Highlights
- +89% engineering delivery output — merged pull requests across all repos, while freeing the team to focus on higher-value work
- −81% human-reported bugs — down to a full-year low, while output nearly doubled
- 2× code-review throughput — reviewers absorbed double the PR volume with zero added latency, including dedicated security review
- Claude Code across the entire lifecycle — 47 custom skills, 6 subagents, and 19 slash commands turning team conventions into governed, reusable workflows
- Precisely scoped releases — regression testing targets only what changed and what’s deployed, with release cuts computed and confirmed at hard gates
- Continuous, automated incident response — production errors are triaged and resolved on an ongoing basis, read-only and security-conscious, with the large majority of issues already closed
- 10× growth in AI operations in a single month, with a 92% autonomous-run success rate
Client
Space Needle – Seattle’s iconic observation tower and one of the most recognizable tourist attractions in the United States. SPD Technology serves as its primary software engineering partner and staff-augmentation engineering team.
Product
Space Needle Ticketing is a guest-admission and venue-ticketing platform built on a single codebase that covers the platform’s backend, customer-facing applications, test suite, and infrastructure.
The platform supports ticket sales and guest admission, making software reliability, security, and development velocity important not only to engineering operations but also to the visitor experience.
Goals and objectives
Space Needle and SPD Technology set out to explore how AI could augment the existing engineering team across the software lifecycle while maintaining human oversight and established quality and security controls.
The initiative focused on:
- Codifying engineering conventions into reusable workflows rather than relying on tribal knowledge.
- Keeping code review, including security review, ahead of rising PR volume.
- Keeping technical documentation and specifications aligned with the evolving codebase.
- Accelerating testing and design-to-UI development.
- Making regression testing and release preparation more precise and repeatable.
- Reducing time spent on routine operational work and production investigation.
- Translating engineering efficiency into faster improvements and a more reliable digital experience for Space Needle guests.
Project challenge
As the ticketing platform evolved, the engineering team faced increasing complexity across both development and operations.
Engineering conventions and knowledge were distributed across the team, while growing development activity increased the amount of code requiring review and testing. As PR volume grew, the team needed review capacity to scale with it. Documentation had to keep pace with frequent changes, and translating designs into production-ready interfaces remained largely manual.
Beyond development itself, release and production operations introduced additional friction. Regression scope could be difficult to determine precisely, release preparation involved manually reconciling multiple sources of information, and production incident investigation required engineers to balance rapid diagnosis with strict controls around system access.
The challenge was therefore broader than simply making developers write code faster. Space Needle and SPD Technology needed a way to increase engineering capacity while preserving human judgment, security controls, and software quality.
Solution
SPD Technology embedded Claude Code into the engineering workflow as an assistive layer spanning development, quality assurance, releases, and production operations.
AI-assisted development and engineering standards
SPD codified the team’s established engineering practices into 47 custom skills, 6 subagents, and 19 slash commands, turning conventions that previously depended on individual knowledge into reusable workflows.
Feature and bug-fix workflows use phased review gates and stop before PR creation, ensuring engineers remain responsible for reviewing and approving changes.
Code and security review
Claude-assisted review provides an additional quality layer before human review.
Dedicated workflows support code review, security checks, and re-evaluation of open PR discussions against the latest version of the code.
This allows AI to help engineers identify potential issues earlier while human reviewers retain final responsibility for approving changes.
Living documentation
Ten documentation-audit skills help keep CLAUDE.md, specifications, and the project knowledge base aligned with the codebase.
Automated verification identifies potential discrepancies between documentation and implementation so engineers can address them as the platform evolves.
AI-assisted testing
Playwright and AQA authoring workflows help engineers create and maintain automated tests.
Additional test-fidelity controls are designed to identify weakened assertions, skipped checks, and other situations where an AI-generated test could appear successful without adequately validating functionality.
Release and regression management
AI-assisted regression analysis compares release changes with what is actually deployed, maps those changes to affected business modules, considers feature-flag state, and generates a prioritized regression scope.
Release-cut automation similarly brings together ticket and source-control information to identify the appropriate release commit and potential blockers.
Remote-facing actions remain protected by explicit human confirmation gates.
Production incident investigation
Read-only production investigation tooling helps analyze production errors and turn previously unstructured monitoring signals into actionable engineering work.
The approach gives engineers faster access to diagnostic information without giving AI unrestricted authority over production systems.
AI operations orchestration
SPD has also developed a Jira- and Slack-triggered AI Agent Orchestrator designed to assist with routine engineering and operational workflows.
Guardrails prevent unsupervised production actions, keeping engineers in control while allowing repetitive work to be handled more efficiently.
Regression-scope analysis, release-cut automation and incident investigation are live; the AI Agent Orchestrator is in final rollout.
Technologies Used: Claude Code (custom skills, subagents, slash commands); cloud CI/CD pipelines with PR validation and branch policies; automated end-to-end testing; issue-tracking and team-messaging integrations; production monitoring; CLAUDE.md, behaviour specifications, and a project knowledge base; dependency graph, feature matrix, feature flags; dedicated AI-agent infrastructure.
Results
The implementation is designed to improve engineering performance without removing human oversight from development, release, or production decisions. The gains this produced in day-to-day development work translated into tangible operational benefits for the Space Needle as a client — and ultimately, into a faster, more reliable experience for guests using the Space Needle’s ticketing platform.
Delivery & quality (2026 vs. a flat 2025 baseline, at constant headcount)
- +89% engineering delivery output (merged pull requests across all repos)
- 2× code-review throughput (reviewers absorbed double the PR volume with zero added latency)
- −81% human-reported bugs (down to a full-year low, while output nearly doubled)
- 6 platform-scale initiatives shipped concurrently (monorepo, CI, IaC, test suite, BDD specs, full documentation)
This growth in delivery and review capacity came while freeing the team to focus on higher-value engineering work, with every release still reviewed and confirmed by the team at each step before it ships.
Operational performance (measured monthly volumes, August 2026)
- 10× AI operations scale in a single month (from 38 pipeline runs in July to 443 in August)
- 92% autonomous-run success rate at production volume
- Production error triage is now continuous and automated, with the large majority of previously untriaged alerts already closed
- Production incidents are now investigated as they happen — a capability the team didn’t have before
Incident investigation is now a continuous, read-only stream rather than an on-demand manual task, keeping security exposure low while returning developer time to higher-value work.
For guests, this means problems are caught and addressed before they become visible, fixes happen faster, and updates are safer and more reliable — resulting in a smoother, more stable experience overall.