Knock vs Honeycomb
Side-by-side trajectory, velocity, and editorial themes.
Knock is rewiring notifications infrastructure to be configured by agents, not just developers.
Knock is methodically rebuilding its primitives — audiences, layouts, reusable steps, in-app guides — so they're versioned, environment-promotable, and addressable from an agent in addition to the dashboard and CLI. The recent run shows a clear pattern: each new feature ships with at least one agent-accessible path. Underneath, the engineering surface is also tightening, with reusable request input schemas making composability less guesswork.
Knock is positioning its platform as agent-buildable messaging infrastructure rather than just a developer SDK. Skills, dynamic audiences, and schema'd reusable steps are the building blocks of a future where a product team agent (or Knock's own) can spin up an entire notification flow without a developer touching code. The Layouts 2.0 refresh and Guides toolbar work in parallel to harden the human surfaces that remain.
Expect Knock to publish a more opinionated agent surface — likely an MCP-style server or an in-product agent that orchestrates skills against dynamic audiences. The reusable-input-schemas release is the kind of plumbing that precedes a 'build a workflow from a prompt' demo, so a higher-level natural-language workflow composer is the most probable next move.
Honeycomb is rebuilding observability around an autonomous investigation surface called Canvas.
Every meaningful release in the last quarter rolls up to one product motion: Canvas, an agentic investigation surface that Honeycomb is propagating across the entire product. The May 20 launch turned Canvas into a multiplayer workspace where humans and AI agents investigate together, with auto-investigations that kick off when triggers fire, GitHub-grounded analysis, custom skills for runbook knowledge, and a Slack app. Around the headline launch, Honeycomb shipped BubbleUp Insights (AI-summarized anomaly diffs), a Gen-AI tab in trace view, Query Math, dark mode, and earlier beta surfaces of Ask Canvas and Slack Canvas that the big release now consolidates.
Honeycomb is repositioning from 'query your telemetry' to 'investigate with agents that know your system.' Canvas is the through-line: it shows up on Home, in Slack, in alert flows, in traces. The Gen-AI trace tab and BubbleUp Insights point at a parallel bet - that the kind of system worth observing increasingly includes LLM-powered apps, and the observability tool has to speak that language natively. Together this is a category-redefining move on the AI-native ops front, where competitors are still bolting chatbots onto dashboards.
Expect Canvas to keep absorbing surface area: deeper IDE/GitHub integration so investigations can suggest or open PRs, marketplace-style sharing of custom skills, and Canvas access via MCP so agents in other tools can query Honeycomb directly. The next spark will likely be Canvas writing back to the system - e.g., proposing config changes or runbook edits from what it learned.
See more alternatives to Knock →
See more alternatives to Honeycomb →