TechSoft
Playbook menu: Stage 3: Build with AI

Delivery Playbook · Lifecycle

Stage 3: Build with AI

Deliver working software in small, reviewed steps. AI helps; people stay responsible for the result.

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

Goal: Deliver working software in small, reviewed increments.

What happens

  • Sprint planning and daily sync
  • Implementation with AI assistance under review
  • Peer review of every change
  • Continuous integration with automated tests and scans
  • Sprint demo and retrospective

What you receive

  • Working increments in a shared environment
  • Automated tests
  • Updated documentation
  • Sprint report

Quality checks

  • Peer review of every change, including AI-assisted ones
  • Automated tests, static analysis and dependency checks in the pipeline
  • Each story meets the definition of done

Approved before we move on

Each story meets the definition of done; the increment is demonstrated to the client.

Who is involved

  • Client Sponsor
  • Delivery Manager · leads
  • UX/UI Designer
  • Tech Lead / Architect · leads
  • Software Engineers · leads
  • QA / Test Automation
  • DevOps / Platform
  • CTO · leads
  • Support & Operations

How a one-week sprint works

MonTueWedThuFriONE-WEEK SPRINTDaily sync (15 min)Backlog refinementPlanning / reviewReleaseStatus reportBuild, test, integrateRefine next weekPlanningReview + retroReleaseWeekly reportReviewed changes merge continuously; checks run on every change
A one-week sprint: with AI-assisted engineering we plan, build and release every week. Length and days can be adapted per engagement.

How a change moves

  1. 1

    Pick up a ready story

    The engineer takes the next story that meets the definition of ready and checks the business context with the client's team if needed.

  2. 2

    Implement with AI assistance

    AI tools may draft code and tests under the AI-use policy. The engineer understands every line.

  3. 3

    Test and self-review

    Automated tests are written or updated; the engineer reviews their own diff before asking others.

  4. 4

    Peer review

    Another engineer reviews. Changes touching architecture, security or data are reviewed by the Tech Lead or the CTO.

  5. 5

    Merge through the pipeline

    CI runs tests, static analysis and dependency checks. Failing checks block the merge.

  6. 6

    Demo and release

    At the end of the one-week sprint the team shows working software to the client, collects feedback and releases what has passed the gates.

= milestone agreed with the client

  1. 01

    Discover

    Problem and baseline

  2. 02

    Design

    Architecture and scope

  3. 03

    Build with AI

    Reviewed increments

  4. 04

    Verify

    Gates and acceptance

  5. 05

    Operate & improve

    Monitor and learn

Measure outcomes, learn, and feed the next increment
Each stage ends with a milestone agreed with the client. What we learn in Operate feeds the next round of Discover.

Related