Milestone: AI Chapter Champion at Sinch!

My work on spec-driven development with Claude Code was selected for Sinch’s monthly AI Champions showcase, representing one of five chapters across the company.

Really, a career milestone!

I used Claude Code to help build a new component for our design system. The approach was to write a plain-language prescriptive spec before touching any code. It covered behavior constraints, design tokens, implementation checklist, and then explicit instructions to follow existing codebase conventions rather than invent new patterns.

Result – a design system component generated in ~30 minutes, with another 30 minutes of fixes. MR review comments were about missed requirements, not code style. That’s a meaningful shift in where human attention goes during review.

Next Steps – formalizing the skills generalized from this task and looking into sharing them with the wider community.

The bigger takeaway so far: the quality ceiling for AI-assisted engineering is set by the spec, not the model. Prescriptive plain-language constraints dramatically outperform ad-hoc prompting.

Tl;DR – It’s Not As Bad As They Say!

“Contrary to conventional wisdom, the 2023 ABS (which produced 2022 data) found that adoption of technology, including AI, did not change overall worker numbers.

Businesses most often reported their “number of workers did not change overall” between 2020 and 2022 after adopting any of the five technologies the ABS tracked: AI, specialized software, robotics, cloud-based tech or specialized equipment.”

Cutting through all the hype on AI, a take from the recent US census report.