Changelog

✨ August’s spotlight is an AI voice-and-browser stack. Vapi lets recipes place outbound calls and control live conversations (speak, transfer, end). AssemblyAI handles the other half — upload audio, transcribe, export SRT/VTT, and run LLM prompts over transcripts, with webhooks when jobs finish. Airtop adds cloud browser sessions so agents can scrape pages, ask natural-language questions, extract lists, and click or type without running their own browser fleet.

Also this month: Clay for company/people lookups and ICP signals; Tanium for endpoint management via the Core Platform API; Azure Event Hub for high-throughput event publish and batch ingest; plus two OPA extensions — Keeper Secrets Manager for in-network secret retrieve/rotate, and Email (Custom) OPA for SMTP/IMAP/POP3 over a secure tunnel.

🔧 Enhancements lean on auth, schemas, and connectivity: OPA secure tunnels for Google Pub/Sub; OAuth/PKCE for Looker and Employment Hero; new Telegram actions and granular event subscriptions; hierarchical field picks and richer time-off filters in HiBob; $select/$expand-aware pills in OData; multi-select job status in SmartRecruiters; Qualtrics mailing lists on XM Directory; Embedded export fixes; and Ironclad Custom action with leaner non-admin OAuth. Veeva Vault continues upload and picklist polish.

🛡 Stability fixes cover OpenAPI anyOf schema rendering, Azure DevOps Service Principal token refresh after idle/expiry, and SOAP DateTime and Boolean unmarshalling.

Genies run support tasks up to 30 minutes — covering deep research, large document generation, and multi-step tool chains — with no setup or configuration required.

• Built for Longer-Running Work — The platform supports Genies running up to 30 minutes across any mix of LLM generation, knowledge base search, and tool calls.
• Real-Time Visibility — End users see agent messages, tool calls, and search calls as they happen, in the correct order, no matter how long the run takes.
• Same Guarantees for Headless API — Teams building on the Headless Genie API get the same real-time, ordered event stream as native Slack and Teams users.

Learn more in Agent Studio.

Skills can be tested directly from the skill editor — no Genie required, no tab switching, no prompt-engineering your way into a skill invocation.

• Test in the Skill Editor — Hit Test and run the skill in one window, exercising its logic directly without going through a Genie.
• No Genie in the Loop — A failed run no longer leaves a Genie stuck waiting for output that never arrived; debug and re-run from the skill itself.

Learn more in Agent Studio.

A stop button is now available in the AIRO input bar whenever AIRO is actively thinking or executing — click it and AIRO halts within a few seconds, preserving everything up to your last completed turn as context.

Learn more about AIRO.

End users can rate Genie responses with a thumbs up or thumbs down directly in the conversation — giving builders systematic, real-time signal on what's working and what isn't. On by default, no setup required.

• Native, Instant Capture — Feedback is captured directly on each response in Slack, Teams, and custom interfaces via API, with an optional short comment from the user.
• Full Context on Feedback — Drill into any flagged conversation from the conversation history tab to see the exact message and full trace behind it.
• Home Page Visibility — A feedback summary widget shows your positive/negative split and trend over a selected timeframe.
• Flows Everywhere You Already Look — Feedback data is included in conversation exports, the Dev API, and log streaming.
• Foundation for What's Next — Native feedback data feeds directly into the batch-run and automated grading phases of the broader Agent Studio evaluation framework.

Learn more in Agent Studio.

A single Genie can connect to multiple chat interfaces and triggers simultaneously — no more creating and maintaining duplicate Genies per connection.

• Multi-Connection Support — Connect one Genie to multiple unique Slack workspaces, unique Teams tenants, Workato GO, and unique custom interfaces all at once.
• Centralized Trigger Management — Chat Interfaces have moved to a new Trigger module, where all connected chat interfaces and recipe triggers are listed and managed in one place.

Learn more in Agent Studio.

The Headless API removes the constraint of deploying Genies only through Slack, Teams, or Workato GO. Customers choose the surface, the authentication model, and the interaction pattern — now in open beta across all workspaces.

• Any Surface — Embed a Genie in your own web app, mobile app, employee portal, or internal tool. Slack, Teams, and Workato GO become one option among many.
• Your Identity Model, Your Choice — Static API key for full identity ownership, or OAuth 2.0 (PKCE) through Workato Identity for SSO-governed per-user access via Okta, Azure AD, or OneLogin.
• Beyond Chat — Drive Genies from CI pipelines, batch jobs, recipes, and other agents — anywhere a human typing in a chat window used to be a hard requirement.
• The Whole Lifecycle in Code — Combine the Headless API with AIRO MCP to create, configure, run, test, and deploy a Genie without ever opening the Workato UI.
• Flexibility Without Losing Oversight — Dedicated Genie Runtime API role, per-client IP allow lists, and integration with log streaming.

Learn more in Headless API.

Event topics can be shared across workspaces within the same Automation HQ, so recipes across multiple workspaces work off the same shared topic in real time — no workarounds, no duplicated topics.

• One Org-Wide Switch — An AHQ admin enables cross-workspace sharing once; any managed workspace can then grant topic access to any other.
• Workspace-Managed Grants — Workspace admins select which topics to share and assign Publish, Subscribe, or both permissions per workspace.
• Multiple Publishers & Subscribers — Several workspaces can publish to and consume from one shared topic simultaneously.
• Clear Topic Differentiation — Shared topics carry a Granted tag so it's immediately clear which topics were shared versus owned, visible in both the topic list and the recipe's Message Topic dropdown.
• Schema & Message History Access — All granted workspaces can view the schema and full message history of any topic shared with them.

Learn more in Cross-Workspace Sharing.

Data pipelines provides expanded connectivity across enterprise apps, ERPs, databases, and file stores — with deep ERP, Finance, and HR reach — plus expanded warehouse and database destinations.

• ERP & Finance — NetSuite, Oracle EBS, Oracle Fusion Cloud, SAP Table Reader, SAP BW OHD, MS Dynamics Business Central, Workday, Workday RaaS, Ellucian Banner, and Sage Intacct.
• Apps — Salesforce, ServiceNow, HubSpot, Coupa, Shopify, Stripe, Zendesk, Jira, Marketo, Intercom, QuickBooks, Zuora, HiBob, Cornerstone, Xero, Asana, BambooHR, Greenhouse, Gong, Anaplan, LinkedIn, Facebook, and more.
• Databases & File Systems — Oracle DB, Microsoft SQL Server, Snowflake, MySQL, Postgres, Google BigQuery, Amazon S3, Google Drive, Google Sheets, SFTP, Azure Blob Storage, and Google Cloud Storage.
• Destinations — Snowflake, Databricks, BigQuery, Microsoft SQL Server On-Prem, Postgres On-Prem, and Amazon Redshift.

Learn more in Data Pipelines.

Intermediate messages and persistent Tool Call Streams are now available in Workato GO, completing channel parity alongside Slack and Teams. Users see exactly what a Genie is doing — step by step — while processing their requests.

• Intermediate Messages Always Shown — Any response-relevant content the LLM returns is surfaced in GO and Test Mode, ensuring full parity with what the Genie intends to communicate.
• Persistent Tool Call Stream — Each intermediate message is accompanied by a real-time stream of the Genie's actions, providing full observability over every step taken in response to a query.
• Collapsible Streams — Users can collapse any Tool Call Stream to reduce visual clutter — it keeps running in the background and can be expanded at any time.
• Human-Readable Tool Labels — Internal tools display plain-language labels (e.g. "Searching knowledge base [My KB] for [query]…") instead of raw function names.

Learn more in Agent Studio.