Using AI coding assistants and agents responsibly
A ready-made course you customise for your organisation, with a live session deck and two surveys. You only add the 9 details that are specific to your organisation.
- Length
- 40 min
- Lessons
- 6 lessons
- Frequency
- When an AI coding assistant or agent is rolled out
- Last reviewed
- 21 Oct 2026
A developer pastes a production error log with customer emails into a public assistant
Try it: this is one of 16 interactive activities in the course.
What's included
Three pieces that work together
Copy once, get everything. Learners prepare on their own, you answer questions live, and the surveys tell you what stuck.
Self-paced course
Short lessons with real workplace scenarios, not walls of text.
- 6 lessons, about 40 minutes
- Sorting activity, scenario, process, timeline and quizzes
Live session deck
An AhaSlides presentation to run after the course, in person or online.
- 10 slides
- Quiz, poll, ranking, word cloud slides
- A closing slide for your contacts
Two surveys
Find out what landed, and whether people use it on the job.
- Post-course feedback, about 2 minutes
- 30-day check-in
- Anonymous by default
- Results feed your next refresher
Learning objectives
At the end of this course, learners can
Each objective and the lesson that covers it.
| ID | Objective | Source | Where it's covered |
|---|---|---|---|
| TO 346.0 | Achieve ≥ 80% on the final assessment | - | Whole course |
| SO 346.1 | Describe what coding assistants and agents do well and where they fail | Best practice | Whole course |
| SO 346.2 | Decide what code and data may be put into a prompt | Organisation's AI acceptable-use policy; ISO/IEC 42001:2023 (voluntary) | Whole course |
| SO 346.3 | Review AI-written code for correctness, security and licence risk before merging | Best practice; NIST AI RMF 1.0 (voluntary) | Whole course |
| SO 346.4 | Keep secrets, personal data and licensed code out of prompts and out of the repository | Organisation's security policy | Whole course |
| SO 346.5 | Record AI use for traceability and follow team AI coding rules + your info | EU AI Act Art. 4 AI literacy [check before build]; organisation rules | Whole course |
Your part: what a template can't do for you
- Your workplace details: fill in the 9 highlighted fields so the course describes your own policies, contacts and locations.
- Records: record completion in your own LMS or record system.
Course outline
6 lessons, about 40 minutes
Minutes per lesson are an estimate, shared out by page count.
1The pull request nobody understood
3 pages
8 min
The pull request nobody understood
3 pages
2What assistants and agents do well and badly
3 pages
8 min
What assistants and agents do well and badly
3 pages
3What code and data may go into a prompt
2 pages
5 min
What code and data may go into a prompt
2 pages
4Reviewing AI-written code
3 pages
7 min
Reviewing AI-written code
3 pages
5Licences, secrets and traceability
3 pages
7 min
Licences, secrets and traceability
3 pages
6Your team's AI coding rules and final assessment
2 pages
5 min
Your team's AI coding rules and final assessment
2 pages
Live deck and surveys
10 slides to run live, two surveys to close the loop
Pink slides are interactive. Both surveys are anonymous; pink questions are written for this course.
Post-course feedback: 11 questions, about 2 min
- Overall rating 5 stars
- Relevant, realistic, right length, helpful activities agree/disagree grid
- What was most useful? multi-select
- Confidence before this course, and now 1-5 scale
- Confidence in prompt data rules · review · licences · secrets · record keeping grid
- Which AI tools do you use for code? multiple choice
- What rule about AI in code is unclear to you? short text
- I can say ‘I pasted something I should not have’ without feeling judged. 1-5 scale
- One thing we should change or add open text
- Would you recommend this course? NPS
30-day check-in
- Have you used what you learned since the course? multiple choice
- How confident are you today? Compare with day 1 1-5 scale
- Do you know where to find the AI coding rules and approved tools list? yes / no / not sure
- A moment where the training helped, or where you weren't sure open text
- Which topics should the next refresher focus on? ranking
Results show whether people use the training on the job, not just whether they finished it.
Make it yours
9 fields to fill in, and you're ready
Everything else is done. These are the details only your organisation knows; each one is highlighted inside the course.
- Link to the data classification policy
{{DATA_CLASSIFICATION_POLICY_LINK}} - Link to the team AI coding rules
{{AI_CODING_RULES_LINK}} - Security team contact
{{SECURITY_CONTACT}} - List of approved tools and versions
{{APPROVED_TOOLS}} - Who to ask for help or to report a concern
{{HELP_CONTACT}} - Where completion is recorded
{{LMS_OR_RECORD_SYSTEM}}
Show all 9 fields
- Link to the post-course and 30-day survey
{{SURVEY_2_URL}} - Link to the self-paced course
{{COURSE_URL}} - Link to the baseline survey
{{SURVEY_1_URL}}
FAQ
Common questions
Can I run using AI coding assistants and agents responsibly training online?
Yes. The course is self-paced and online, and the live deck lets you add a live session in the room or online.
How often is this training needed?
When an AI coding assistant or agent is rolled out, and at developer onboarding.
Who needs this training?
All developers and the team leads who set AI usage rules for code; run by engineering managers with L&D.
What records should I keep?
Record completion in your own LMS or record system, so you can show who finished the course and when.
Can I edit the content?
Yes, everything. Change the wording, swap scenarios for ones from your workplace, add your logo, or remove parts that don't apply.
Related templates
Often taught together
Secure coding fundamentals: OWASP top 10, input validation and least privilege
Developers on web and back-end teams · Secure and responsible coding
Memory-safe c and c++ to CERT and MISRA standards
C and C++ developers · Secure and responsible coding
Concurrency safety: Threads, locks and race conditions
Back-end developers and systems engineers · Secure and responsible coding
Ready to run it?
Open the live deck to see how the session runs alongside the course and both surveys.