Solutions · Use cases

Coding

Build, review and maintain software faster.

Coding assistants help developers write, explain, test and review code. For many teams they are the fastest AI win, and also a place where source code and secrets can leave the organisation without anyone noticing.

01 / Where AI helps

Opportunities

Code completion and generation

Faster first drafts of routine code, tests and documentation.

Legacy modernisation

Explain old code, map dependencies and help plan migrations.

Review support

A second reader that flags likely bugs and security issues before a human review.

02 / Australian rules to check

What to get right

Source code confidentiality

Code, configuration and secrets sent to a hosted assistant leave your network. Check the provider's retention and training terms, and never paste credentials.

Secure development

Generated code needs the same review, testing and dependency checks as human code. ASD's Essential Eight and ISM controls still apply to what you ship.

Licensing

Check the licence of any open weight model you run, and keep your normal process for open source code that appears in suggestions.

This is general information, not legal advice. See our Australian AI compliance guide for the wider landscape and links to official sources.

03 / Getting started

Where to run it

Open weight coding models now run well on a single workstation GPU for small teams, which keeps source code in house. Larger teams can share one inference server behind their existing single sign on.

First steps

  1. Write a short policy on what code and data may be shared with which tools.
  2. Pilot with one team and track review findings, not just speed.
  3. Add secret scanning to catch credentials before they reach any tool.

Related guides