2026May

Openlayer Gateway, customizable dashboards, and Salesforce Agentforce GA

Published May 15, 2026
Openlayer Gateway

Openlayer Gateway is a new managed control layer for every LLM call your stack makes. The admin portal handles API-key management, per-key rate limits and freeze, and team-based organization — and every request that flows through is observable end-to-end in Openlayer.

Customizable project dashboards

Project home pages are now fully customizable. Pin widgets for the metrics you watch most closely, see project notifications inline, and jump between alerts from a new notification center in the sidebar.

Customizable project dashboards

Salesforce Agentforce Integration is live

Trace Agentforce conversations end-to-end. Pick your login domain (production, sandbox, or My Domain) and let the updated Builder schema capture every intermediate step.

Salesforce Agentforce integration

Also new this quarter

  • On-prem Helm chart. Deploy Openlayer to Kubernetes via a Helm chart on Docker Hub OCI, with config for storage, database, replicas, image pull secrets, and Node heap.
  • Built-in governance frameworks. EU AI Act, TRAIGA, E23 MRM, and the Openlayer Governance Framework, available out of the box.
  • Audit trails. Full workspace activity log with export.
  • PII redaction in traces. Workspace-wide redaction with per-project entity-type configuration.
  • New guardrails. Llama Prompt Guard for prompt injection, English and Portuguese toxicity, and Brazilian PII recognizers (CPF, CNPJ, CEP, phone).
  • New tests. Bias, Contains PHI, and Unauthorized tool call.
  • Universal search. Jump across projects, sessions, users, and tests from one search bar.

Full feature, improvement, and fix lists are below.

Features

  • IntegrationsSalesforce Agentforce integration (GA), with configurable login domain (production, sandbox, or My Domain) and updated Builder intermediate-step schema
  • IntegrationsDialogflow integration
  • SDKsAzure Content Understanding tracer
  • SDKsPydanticAI OTel GenAI attribute parsing
  • SDKsTrace OpenAI Responses API from the TypeScript SDK
  • SDKsopenlayer-ts now accepts .csv datasets
  • SDKsTrace decorator promote parameter — surfaces nested step outputs to the parent span for easier debugging
  • PlatformPrompt-injection guardrail (Llama Prompt Guard)
  • PlatformToxicity guardrails for English and Portuguese, with opt-in chunking for long inputs and category filtering
  • PlatformBrazilian PII recognizers in PIIGuardrail (CPF, CNPJ, CEP, phone), with checksum validation
  • PlatformBias test
  • PlatformUnauthorized tool call test
  • PlatformContains-PHI test
  • SecurityWorkspace-level PII redaction on trace processing
  • SecurityPer-project PII redaction settings — pick which entity types to redact
  • SecurityAudit trails — full activity log with export
  • SecurityDomain verification on the workspace settings page
  • SecurityWorkspace setting to restrict workspace creation to deployment admins
  • SecurityWorkspace setting to prevent users from a given domain from creating workspaces
  • PlatformBuilt-in governance frameworks — EU AI Act, TRAIGA, E23 MRM, and Openlayer Governance Framework
  • UI/UXCustomizable widgets on project home pages
  • UI/UXProject notifications surfaced on the home page
  • UI/UXNotification center in the sidebar
  • UI/UXUniversal search across the workspace
  • UI/UXMore keyboard shortcuts across the app
  • UI/UXBatch actions on rows, rules, and projects tables (including multi-select and delete)
  • UI/UXFiltering and sorting on sessions, users, data sources, projects, rules, and framework progress tables
  • UI/UXHide columns in the users table
  • UI/UXTag multiple tests at once
  • PlatformSession-level aggregated metrics — view cost, latency, and token counts rolled up per session
  • PlatformLLM cost configuration — view and edit per-model pricing used for cost calculations
  • PlatformView, edit, and download custom-metric parameter bundles from the UI
  • PlatformLLM evaluator settings now configurable for Ragas metrics
  • PlatformMonitoring-data limit notifications
  • PlatformTest-connection button for LLM configuration
  • PlatformOpenlayer Gateway — centralized AI gateway with admin portal, API key management (including rate limits, visibility, and freeze), and team-based organization
  • IntegrationsBigQuery data sources without a timestamp column
  • CLIBrowser-based openlayer login (device code flow)
  • APIDelete records in monitoring mode via API
  • APIRetrieve sessions linked to a test result via API
  • APIdateUpdated filter on the List Tests API
  • On-PremHelm chart for on-prem deployments, published to Docker Hub OCI
  • On-PremSet workspace admins via environment variables on deployment
  • On-PremLicense usage and version reported from on-prem deployments to Openlayer
  • UI/UXUniversal logout improvements
  • PlatformAutomatic threshold mode for custom metrics

Improvements

  • UI/UXTrace viewer performance and navigation — faster resizing, better breadcrumbs, attachment rendering, and clearer tools view
  • SDKsLangChain callback handler latency reduced
  • UI/UXProject home page redesigned
  • UI/UXRedesigned settings pages
  • UI/UXFilter and table UI polish — multi-filter flows, virtualization for large result sets, loading states, and keyboard navigation
  • PlatformFaster initial app load
  • SecurityMFA passcode auto-authenticates on entry
  • SecurityDeep-link redirect now works after auth and with SSO
  • UI/UXUniversal search relevance improvements
  • PlatformBuilt-in framework refinements
  • PlatformDefault test thresholds set to manual mode
  • SDKsDefault session and user IDs assigned automatically if none supplied
  • IntegrationsBigQuery connection now supports Service Account secrets
  • DocsCustom CA certificates flow documented

Fixes

  • PlatformLLM-as-a-Judge reliability — rate-limit retries, temperature errors, and vague skip messages resolved
  • PlatformAnswer-relevance test no longer breaks on OpenAI embedding usage
  • PlatformJudge score false positives when set to 1 fixed
  • SDKsGoogle ADK, Azure OpenAI, and OCI tracers handle edge cases correctly
  • SDKslog_context and log_output work when called from the same function
  • UI/UXTool step type now displays actual tool name
  • UI/UXTrace modal stability — no longer reloads when new records stream in, and data no longer overflows
  • IntegrationsSalesforce Agentforce sync and session context fixes
  • IntegrationsCopilot Studio sessions: failing posts to API fixed
  • IntegrationsSlack workspace integration deletion works
  • IntegrationsVertex AI configuration now correctly reports as connected
  • SecurityLogin and auth flow fixes — SSO deep links, MFA, and WorkOS "org not found" issue
  • Security403 error when removing users from a workspace fixed
  • PlatformCustomizing the dashboard works for all roles
  • UI/UXTable and filter reliability — column widths, null filters, infinite scroll, and data display
  • PlatformCustom metrics no longer break when adding filters or with multiple tests
  • PlatformFramework sync no longer creates duplicate rules
  • CLIopenlayer update no longer fails with "invalid semantic version"
  • SDKsLangChain callback handler correctly attributes sessions and user IDs

Ship with confidence.

See your first AI system tested, monitored, and audit-ready in one demo.

2026 Openlayer. All rights reserved.