Senior Principal Engineer, Platform/DX/AI Infra @Skyscanner ✈️
London, United Kingdom
Joined January 2010
- Tweets2.1K
- Following726
- Followers745
- Likes2K
At Skyscanner, we eventually landed on OpenCode as our harness, to be shielded from this type of impact. It’s not a guarantee with acquisitions though, as we can see from the Cursor’s example
We’ve been running some interesting experiments at Skyscanner, trying to preempt (we weren’t in time) and then address the growing code review load. The key for us is to understand “what” is safe to merge and “where” it is safe to merge. So team can spend time on less safe
Designed in Blender, 3d-printed, then hand-painted and varnished. Your @openclaw’s own crab shell from an independent maker 🦀 etsy.com/uk/listing/44917958…
Igor Karpovich retweeted
Great morning bringing the speakers from @aiDotEngineer to Downing Street to discuss transforming the state.
Through the Incubator for AI and the No10 Innovation Fellowship, we are making sure that top AI talent can help build a better Britain!
job-boards.eu.greenhouse.io/…
What a day! As part of the @aiDotEngineer conference, I was invited to an event at No 10. There are plenty of practical problems to solve, and it’s encouraging to see the Government actively seeking advice from industry leaders.
Comprehensive context creates maintenance burden. Staleness creeps in, accuracy drops, no one owns it. Curated context can be kept current, validated, owned. IDP is your friend here.
Teams ask "how do I give Claude context?" Instinct: dump repos, link all Confluence, create massive CLAUDE.md. Wrong. More comprehensive ≠ better. Quality over quantity.
MTTR improved once context existed. Debugging sped up when Claude could query actual architectural decisions instead of guessing from training data. Context infrastructure pays off in metrics.
The onboarding agent pattern: configure Claude NOT to generate code, but to guide learning. Pull context from Confluence + GitHub + Jira, generate bespoke plan. That's the cycle working.
Set up Skyscanner Claude Plugin Marketplace - central repo with codeowners, provisioned via managed Claude config. The place is absolutely buzzing!
Infrastructure work isn't flashy. Building knowledge bases, auto-generating docs with quality gates, creating skills. It's not free. That's what makes coding agents work in enterprise.
Layering LLM on LLM to compensate for missing context degrades output. Text gets duller. The breakthrough wasn't better agents - it was simpler agents with better context.
Built "bee" - declarative YAML layer on AWS Strands. Define agents, tools, prompts, workflows in YAML. Boilerplate dropped ~70%.
Debugging speed improved measurably once context existed. MTTR dropped. Claude could query actual architectural decisions, ownership chains. Context infrastructure shows up in metrics.
A team built an onboarding agent that doesn't generate code - it guides learning. MCPs pull context from Confluence, GitHub, Jira. Generates bespoke onboarding plan. Simple AND practical.
We seconded a junior engineer to a new team. With curated docs in the knowledge graph, they ramped up fast - even in an unfamiliar language. Curation over comprehensiveness works.
The echo chamber risk: AI generates docs - docs feed AI - AI generates more docs. Without human validation, you get AI slop multiplying. Design for humans-in-the-loop from day one.
Curation beats comprehensiveness. We give Claude 50 standards that matter (curated, owned, current) not 5,000 Confluence pages (stale, unowned, noisy). Signal over noise wins every time.
We rolled out Claude Code to hundreds of engineers. Output quality varies wildly. Same model, different results. The differentiator isn't the tool - it's how well we give it Skyscanner's knowledge.