Systems | Development | Analytics | API | Testing

ably

Raw WebSockets for AI streaming: when patching stops paying off

Sep 3, 2026 By Madeleine Quinn In Ably
Raw WebSockets drop connections, lose track of canceled responses, and don't natively reach a second device. If your AI streaming feature has been in production for a while, you've probably already built a fix for at least one of these and found another one waiting. Reconnection, cancellation, multi-device delivery, and crash detection are the four problems raw WebSockets leave for you to solve, and each is its own piece of infrastructure to build. Solve one, and the other three remain unsolved.
Read Post
zymr

AI in Claims Processing: What's Actually Working in 2026

Sep 3, 2026 By Jay Kumbhani In Zymr
‍AI claims processing applies predictive models, machine learning, computer vision, and generative AI across claims workflows. These technologies analyse documents, images, policy terms, historical records, and structured claim data. Insurers use AI for document extraction, claim triage, fraud detection, damage assessment, and adjuster assistance. Predictive models classify claims, estimate severity, and identify cases requiring specialist review.
Read Post

[Product Demo] AgentSpot Use Case - Automate Release Notes

Sep 3, 2026 By ThoughtSpot In ThoughtSpot
Release notes are the thing that always gets written last, usually by whoever has the least context, usually the morning after ship day. Everything you need is already sitting in GitHub, it just isn't in a form anyone outside engineering can read. In this video, we use AgentSpot to build a Release Notes Workflow that reads what's been merged in GitHub, translates the changes into human-readable notes, posts them to your team's Slack channel, and keeps a running Slack canvas so every release stays in one place.
View Video

[Product Demo] AgentSpot Use Case - PM Jira Assistant

Sep 3, 2026 By ThoughtSpot In ThoughtSpot
Writing tickets is the tax every PM pays. You know exactly what needs to get built, then you spend an hour turning it into properly scoped Jira issues with acceptance criteria, labels, and the right epic. AgentSpot does the writing for you. In this video, we use AgentSpot to build a Product Assistant that turns a rough feature idea into fully drafted Jira tickets, pulls in context from your existing backlog so nothing gets duplicated, and files them to the right epic ready for grooming.
View Video

From IoT Data to AI-Ready: The Edge Solution

Sep 3, 2026 By Cloudera, Inc. In Cloudera
Is your data actually ready for AI? While companies rush to deploy machine learning models, 83% of executives realize that high-value, real-time data is trapped at the physical edge—on factory floors, inside hospitals, and at retail terminals. With billions of connected IoT devices, managing this data creates massive hidden headaches like security risks and pipeline blind spots. True AI readiness starts at the edge. Bridge the gap between your edge devices and your AI goals today.
View Video
Best Hosting for Odoo: Backups, Uptime and Disaster Recovery

Best Hosting for Odoo: Backups, Uptime and Disaster Recovery

Sep 3, 2026 By SystemsDigest In SystemsDigest
Almost every Odoo host advertises backups. Very few will tell you when a restore was last tested, and those are completely different claims. The gap between them is where agencies get hurt. A backup that exists but has never been restored is not a backup. It is a file, and you find out which one it is on the worst possible day. Cloudpepper is Odoo hosting with automated backups and monitoring built for agencies running client systems, and on this particular criterion it is the strongest option available, for a structural reason covered in point seven below.
Read Post

Using MCP Tools for Declarative Pipelines - Creating the Data Pipeline - Video 2

Sep 2, 2026 By Qlik In Qlik
This is Part 2 of a two-part video series exploring how Qlik MCP tools can be used with declarative pipelines directly within VS Code. In this video, Mike Tarallo, demonstrates how to now create the data pipeline using declarative YAML in VS Code. You will see the creation process, learn some tips and tricks and see the final result.
View Video

Using MCP Tools for Declarative Pipelines - Video 1

Sep 2, 2026 By Qlik In Qlik
This is Part 1 of a two-part video series exploring how Qlik MCP tools can be used with declarative pipelines directly within VS Code. In this video, I demonstrate how to use the MCP tools to explore and validate your Qlik environment before building anything—identifying available connections, inspecting source tables, reviewing pipeline project information, and verifying the resources you plan to use.
View Video

AI Changed Everything. Except What Matters.

Sep 2, 2026 By ThoughtSpot In ThoughtSpot
AI changed the process, but not what matters. In the latest episode of The Data & AI Chief, three authors explore what it takes to lead through the AI era, from scaling innovation to building AI-ready data foundations to keeping humans at the center. This episode features: Linda Hill, Harvard Business School Professor and author of Genius at Scale, on scaling innovation and leading through uncertainty.
View Video
ably

Add resumable streaming and reliable tool calling to your OpenAI agent

Sep 2, 2026 By Fiona Corden In Ably
If you build an agent against OpenAI's Responses API then the simplest way to get output to the user is streaming over HTTP/SSE. If the user refreshes the page, loses connection, switches devices, or needs to approve a tool call, then there's nothing in the API to help you. AI Transport is Ably's session layer for agent-to-user conversations. An agent built on it gets resumable streams, multi-device sessions, and approval gates that wait for a human user, without deploying additional infrastructure.
Read Post

Copyright © 2026 OpsMatters™. All rights reserved.