LoginSign Up
← Back to all sparks
C

Comet

AI-ASSISTANTS
Velocity6.3

ML experiment tracking and LLM observability platform, including Opik for evaluating LLM apps.

www.comet.com ↗

Comet bends Opik from eval and tracing toward AI-cost governance.

opikobservabilityagent-evalai-costllmopsintegrations
◆Current state
Comet's feed centers on Opik, its LLM and agent evaluation and observability layer, plus a heavy run of content on controlling AI and Claude Code token spend. Recent posts announce Comet Cost Intelligence, a Test Suites eval workflow, and an Oracle Open Agent Specification integration, interleaved with educational pieces on evaluation-driven development and agent tracing.
◆Where it's heading
Comet is widening Opik from evaluation and observability into cost governance for agentic systems, while hedging framework lock-in through standard agent specs. The AI-spend theme dominates the feed and now has a shipped capability behind it.
◆Prediction
Expect more cost-governance and automated-eval features on Opik plus further framework and provider integrations; the volume of cost-tracking content suggests spend control is the near-term wedge into enterprise LLMOps.

◆Recent moves

  1. 20h ago

    Engineering Insights: How Internal Optimizations Led to Comet Cost Intelligence

    ⚡ SPARK

    Cost Intelligence turns the feed's recurring AI-spend theme into a shipped capability, extending Comet and Opik from evaluation and tracing into governing what agents actually cost to run.

    View source ↗
  2. 6d ago

    How Evaluation-Driven Development (EDD) Works

    An explainer on evaluation-driven development; educational framing of the eval workflow Opik supports, not a release.

    View source ↗
  3. 9d ago

    Opik + Oracle Agent Specification: Build Once, Run Anywhere

    Opik's integration with Oracle's Open Agent Specification broadens framework interoperability, letting teams build against a standard spec and reduce lock-in — an incremental but real expansion of where Opik plugs in.

    View source ↗
  4. 13d ago

    AI Evaluation Simplified: Automate Dataset & Metric Eval Workflows with Test Suites

    Test Suites automate dataset and metric evaluation workflows in Opik, cutting the manual setup of reference datasets and LLM-judge prompts; a concrete usability gain for the eval product.

    View source ↗
  5. 13d ago

    Advanced Claude Code Cost Tracking: How to Save 30% on Token Spend

    A how-to on trimming Claude Code token spend; part of the cost-themed content run, educational rather than a product change.

    View source ↗
  6. 21d ago

    Understanding Your Claude Code Spend: What’s Actually Driving the Cost

    An analysis piece on what actually drives Claude Code costs; top-of-funnel content feeding the cost-governance narrative, not a release.

    View source ↗