Last week, we released our first step in making observability programmable and agent-ready with the bitdrift Public API. Today, we're announcing the release of bd skills, a set of skills that give your AI agents access to everything that happens on any of your customers' devices in real time. Together, bd skills and the bitdrift Public API empower the next generation of our mobile observability platform: bitdrift.ai.

Agentic AI has fundamentally changed software engineering

Observability no longer has to be a reactive exercise. Rather than drowning in a sea of alerts, charts, and logs, agents can autonomously triage, investigate, debug, and even fix issues as they happen. This allows teams to focus on what really matters: your customers and their experiences. Now, those agents, regardless of the model and harness, must have access to high fidelity data to do their job. More importantly they need to be able to iterate in tight feedback loops. In the past that’s been impossible on mobile devices with slow app release cycles and challenging SDK syncs limiting the telemetry being collected. As a result, all other observability tools rely on sampled or stale data. This means you are always working with approximations, partial visibility, historical snapshots, false metrics, and educated guesses.

bitdrift: purpose-built for mobile observability

The bitdrift platform uniquely provides a level and quality of data on deployed mobile applications that no one else can. Data is captured on the device, aggregated in real time, and unsampled by default. When you investigate an issue, you are not querying a static dataset. You are interacting with live user behavior from the device.

Full-fidelity observability, now accessible to AI agents

Now, our real-time observability system allows you or your agents to dynamically create and collect telemetry on any device instantly. User journeys, performance metrics, and behavioral changes are all available when your agent needs them, not ten days later waiting for an app release. And with our ability to narrowly target exact cohorts and data sets, you won’t blow your context window on useless noise. With this release, agents will be able to leverage our powerful CLI and public API to programmatically access and create the core components of the bitdrift platform: workflows, charts, issues, and captured sessions, letting them iteratively query and analyze telemetry from customer devices. You can create and manage workflows in code, retrieve full-fidelity sessions on demand, and integrate bitdrift into your existing tooling, your deploy pipelines, or your on-call workflows, all without ever opening a dashboard.

Let your AI agents query reality today

Get started: Learn more about mobile observability for AI agents at bitdrift.ai, or try it out by running the following in any terminal:

bash
npx skills add bitdriftlabs/bd-skills

Full instructions at https://github.com/bitdriftlabs/bd-skills Not quite ready to dive in but curious to learn more about bitdrift? Sign up for a free trial of bitdrift's mobile observability platform, or contact us for a quick demo.