by Gary Mintchell | May 1, 2026 | Cloud, Generative AI, Manufacturing IT, Software
Yes, I know that a couple of weeks have passed since I returned from Miami and the Aras Community Event. I got a quick podcast (also YouTube) recap posted, then went on vacation. This week had more appointments than my usual month. I’ve done a bunch of research (thanks Claude) and have much to digest. That’ll be tomorrow’s work (in between helping replace my daughter’s front door hardware and catching an English Premier League game). Tonight, a concert at Chicago Symphony Center celebrating Chicago’s contributions to jazz.
I also have two things in queue regarding frontline workers–one from ACE and another a report from PwC where I finally was able to connect with the report’s author.
Finally in queue, are thoughts from the Siemens press conference from Hannover Fair. A bit of compare and contrast with the ACE experience with AI, LLMs, and agents.
Have a good weekend. Back Monday.
by Gary Mintchell | Apr 28, 2026 | Manufacturing IT, Software
Ignition 8.3.5 is here, and Inductive Automation’s Jennifer Faylor explains on the company blog.
Expanded OPC UA support
Ignition 8.3.5 delivers OPC UA support for using a Global Discovery Server, a new file-based Secret Provider type, and major improvements for large-scale systems (including an OverridesOnly tag parameter and 4X increased throughput for managed tag providers).
In Ignition 8.3.5, you now have the ability to automate the certificate management of multiple OPC servers and devices from a single Global Discovery Server (GDS). This is possible thanks to a new property on the OPC UA Server Settings page: “GDS Push Enabled.” When this new property is enabled, the server’s certificate and trust list can be managed by an external GDS.
With this new functionality you can use an external GDS to centrally manage a dispersed system. By opening the door to central certificate management with a GDS, this new feature helps strengthen security in your industrial control systems.
File-Based Secret Provider
Another security improvement in 8.3.5 is a brand new way to store secrets from your Ignition Gateway. A new “File” Secret Provider type lets you read secrets in files on disk, as opposed to storing them internally on the Gateway installation directory. This Secret Provider supports encrypted (Ignition) secrets as well as cleartext secrets.
OverridesOnly Tag Parameter
As a result of some Ignition users’ more complex scripting needs, we’ve added a new overridesOnly parameter to the system.tag.getConfiguration() function. What this means is that when you’re calling the getConfiguration function for a specific tag path, you can now have just the local (overridden) properties returned. If this new parameter is set to “True” then only overridden properties from UDT members (instances and definitions) will be returned. And if the tag is not a UDT member, then there will be no effect.
Improved Gateway Configuration
In 8.3.5, we’ve improved the performance of the Gateway’s configuration file system and added new Gateway diagnostic resource metrics.
By allowing operations on different resource types to proceed concurrently with minimal locking on changes, we’ve greatly boosted the performance and responsiveness of the Gateway’s configuration system. This update optimizes tag value handling and increases throughput by 4X for managed tag providers.
The process of writing Ignition resources (such as EAM agents, OPC UA server profiles, database connections, SIP notification profiles, and more) into the Gateway file system is now significantly improved. And thanks to the new diagnostic resource metrics, you can use the Metrics Dashboard to observe those various resources more closely.
This update is an especially big deal for anyone using MQTT modules with Ignition, since it represents a substantial increase in capabilities for customers with large systems.
Docker Utility
We added the jq command-line utility to Ignition’s Docker image for easier JSON parsing. This is a helpful addition if you’re customizing Helm charts or entrypoint scripts, since you can use this utility to grab specific properties from particular files.
Event Streams Improvements
Ignition 8.3.5 adds tooltips to each stage of an Event Stream’s data to provide you with additional context. These tooltips display upon hovering over element subtext, and update dynamically as real-time values change.
And there’s more to discover on their website.
by Gary Mintchell | Apr 27, 2026 | Manufacturing IT, Software
I had an opportunity to talk with long-time business colleague Juliann Grant at the recent Aras Community Event in Miami. She is Marketing VP at digital engineering firm Razorleaf. She’s been a great source of PLM market insight. She told me about a podcast she hosts. Stay Sharp in Digital Engineering presented by Razorleaf, is a brisk conversational look at news and technology in the space. The linked episode will improve your understanding of AI agents with Razorleaf and Diego Tamburini of CIMData.
I highly recommend both this episode and the series. You can subscribe on your favorite podcast source or on YouTube.
by Gary Mintchell | Apr 21, 2026 | Data Management, Generative AI, Manufacturing IT, Podcast, Software
I’ve posted a podcast to both my podcast channel (subscribe on any podcast app) and my YouTube channel.
A first summary of my three days with the Aras community in Miami. These PLM events always return me to the time when I did this sort of work–manually. Then my first taste of computers digitizing the bill of materials as a first step in our data management journey. Unfortunately, that company hit a big bump in the road and I was invited to try other things–at other companies.
Aras product managers showed how LLMs trained on the data within the app along with proper governance worked with agents to perform a number of tasks. Tasks in many cases that would require days of pain-staking work from a human.
While I heard from an analyst in the market that they thought this was all painfully slow, I’d offer the thought that a company does not want to outpace its customers. Most will not want to jump into the deep end immediately.
As always, this podcast was sponsored by Ignition from Inductive Automation.
by Gary Mintchell | Mar 26, 2026 | Generative AI, Process Control, Software
TwinThread is one of those smallish software companies within an interesting niche that I can’t believe has yet to find a buyer. I quoted noted software developer and LinkedIn commentator Rick Bullota in 2020 extolling the value of the AVEVA/TwinThread link with the AVEVA purchase of OSIsoft. Just last year, I wrote about a stronger partnership between the two.
I see the company has pivoted a bit to now proclaiming itself as “the world’s first to have a complete Industrial AI platform.” I’ll leave that proclamation to your judgement. But this product looks worthwhile to check out.
Last week’s news involved TwinThread releasing an AI-powered manufacturing analytics solution targeting batch processes called Perfect Batch. This product empowers manufacturers to standardize and consistently replicate their best performing or “golden batches”.
Perfect Batch applies industrial AI to dynamically identify ideal batch profiles from historical data and actively recommend actions for increasing efficiency. This enables organizations to rapidly shift from reactive firefighting to proactive optimization in a matter of weeks – not months or years.
Perfect Batch At-a-Glance:
- Rapid Speed to Value: Perfect Batch connects to existing batch execution systems and automatically interrogates past data to build digital twins and apply models in hours.
- Dynamic Perfect Profile Learning: Instead of setting limits manually, Perfect Batch dynamically learns ideal control limits and process centerlines, based on actual process capability and historical performance.
- Unlocked Hidden Capacity: Granular cycle time analysis identifies bottlenecks and lost production time, facilitating capacity improvements from existing assets without new capital investment.
- Optimization by Exception: Automated alerting and issue diagnosis empowers operations teams to focus on solving problems, without getting bogged down with endless troubleshooting and investigations.
- Optional Closed-Loop Action: Thread Builder, a real-time workflow engine that works with Perfect Batch, automates anomaly responses, performs automatic diagnoses, and can trigger specific corrective actions automatically.
- Automated Compliance: Tailored for regulated industries, Perfect Batch provides automated material tracking, quality and yield conformance, and audit-ready histories.
Beyond the plant floor, Perfect Batch helps drive strategic and collaborative alignment across organizations’ entire manufacturing portfolios by providing a global view of asset utilization and batch making performance. As a result, the platform serves as a single source of truth for cross-functional teams. This offers a common lens that operations teams, engineering teams, and supply chain leaders can all use to identify, prioritize, and proactively execute improvement initiatives that optimize the deployment of capital across the supply network.
Click on the Follow button at the bottom of the page to subscribe to a weekly email update of posts. Click on the mail icon to subscribe to additional email thoughts.
by Gary Mintchell | Mar 19, 2026 | Generative AI, Software
Notes and news about AI continue to build in my pending folder. Too many to figure out. I’ll start with this one. I saw this news item from Morning Brew, one of my daily news feeds…The AI…it filled the code with bugs.
The amount of bugs popping up in AI-generated code is reaching the loose Sour Patch Kids under a camper’s bunk level. Amazon’s e-commerce senior VP, Dave Treadwell, called an all-hands for engineers at the company yesterday to address the growing frequency of outages, some of which can be traced back to code developed by generative AI, according to the Financial Times.
It continues…
- Last week, Amazon’s store malfunctioned for a few hours, which the company attributed to “a software code deployment.”
- And Amazon’s cloud services unit, AWS, had at least two large outages recently related to AI coding assistants. In December, the company’s cost calculator was down for 13 hours when Kiro, its AI coding tool, tried to change the code, and delete and remake the entire system.
- Though Amazon downplayed the meeting as routine in comments to the FT, the paper reported that Treadwell told employees that senior engineers will now need to sign off on AI-assisted changes made by junior and mid-level engineers.
Solutions?
An expensive solution. Anthropic rolled out a review tool yesterday in Claude Code to (hopefully) catch those vibe-coded mistakes—but with each pull request costing up to $25, it may get pricey fast.
Concurrently with this news, I received a PR request to interview Pramin Pradeep, CEO of BotGauge AI. I receive this sort of thing many times daily. Supposedly, Pradeep wanted to talk about “shadow code” left behind, supposedly maliciously, by AI generated code.
I asked for something in writing. They sent the usual PR thing that mentions shadow code but switches the topic to cybersecurity and then cites an irrelevant “case study”.
However, BotGaugeAI does participate in a market (Claude told me they were 20 out of 128 in that market for what it’s worth) called AI-assisted QA for code.
My research revealed that the basic problem comes from where the LLM AI code was trained. If trained too broadly, it will tend to being in superfluous code. Managers, meanwhile, are discovering that while maybe coders can save time in development using LLMs the task of checking and approving is becoming onerous.
If you’re using LLMs to help code, it would probably pay to check out the companies like BotGaugeAI for automated QA.
Click on the Follow button at the bottom of the page to subscribe to a weekly email update of posts. Click on the mail icon to subscribe to additional email thoughts.
