Meet Preflight 🛫
DevTools for AI coding. Free, open-source observability for Claude Code (and other AI coding agents). Runs 100% locally, no New Relic account needed.
- Live-tail of all activity
- Subagent and workflow tracking
- Per-model cost breakdown
- Throttle detection, before your agent silently stalls
- Budget alerts
- Git hygiene tracking
Stop guessing your AI agent's ROI on vibes.
Building with a team? Optionally dual-send to New Relic to measure AI coding ROI across your whole org.
10,000+ downloads and counting.
npm i -g @newrelic/preflight
https://t.co/uSvCFyjqtZ
There is still no substitute for caring. Every piece of software getting rapidly better is happening because a human cares. And happens to be using AI to move really fast.
Claude Platform (Claude Managed Agents, the Messages API and the Claude SDKs) now emit OpenTelemetry (#OTel) traces in public beta.
In New Relic, they can land in the same trace as your services. A failed tool use or slow model request sits next to the code that triggered it. https://t.co/rbow8K4kpq
Now in public beta, Claude Platform can send OpenTelemetry traces from the Messages API, Claude Managed Agents, and the Claude SDKs to your observability stack.
As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS.
A healthy team needs a mix of these, depending on the product:
- A product that is new and pre-PMF needs people that are strong at 1+2+3
- A product that is growing and has found PMF needs 2+3+4 and some 5
- A product that has strong PMF needs 3+4+5 and some 2
Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?
Eating our own dogfood.🐕
Discover how New Relic's engineering team scales AI agents by switching from manual debugging to integrated AI Observability, reducing cost and boosting performance. https://t.co/llWCVqMvr0
Every tap that went nowhere. 🚫
Meet Session Replay for mobile applications, providing a high-fidelity visual replay of every user interaction automatically synced with your backend telemetry.
Learn more here: https://t.co/fPz3WT5IEX
Manual correlations between your IDE and observability data kill your MTTR.
With the New Relic AI MCP Server, your AI agents now have direct access to live production telemetry.
Be the first to preview our new features: https://t.co/SVPPoXOAQ7
Huge win for the team: IDC named @NewRelic a Leader!
Whether it is agentic AI or plain-language incident explanations, we’re building the future of #AIOps.
Read the full report: https://t.co/uLPNpcaU57
New innovations in Agentic #AI? Measurable business impact? Hands-on workshops?
Check, check, and check. ✅ Whatever you’re seeking insight on, our annual edition of #NewRelicNow has you covered with our biggest product announcements yet!
Save your spot: https://t.co/maA5u8rkrf
📈 Accelerate tech #ROI and dev productivity
🧑💻 Manage complex architectures
☁️ Tame #cloud costs
What if we told you that #IntelligentObservability could help you do all that and more? RSVP to see it in action: https://t.co/maA5u8rSgN
🗞️ We’re launching the industry’s only #observability solution for monitoring #DeepSeek to optimize quality, cost, and performance.
By monitoring DeepSeek with #NewRelicAImonitoring, you can 🧵