Senior Principal Engineer, Platform/DX/AI Infra @Skyscanner ✈️
Joined January 2010
- Tweets 2,052
- Following 711
- Followers 746
- Likes 2,041
98 Photos and videos
Apr 21
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…
2
191
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/…
3
9
49
12,656
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.
1
1
10
1,099
Jan 30
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.
52
Jan 30
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.
62
Jan 29
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.
38
Jan 28
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.
44
Jan 28
Set up Skyscanner Claude Plugin Marketplace - central repo with codeowners, provisioned via managed Claude config. The place is absolutely buzzing!
39
Jan 27
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.
24
Jan 26
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.
27
Jan 26
Built "bee" - declarative YAML layer on AWS Strands. Define agents, tools, prompts, workflows in YAML. Boilerplate dropped ~70%.
35
Jan 25
Debugging speed improved measurably once context existed. MTTR dropped. Claude could query actual architectural decisions, ownership chains. Context infrastructure shows up in metrics.
41
Jan 24
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.
39
Jan 24
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.
23
Jan 23
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.
47
Jan 22
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.
34
Jan 22
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.
40
Jan 16
Curated knowledge beats comprehensive. Don't ingest everything. Tie docs to IDP (e.g Backstage). Quality over quantity. Ownership enables accountability
19
Jan 15
Your competitive advantage in AI: not which model you use, but how effectively you feed any model your org's context. It really is all about building the right infra, not flashy demos
21
Jan 14
Context engineering has four dimensions (Curate, Persist, Isolate, Compress). Most teams only do Curate. The other three are why your context doesn't scale
50