists what shipped in Prefactor, grouped by month and filterable by category — platform, SDK & CLI, observability, evaluation, governance & compliance, integrations, and more.

July 2026

Agent alerts

Agents can now raise alerts when something needs a person. Define alert schemas per agent, raise and clear with severity and a structured payload through the API and CLI, and get every lifecycle event recorded as a span so the history is auditable.

Quality payloads, readable at a glance

The quality tab now renders an instance's quality payload as a sorted key-value table — measures on the left, results on the right, nested values pretty-printed — with the template summary kept up top. No more reading raw JSON.

Risk levels in the conversation view

The conversation view now shows a risk level beside every item in the exchange, so you can scan a whole conversation and spot the step that needs a closer look without opening each span.

Span purpose: quality signals split from activity

Every span now carries a purpose — activity or quality — visible in span details and filterable in the API and CLI, so you can watch what an agent did and evaluate how well it did it without the two muddying each other.

One conversation view across every SDK

A dedicated Conversation API now powers the instance conversation view, with mappers for Claude SDK, LangChain (Python and TypeScript), and LiveKit spans, plus a visual lift for the chat components.

Instance purpose and quality payloads

Mark every agent instance as live, smoke test, or eval; register a quality schema per agent; and attach quality payloads to instances, surfaced in the UI so you can evaluate runs against the outcomes you said matter.

Sensitive data redacted by default

Sensitive values are separated from span payloads at the source and shown redacted by default, so agent telemetry can be watched and shared without exposing what your agent touched. The sensitive half is stored apart from the span and can be discarded on its own.

Onboarding experience revamp

A reworked first-run experience that takes you from an empty workspace to your first instrumented agent with less friction.

June 2026

CLI setup command, ping, and startup token validation

A new setup command scaffolds a working configuration, the ping endpoint tells you exactly what your token can do, and the Python SDK validates its token at startup instead of failing on the first span.

GitHub Copilot agent visibility

Agent sessions driven through GitHub Copilot in VS Code, ingested over OpenTelemetry, now show the user's request, a proper conversation view, and a per-instance cost breakdown.

Conversation view for Vercel AI SDK agents

Agents built on the Vercel AI SDK now get the full conversation view: messages, tool calls, and compact rendering for custom spans.

Agent context API and CLI review workflow

Pull the full context of an agent instance, its spans, inputs, and outputs, through a dedicated endpoint, straight from the CLI. Built for reviewing what an agent actually did.

Teams and people

Model the humans around your agents. Create people and teams, connect agents to owners and owning teams, browse team overview pages, and navigate agents grouped by team.

May 2026

Quality tab on the agent detail page

A dedicated quality tab on every agent: the home for evaluating how well an agent's output holds up, not just whether it ran.

Risk profiles and the redesigned agent risk overview

Define risk profiles, agree a maximum acceptable risk per agent, and watch live risk roll up from instance to agent to overview. The redesigned risk summary shows where an agent stands against what you agreed.

Terminate running agents from the platform

Stop a running agent instance remotely. Termination requests flow from the platform over the WebSocket API, and both SDKs now honour them.

Token and cost metrics for agent instances

Every agent instance now shows token usage and cost computed from model pricing: prove what each run costs instead of guessing.

Voice agents: LiveKit SDKs for Python and TypeScript

Watch voice agents the way you watch text agents. LiveKit integrations for both SDKs capture sessions, turns, and tool use from real-time voice pipelines.

April 2026

Install the CLI with one shell command

A shell installer for the Prefactor CLI: one command fetches the right binary for your platform and gets you to a logged-in prompt in seconds.

Report data risk from your agent code

Both SDKs can now report data risk categories directly from agent code, feeding the platform's risk picture with what your agent actually touches, plus an agent skill that walks coding agents through wiring it up.

Telemetry failures can no longer take your agent down

An SDK telemetry problem now stays contained instead of bringing your agent down with it. Malformed bearer tokens are rejected cleanly at the API, and platform views recover gracefully when a load fails.

March 2026

Claude Agent SDK support in the TypeScript SDK

Instrument agents built on Anthropic's Claude Agent SDK. Sessions, tool calls, and results flow straight into Prefactor alongside your LangChain, Vercel AI SDK, and OpenClaw agents.

Per-tool span schemas for granular agent visibility

Define custom span schemas for individual tools in your LangChain and Vercel AI SDK agents. Tool-specific span types replace generic "tool call" events, giving you observability that matches your agent's actual architecture.

CLI login flow and multi-platform binaries

One-command authentication with `prefactor login`. Pre-built binaries for Windows, macOS, and Linux (x64 + ARM), with canary and stable release channels.

Real-time WebSocket API for agent management

Subscribe to agent instance updates in real time. WebSocket API includes graceful instance termination handling and live status streaming for running agents.

Data risk tracking in span schemas

New `data_risk` field in span type schemas surfaces agent risk signals directly in the Prefactor dashboard. Monitor which tools are handling sensitive data at a glance.

Idempotency key support for safe retries

UUID-based idempotency keys across Python and TypeScript SDKs. Every span and agent operation is retry-safe with server-side validation, ensuring data integrity in production workloads.

OpenClaw conversation view

Agent instances from OpenClaw now render in a human-readable conversation format. Understand agent reasoning and tool usage patterns at a glance instead of parsing raw event logs.

API docs, skill guides, and macOS setup fixes

TypeDoc-generated API documentation for Core, AI SDK, LangChain, and OpenClaw packages. New guides for instrumenting existing agents and building provider adapters. Setup scripts now work on macOS.

macOS setup, OpenAPI CI, and SDK init refactor

Setup scripts now work on macOS. OpenAPI spec generation added to CI. SDK core init refactored to a provider-based client API with improved shutdown semantics.

February 2026

Getting started redesign and OpenClaw conversation view

Redesigned onboarding with integration cards and guided setup panel. OpenClaw agent instances now render as human-readable conversations.

SDK documentation, CLI tool, and skill guides

TypeDoc-generated API docs for all major packages. New P2 CLI tool for managing agents from the terminal. Skill guides for instrumentation and provider adapters.

Python SDK v2

Major version update to the Python SDK with an improved API surface. Aligns with the TypeScript SDK's architecture for consistent cross-language developer experience.

OpenClaw plugin for Vercel AI SDK

First-party OpenClaw plugin for instrumenting Vercel AI SDK agents. Drop-in integration with automatic span collection and skill guides for setup.

SDK architecture overhaul with direct transport

Next-generation TypeScript SDK architecture with a direct transport layer. Removes intermediary abstractions for lower latency and simpler debugging.

Frequently asked questions

How often is the changelog updated?
Entries are added as features, fixes, and improvements ship — there is no fixed release cadence.
Can I filter the changelog by category?
Yes. Use the filter pills above the timeline to view updates for a single category, such as SDK & CLI or Security.
Is there an RSS feed or way to subscribe to updates?
Check this page directly for the latest entries. For platform-specific release notes, see the docs at docs.prefactor.ai.

See how every agent performs, and make it better

Prefactor helps teams observe, evaluate, and improve their AI agents in production, across every framework and provider.