TechSoft
Playbook menu: AI engineering

Delivery Playbook · Quality & AI

AI engineering

How AI supports the whole engineering workflow, who is responsible for what, and the rules that keep it safe.

Owner: CTO · Last reviewed: · Next review: 28 April 2027

AI tools make good engineers faster. They also make it easier to produce code nobody understands. Our approach keeps the speed and keeps people accountable for what ships. We want to be paid for results, not for typing.

Three levels of AI adoption

Level 1 · Where it starts

AI-assisted engineering

Individual engineers use approved AI tools to speed up specific tasks, such as drafting code and tests, explaining unfamiliar code or summarizing requirements. The engineer reviews and owns the result.

Level 2 · Where we are building toward

AI-orchestrated delivery

Controlled AI-agent workflows handle bounded engineering tasks, for example a refactor or a test suite. Each has defined permissions, automated verification and clear rules for when to stop and ask a person.

Level 3 · The longer-term direction

AI-enabled operations

AI helps monitor running systems, diagnose incidents, spot recurring defects and technical debt, and suggest improvements. People decide what changes in production.

These are capabilities and working patterns we apply step by step, agreed with each client. They are not a claim that every capability is already in use on every project.

Where AI helps across the workflow

AI can support the whole engineering workflow, not only code writing. In every case a person stays responsible for the result.

ActivityWhat AI can doWhat stays with people
Requirements analysis and clarificationSummarizes notes, spots gaps and conflicts, drafts questions and acceptance criteriaDesigner, Tech Lead and client confirm what is actually needed
Architecture explorationLays out options and trade-offs, drafts diagramsTech Lead decides and records the decision
Code generation and modificationDrafts and changes code in small stepsEngineer reads, understands and owns every change
Automated test generationProposes test cases, data and edge casesEngineers check that tests fail when the code is wrong
Code review assistanceFlags common defects, risky patterns and missing testsA human reviewer approves the change
DocumentationDrafts docs, release notes and runbooks from the code and ticketsOwners check accuracy before publishing
Legacy-code analysis and modernizationExplains old code, maps dependencies, suggests refactors and test coverageArchitect decides the approach; tests protect existing behavior
Defect investigationTraces likely causes from logs, code and recent changesEngineer confirms the cause and the fix
Production incident analysisCorrelates alerts and logs, summarizes timelines and drafts post-incident notesOn-call engineers decide and act; consequential changes are approved by a person
Technical debt identificationFinds duplication, outdated dependencies and hotspotsTech Lead and client agree what to fix and when

Who does what

AI

Generates, analyzes, summarizes and recommends

Never approves, accepts or releases anything.

Engineers

Review, validate, understand and own changes

If an engineer cannot explain it, it does not ship.

Automated controls

Test, scan, validate and enforce defined policies

Failing checks block the merge or the release.

Human decision-makers

Approve architecture, security exceptions, releases and consequential production changes

Named people, recorded decisions.

Engineering taskClient secrets orregulated data?NoArchitecture, securityor business decision?NoAI may draft or assistYesOnly an approved tool, only if the policy allows; otherwise no AIYesHuman decides; AI may informEngineer reviews, tests and owns itMerged only through the pipeline, after review and passing checks
The default is a human decision. AI is used where it is allowed by the engagement's AI-use policy.

Confidentiality, access and data handling

Your code and data are yours. These are the rules we follow, and we confirm the details in the engagement's AI-use policy at kickoff.

Client code and data

Agreed at kickoff in the engagement's AI-use policy. Only approved tools touch client code or data.

Access control

AI tools and agents get the minimum access they need, on specific repositories and environments, and nothing more.

Secrets and regulated data

Credentials, secrets and regulated data stay out of AI tools unless the policy explicitly allows it.

Auditability

Changes live in version control with the author, the reviewer and the checks that ran. We record when AI assisted a change where the policy requires it.

Human approval

Architecture, security exceptions, releases and consequential production changes are approved by named people.

Tool terms

Each AI tool has its own data-retention and training terms. We check them before approving a tool, and we tell you which tools we use. We do not promise anything beyond what a tool's terms and our controls support.

Rules we follow

  • Only tools approved in the engagement's AI-use policy are used on client code or data
  • No secrets, credentials or regulated data are placed in AI tools unless the policy explicitly allows it
  • Every AI-assisted change is reviewed by a human engineer who understands it
  • AI-generated tests are checked to ensure they fail when the code is wrong
  • We tell clients how we use AI on their project, at kickoff and on request
  • We review in retrospectives how AI affects quality and speed, and adjust

Responsibilities by role

RoleResponsibility for AI use
Client SponsorAgrees which tools may touch their code and data
Delivery ManagerMakes sure the policy is followed and visible
Tech LeadSets where AI-generated code is acceptable and how it is reviewed
EngineersUnderstand, test and own every change they commit
QAApplies extra scrutiny to AI-assisted changes
CTODefines approved tools and data-handling rules, and is accountable for the behavior of AI features delivered to the client

Related