Software Development

Our high performance development teams hit the ground running working with your stakeholders to deliver working software every two weeks.

We’re able to deliver working software through our unique Way of Work that’s backed by world-class governance that enables increased control and transparency over development processes.

Our approach is the product of years of research and decades of experience.

Our Application Development Offering is:

Technology Agnostic

We can create solutions in almost any technology stack you pick. Or if you don't know what to choose, our consultants can architect your solution

Scalable

Need more resources? We can easily deploy teams backed by our unique Way of Work that enables them to hit the ground running

Transparent

Our governance processes put you firmly in the drivers seat, giving you control over priorities for each two week sprint

Development

Development as a Service

Developing working applications requires more than just developers - it requires teams of skilled individuals who are working with a common framework and methodology. 


Our Way of Work means that we deploy small multi-disciplinary teams of five into client organisations to deliver working software in two week sprints. 


They’re autonomous and work quickly to remove roadblocks towards a clear objective that we define with you. Critically, our teams have worked together and are skilled at using our Way of Work to turn your requirements into working software.

GET IN TOUCH

Testing

Automated Testing

We integrate automated testing into development process to ensure that when we deploy into our customers target environment, we’re deploying working software – every time. 


Our testing process is highly visible, with our team generating regular reporting on test results as part of their development process. 

GET IN TOUCH

Deployment

Deployment Approach

Adopting a Continuous Integration/Continuous Deployment (CI/CD) approach means that we’re focused on making incremental code changes frequently and reliably. 


The end result of this is that our clients get to see a demonstration of their working software, in their target environment, at the end of every sprint.

GET IN TOUCH

Governance

Governance Frameworks

Our unique governance framework gives clients transparency over the work to be done in each and every two week sprint, through the client signing off on individual user stories for each project.


Approving individual stories gives clients the flexibility to prioritise features as a project is built, and for stakeholders to provide feedback on the project as it goes through regular showcases.

GET IN TOUCH

Case Studies

We're extremely proud of the work we complete for each and every client.

From enterprise clients all the way through to small businesses and startups, our focus has always been on providing positive results in the most efficient way possible. Our Way of Working paves the way for successful outcomes for each project.

SEE CASE STUDY

Our Latest Thinking

Prompt Injection Capture-the-flag – Red Team x AI

By Joe Cooney • 02 Apr, 2024
Red-team challenges have been a fun activity for PZ team members in the past, so we recently conducted a small challenge at our fortnightly brown-bag session, focusing on the burgeoning topic of prompt injection. Injection vulnerabilities all follow the same basic pattern – un-trusted input is inadvertently treated as executable code, causing the security of the system to be compromised. SQL injection (SQLi) and cross-site scripting (XSS) are probably two of the best-known variants, but other technologies are also susceptible. Does anyone remember XPath injection? As generative models get incorporated into more products, user input can be used to subvert the model. This can lead to the model revealing its system prompt or other trade secrets, reveal information about the model itself which may be commercially valuable, subvert or waste computation resources, perform unintended actions if the model is hooked up to APIs, or cause reputational damage to the company if the model can be coerced into doing amusing or inappropriate things. As an example, entrepreneur and technologist Chris Bakke was recently able to trick a Chevy dealership’s ChatGPT-powered bot into agreeing to sell him a Chevy Tahoe for $1 . Although the U.S. supreme court has yet to rule on the legal validity of a “no takesies backsies” contract (as an employee of X Chris is probably legally obligated to drive a Tesla anyway) it is not hard to imagine a future scenario with steeper financial consequences.

Five Key Areas for AI Disruption in Insurance

27 Feb, 2024
With the advent of ChatGPT, Bard/Gemini and Co-pilot, Generative AI, and Large Language Models (LLMs) have been thrust into the spotlight. AI is set to disrupt all industries, especially those that are predominately based on administrative support, legal, business, and financial operations, much like insurance and financial organisations.

Running AI locally when GPT-4 goes crazy

By Joe Cooney • 22 Feb, 2024
One of the features of life working at PZ is our brown bag lunch and learn sessions; presentations by staff on topics of interest – sometimes, but not always technical, and hopefully amusing-as-hell. Yesterday we took a break from discussing the book Accelerate and the DORA metrics to take a whirlwind tour of the current state of play running “open source” generative AI models locally. Although this talk had been ‘in the works’ for a while, one challenge was that it needed to constantly be revised as the state of AI and LLMs changed. For example, the Stable Video Diffusion examples looked kind of lame in comparison to OpenAI’s Sora videos (released less than a week ago) and Groq’s amazing 500 token-per-second hardware demo on Monday/Tuesday , and the massive context size available now in the Gemini 1.5 models (released a few hours before OpenAI announced Sora...coincidence? An effort by OpenAI to steal back the limelight! Surely NOT!). And now a day later, with the paint still drying on a highly amusing slide-deck for the talk, Google releases their “open-source" Gemma models! The day itself presented an excellent example of why having more control of your models might be a good thing. ChatGPT 4 users began reporting “crazy” and highly amusing responses to fairly normal questions . We became alerted to this when one of our own staff reported on our internal Slack about a crazy response she received to a question about the pros and cons of some API design choices. The response she got back started normally enough, but then began to seem to channel Shakespeare’s Macbeth and some other olde English phrases and finished thusly. "Choose the right charm from the box* dense or astray, it’ll call for the norm. Your batch is yours to halter or belt. When in fetch, marry the clue to the pintle, and for the after, the wood-wand’s twist'll warn it. A past to wend and a feathered rite to tend. May the gulch be bygones and the wrath eased. So set your content to the cast, with the seal, a string or trove, well-deep. A good script to set a good cast. Good health and steady wind!" The sample JSON payload was also in keeping with the rest of the answer. { "htmlContent": "

Your HTML here

", "metadata": { "modifiedBy": "witch-of-the-wood", "safety": "sanitized", "mood": "lunar" } } Hubble, bubble, toil and trouble. Although there were no reports of the GPT4 API being affected by this (only ChatGPT) it might have given people developing automated stock trading bots using GPT4 a reason to pause and contemplate what might have been if their stock portfolio now consisted of a massive long position on Griselda’s Cauldron Supplies. As ChatGPT would say, Good health and steady wind.
SHOW MORE
Share by: