Claude Projects vs Travel Hacking Toolkit

“The primitive here is a named, persistent system-prompt-plus-document-store scoped to a workspace — which is genuinely the thing developers have been duct-taping together with system prompt files committed to git and copy-pasted on every new chat. The DX bet is 'make the right thing the default thing': instead of building a wrapper that injects context programmatically, Anthropic just made the UI do it natively. The gap is API parity — if Projects context doesn't flow through the API with the same scoping, developers will still be hand-rolling this, and that's the specific thing I'd want confirmed before calling this a full ship.”

“The MCP architecture is exactly right for this problem—travel APIs are diverse and constantly changing, and skills-as-markdown-files means any developer can add a new loyalty program or airline API in 30 minutes without touching a codebase. The Seats.aero integration alone makes this worth setting up.”

“The direct competitor is ChatGPT's Custom Instructions plus Memory, which has had persistent context for over a year — so Anthropic is catching up, not leading. The scenario where this breaks is team use at scale: shared document libraries with no versioning, no access controls beyond plan-level sharing, and no audit trail mean the first time a team's shared prompt gets silently edited and causes a bad output, trust collapses. What kills this in 12 months isn't a competitor — it's Anthropic itself shipping a proper API-native version that makes the UI feature redundant for the power users who care most about it.”

“Most of these APIs require paid keys or have aggressive rate limits, and the 'sweet spots' data will go stale quickly as airlines devalue programs. This solves a real problem but requires significant manual maintenance to stay useful—you're essentially signing up to maintain your own travel hacking research infrastructure.”

“The job-to-be-done is sharp and singular: stop re-explaining yourself to Claude every time you start a new conversation. Onboarding is as fast as it gets — create a project, paste your instructions, upload a doc, done, under two minutes to value. The product opinion baked in here is correct: most users don't need a memory graph or semantic search over past conversations, they need a stable persona and a document library, and Claude Projects makes exactly that bet without over-engineering it. The gap between shipped and needed is team permission controls — right now it's blunt-instrument sharing, and that will matter the moment any organization with more than five people tries to use this seriously.”

“The thesis this bets on: within two years, AI assistants aren't used as one-off query tools but as persistent collaborators with institutional memory, and whoever owns the persistent context layer owns the workflow. The dependency that has to hold is that Claude remains the preferred model for knowledge-work tasks — if GPT-5 or Gemini Ultra pulls far enough ahead on capability, users don't move their Projects, they just stop opening the tab. The second-order effect nobody is talking about: shared Projects make Claude's system prompt a team artifact, which means prompt engineering starts being treated like documentation — owned, versioned, and argued about in PRs. That's a genuine shift in how organizations relate to AI, and Anthropic is positioning itself as the place where that institutional knowledge lives.”

“This is an early template for domain-specific MCP skill sets—curated API knowledge plus structured data that turns a general AI assistant into a specialist. As MCP adoption grows, we'll see these skill bundles for every vertical from legal research to healthcare, and travel hacking is a natural first mover.”

“Finally something that makes the 'just ask your AI to book travel' promise real rather than theoretical. The alliance and partner award data files are the kind of curated, hard-to-find knowledge that normally lives in obscure blog posts—having it structured for AI consumption is genuinely useful.”