Highlights
- +89% engineering output at the same headcount, with the team effectively doubling delivery without new hires
- −81% human-reported bugs, reaching a full-year low while output nearly doubled
- 2× code-review throughput with zero added latency, including dedicated payments/PII security review
- Claude Code across the entire lifecycle: 47 custom skills, 6 subagents, and 19 slash commands turned team conventions into governed, reusable workflows
- Precisely scoped releases: regression testing targets only what changed and what is deployed, and release cuts are computed with hard confirmation gates
- 437 production incidents auto-investigated and ~200 errors/month auto-triaged, now running as a continuous, read-only, security-conscious stream
- 10× growth in AI operations in one month (38 → 443 pipeline runs) with a 92% autonomous-run success rate
Client
An iconic US landmark and one of the country’s most recognizable tourist attractions. SPD Technology serves as its primary software engineering partner and staff-augmentation engineering team.
Product
The Client’s guest-admission and venue ticketing platform, built on a single monorepo that consolidates the backend, four frontends, BrightSign digital signage, the automation-test suite, and infrastructure-as-code. SPD Technology delivers across this entire codebase, which handles ticket sales and admission for the attraction. On top of it, an operations layer connects the platform’s release process and production monitoring (Jira, Slack, Azure DevOps, Sentry) to guarded AI automation.
Goals and objectives
Development & quality
- Codify engineering conventions into reusable, enforceable workflows instead of leaving them as tribal knowledge.
- Keep code review, including payments/PII security, ahead of rising PR volume rather than trading quality for deadline pressure.
- Keep documentation, specs, and the knowledge base continuously in sync with code, so they stay trustworthy as the platform evolves.
- Accelerate and de-risk the translation of design files into front-end code.
Release & operations
- Free developer time from routine tickets for higher-value work.
- Scope regression testing precisely to what actually changed and what is actually deployed, instead of broad over-testing.
- Make release cuts computed and repeatable rather than manual and error-prone.
- Investigate production incidents quickly while minimizing security exposure, resolving the access-vs-exposure tension.
Overall: raise delivery throughput and quality without adding headcount.
Project challenge
As delivery accelerated, pain points across development and operations threatened quality, security, and velocity.
In daily development
- Conventions lived in people’s heads rather than being codified, so consistency and onboarding depended on tribal knowledge.
- Code review could not keep pace with PR volume, creating security risk under deadline pressure, especially around payments and PII.
- Documentation drifted out of sync with code, eroding trust in specs and the knowledge base.
- Design-to-UI translation was slow and imprecise, handled manually from design files to front-end code.
In release & operations
- Routine tickets consumed developer time that could have gone to higher-value work.
- Teams over-tested because regression scope was unclear relative to what was actually deployed.
- Release-cut decisions were manual and error-prone, relying on cross-referencing Jira and git history by hand.
- Incident debugging pulled against security: fast resolution needed broad access, which conflicted with minimizing exposure.
Solution
SPD Technology embedded Claude Code directly into the daily engineering workflow, then built a guarded AI operations layer on top of it.
Development workflow enablement
- Codified engineering toolkit: 47 custom skills, 6 subagents, and 19 slash commands that capture the team’s conventions as executable workflows.
- Governed feature/bugfix pipelines: the /feature and /bugfix flows run through phased review gates with a hard stop before PR creation, so nothing reaches a human reviewer unchecked.
- Automated code and security review: every PR in the governed flows passes mandatory Claude review before a human sees it, with a dedicated /security-review profile for the payments/PII surface and /pr-comment-triage re-checking open threads against current code.
- Living documentation: 10 doc-audit skills keep CLAUDE.md, specs, and the knowledge base in sync with code; kb-verify catches drift between docs and code.
- Test authoring with quality guardrails: AQA/Playwright authoring skills plus a test-fidelity guardrail that catches phantom or weakened assertions and skips, so AI-generated tests can’t pass without actually testing anything.
- Design-to-code/UI redesign workflows: currently in pilot, with broader rollout pending removal of a local Figma Desktop dependency.
Release & operations enablement
- Jira/Slack-triggered AI Agent Orchestrator: a multi-mode pipeline with guardrails against unsupervised action, so agents assist without acting unattended.
- Automated regression-scope analysis: diffs the release branch against what is actually deployed to staging, maps changes to business modules via the dependency graph and Confluence feature matrix, checks feature-flag state, and publishes a prioritized Critical/High/Medium/Low scope with checklists. It re-runs incrementally on every push.
- Release-cut automation: resolves the full fix-version scope to the earliest trunk commit containing every ticket, surfacing the exact SHA, the gating ticket, and blockers not yet in trunk. /cut-release then automates the branch cut, flag-enable migrations, and the PR back to trunk, with hard confirmation gates on every remote-facing step.
- Guarded incident investigation: read-only production investigation tooling that auto-files Sentry errors as investigated tickets.
Deployment status: regression-scope analysis, release-cut automation, and incident investigation are live and in active use. The AI Agent Orchestrator has its infrastructure provisioned and its integration merged as a draft PR, with final rollout pending remaining setup (a secret, a service connection, and a data migration).
Tech Stack
-
Claude Code -
Azure - Jira
-
Sentry
Our results
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)
Sustaining +89% merged output without AI would have required roughly 0.9× additional engineering capacity. The team effectively doubled output at the same size.
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
- ~200 production errors auto-triaged and resolved per month (converted from untriaged Sentry noise; 77% already closed)
- 437 production incidents auto-investigated (a net-new capability that did not exist as tracked work before July)
Incident investigation is now a continuous automated stream rather than an on-demand manual task: issues surface and close continuously instead of waiting to be noticed. Releases are more precisely scoped, with regression testing targeting what actually changed and what is actually deployed, and each release cut from a computed, minimal-drift commit with hard confirmation gates. Routine triage and release mechanics run as guarded automation, returning developer time to higher-value work, while read-only investigation and per-step confirmation gates keep security exposure low.
Highlights Client Our client is one of the U.S.’s largest asset management companies, with 12 000 + employees in...
Explore Case