During my time as Head of Professional Services for a private Genomics based company I spearheaded an initiative to utilise an open source offline LLM for analysing our Jira, Confluence and Salesforce docs for quick retrieval of process and technical information.

The purpose was twofold,

a) To create a common ‘search’ tool in order to locate a source of truth as to what was configured and where, and

b) To be able to generate process documents very quickly in whole or in part through the use of generative AI.

As these were sensitive company documents, use of a service like ChatGPT was restricted, which is why we opted to trial PrivateGPT with Llama-2-7b amongst other models.

We found RAG to be less than perfect, but it did effectively allow us to search out the right documents. Text generation was better in that we managed to produce good content as an initial template for a process guides, as well as feeding a full process document to generate a RASCI chart. We ran the pilot service on AWS EC2 infrastruture.

The post RAG with Offline LLM appeared first on fitzmoskal.

This script I wrote essentially takes a python version or an ansible version and will loop through checking out each branch then printout which versions of Kubespray are supported.

The post Kubespray Dependencies appeared first on fitzmoskal.

The post Egyptian Genomics Institute – Software Delivery appeared first on fitzmoskal.

As Head of Professional Services I took over responsibility for a number of software integrations written by a bioinformatics consultant who had previously left the company. One of these integrations was supplied to a parnter organisation and had been reported to have an undetected design flaw which raised a ‘highest severity’ ticket. No-one in my team was familiar with the code, so I had to reach out and coordinate with DevOps and Engineering for assistance.

Through bargaining and persistance I secured some time of one of the lead bioinformaticians to take a look at the code, review the clients requirements and make the changes. This was the easiest part – I recognised the issue with the code myself, but as I wouldn’t understand the genomics interpretation part, I did not want to make edits myself. The second part of the issue was with clinical decisions that had already been made with the flawed code. There was little that I could do here, but it was down to me to make sure that the right resources were aware and assigned to figure out which decisions had been impacted to report back to the client.

The code fix was done within SLAs, finding the impacted clinical decisions took longer. My final action was to ensure that the application was correctly documented for future support and ensure that the client sign off on the new implementation of the code (to ensure that there is record of agreement that it now worked as expected – which was missing before).

I was also engaged with this partner through organising a resource to work on custom reporting, using a combination of python and flask. I acted as liaison and project manager with the customer ensuring that the code was developed to specification and that milestones for delivery, test and sign off were met.

The post NHS Genomics Partner – Integrations & Software Development appeared first on fitzmoskal.

I was asked to provide a health check with insights into the clients Discovery operations. I created a custom application called Pithos – a python-based application which collected data from CMDB and Discovery. This data was then imported into Power BI and we were able to present the following back to the client:

• High disk utilisation
• Presence of core dumps
• Segregated architecture, but no network segregation
• Sensitive data such as plaintext usernames and passwords stored in unstructured data fields
• Scan schedules impacting performance

This was followed up with a roadmap of improvements for the client with the option of being delivered by my company.

The post US Retailer – DevOps appeared first on fitzmoskal.

I worked with presales to deliver a $55k project with insights into the clients Discovery operations created with Pithos – a custom built python-based application which collected data from CMDB and Discovery. This data was then imported into Power BI and we were able to present the following back to the client:

• Sensitive data filters not capturing plaintext username/password
• Under-specced Outpost sizes causing performance issues
• Active user accounts from departed users not removed
• Various data quality issues
• Configuration discrepencies between prod and dev environments

This was followed up with a roadmap of improvements for the client which included development of a runbook, and 10 consultancy days of remediation.

The post UK Pharmaceutical – DevOps appeared first on fitzmoskal.

I worked in presales to present insights into their ITSM operations gathered from Talos back to the client. My involvement was in data cleansing and preparation for injesting into Talos for supervised and unsupervised learning. Once Talos had created the reports, I would then import these to PowerBI to develop the insights. With AI we were able to identify:

• Issue candidates for automation e.g. “password reset”
• Lack of categorisation and service catalogue, poor summaries written in tickets
• 3rd party structured automation information posted into notes fields
• Categorical data located in unstructured notes fields
• Under-utilisation of knowledge
• Change requests logged as tickets leading to high level of tickets with low MTTR
• High level of critical abnormalities requiring problem RCA
• General lack of granularity in categories, impacting management reporting

This was followed up with an offer to the client to deliver the recommendations such as service desk training, restructuring categories, data cleansing, and knowledgebase improvements

The post Healthcare Company – AIOps appeared first on fitzmoskal.

I worked with this German company to enhance their Discovery and CMDB with various storage metadata and data from unsupported storage systems. I wrote extensive TPL code which integrated with APIs for NetApp, Dell Isilon, IBM Spetrum, and Nasuni.

For Nasuni I had to develop the whole model using data extracted from the APIs to model the Management Console, Volumes and Shares.

The outcome of this project was to allow the client to accurately track storage usage and billing.

During this time I also assisted the client in troubleshooting Azure discovery and retrieving additional matadata from VMware.

The post German Car Systems Maker – Storage Integration appeared first on fitzmoskal.

I was technical lead on a project worth $40k to implement the Helix Discovery SaaS solution. Since scanning hybrid infrastructure requires on-prem components there was still substantial Solution Design work required.

At this time the SaaS product was less than 18 months old and there were gaps in features and functionality in how it worked compared to the on-prem version. This led to challenges with unkown behaviour and bugs in the collector/outpost components which had to be resolved whilst maintaining client confidence in the solution they had bought.

An example challenge was in deploying shared outposts (documented as supported) between prod and dev SaaS instances. During deployment, an update was made to prod which delivered a change in key management to the outpost, and caused it to stop communicating with dev. The issue was resolved a week later when dev was updated, however it did mean that future architecture had to be updated to avoid this type of issue. Thankfully it did not impact delivery of the project.

The customer was also given value added data quality reporting allowing them to identify various gaps and misconfiguration across their estate.

The post UK Non-Profit Organisation – SaaS Solution appeared first on fitzmoskal.

As part of a larger digital transformation I was responsible for the architecture of their Discovery, modelling application architecture and data integration pipelines to the CMDB.

The initial deployment was minimal and did not cover the whole estate, which was airgapped. I was challenged to come up with an architecture which would be suitable enough capture data across the airgapped environments. The proposed solution involved manual DB snapshots which would be transferred by ftp, however this was later dropped in favour of deployment of a mutual shared platform, which was desperately needed.

This was a part-time multi-year engagement, during this time I developed and delivered various customatisations to their data collection and pipeline, such as:

• SSL Certificate Discovery
• Netcool edge device intergration
• Service modelling
• Reporting and analytics
• Written maintenance manual

The post UK Telecoms Company – Digital Transformation appeared first on fitzmoskal.