Owlcast

Watch the video version for the demos and screen shares: https://www.youtube.com/live/-nuLcSKS1cIMelanie was joined by Xinyi Chen, a software engineer on Temporal's Cloud Growth team, and co-host Melissa McGregor from Temporal's docs team and author of the priority and fairness docs. Xinyi built priority and fairness into Temporal workflows from scratch, using a pizza shop with a single chef to make the concepts concrete before moving into live coding.Topics covered:Rate limiting, priority, and fairness as task queue features, explained with a pizza shop analogyBuilding the workflow from scratch live in an IDE with Claude and the Temporal Skill loadedRunning the logic as a standalone activityStarting workflows and activities directly from the Temporal Cloud UIWorkflow streams, now in public preview for Python with TypeScript coming soonResources:Task queue priority and fairness docs: https://docs.temporal.io/develop/task-queue-priority-fairnessTemporal AI cookbook: https://docs.temporal.io/ai-cookbookTemporal on GitHub: https://github.com/temporalioDatabricks Data + AI Summit: https://www.databricks.com/dataaisummitOriginally streamed June 11, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/live/-nuLcSKS1cI

Watch the video version for the demos and screen shares: https://youtu.be/rAY1ERVJLY4Terry Ryan from Google walks us through Naval Plan, a real app he built (and actually uses) to plan sailing trips using ADK Go. The app combines agentic research — pulling from old sailing forums and local knowledge — with deterministic API calls for tides, weather, and sunrise/sunset data. We dig into how the agents are architected, the quirks of working with Google Search as a tool in ADK, and Terry's dev workflow using Gemini CLI.Topics covered:Building Naval Plan: an agentic sailing trip planner with ADK GoMixing agentic research with deterministic API tools (tides, weather, sunrise/sunset)ADK agent architecture: subagents, tool composition, and the Google Search tool workaroundStructured JSON output from agents and how to make it reliableDev workflow: Gemini CLI in YOLO mode, git-based rollback, and prompt managementUsing LiteLLM for multi-model support in ADKTool count limits and context window considerationsUpcoming Temporal + ADK integrationLinks mentioned:ADK: https://adk.devNaval Plan walkthrough video: https://www.youtube.com/watch?v=kwSVtQ7dziUCharm (Go terminal UI libraries): https://charm.shGoogle Cloud Next (Las Vegas): https://www.googlecloudevents.com/next-vegasOriginally published April 6, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://youtu.be/rAY1ERVJLY4

Watch the video version for the demos and screen shares: https://www.youtube.com/live/GMsIhP3RIHgElvis Kaharu (Developer Advocate at dltHub) joined Melanie and co-host Cecil Phillip for a Vibe Check on building data pipelines in 10 minutes with dlt, the open source Python SDK for moving data from anywhere it lives. Elvis walked through how dlt fits between custom Python scripts and managed platforms, and showed how an agent can one-shot a pipeline when the SDK gives it strongly typed, declarative primitives to fill in.Topics covered:Why data pipelines are more than copying from point A to point B (schema normalization, incremental loads, schema evolution as a SEV)Scaffolding a project with uvx dlthub start and what gets generated for Claude (skills, roles, starter pipeline)Installing dlt toolkits for REST APIs, data quality, and file systemsOne-shotting a GitHub issues pipeline with Claude and the REST API skillSwitching destinations with a single line of code (DuckDB, Snowflake, Iceberg, S3, Hugging Face)Schema contracts with Pydantic and the gatekeeper pattern for handling bad rowsAttaching to a pipeline with Marimo notebooks to inspect data, schemas, and run data quality checksFailure introspection via checks.get_failures() and feeding failed rows into another dlt pipelineExporting dlt transformations as dbt models for regulated industries (health, finance)Where Ibis fits in (Python expressions that compile to SQL in Snowflake)Snowflake Cortex AI operators through Ibis as a way to shift left on AI workloadsSkills vs. MCP in the dlt setup, and how skills get tuned differently for Claude, Codex, and CopilotdltHub Pro for hosted pipelines, monitoring, and deploying Marimo notebooks as dashboardsIf you have ever wired up a brittle ingestion script, fought with a managed connector that did not quite fit, or wondered how agents should actually pull data into your warehouse, this episode is for you.Resources:dltHub: https://dlthub.com/dltHub on GitHub: https://github.com/dlt-hubIntroducing dltHub Pro: https://dlthub.com/blog/introducing-dlthub-proHugging Face + dlt for ML: https://dlthub.com/blog/hugging-face-dlt-mlElvis on GitHub: https://github.com/elviskahoroTemporal on GitHub: https://github.com/temporalio

Watch the video version for the demos and screen shares: https://www.youtube.com/live/CXSHANydwigIn this livestream, Donald (AI Foundations engineer at Temporal) and Mark Biza (DX engineer at Vercel) join us for a Vibe Check on skills — what they are, how to build them, and what they unlock for AI-assisted development. Donald previews the upcoming Temporal Agent Skill and live-demos it in Claude Code, while Mark walks through skills.sh, the distribution platform Vercel built to share skills across agents and teams.We go beyond the surface and explore:What Claude Code skills actually are — markdown files with YAML frontmatter that give coding agents structured, domain-specific contextWhy skills matter: how they guide agents past incomplete or inaccurate training data toward real best practicesHow the Temporal Agent Skill is structured — a shared core for cross-language concepts plus language-specific folders for Python, TypeScript, Go, and moreA live demo: Claude Code building a durable payment workflow using the Saga pattern — unprompted — because it was encoded in the skillWhy being able to run and iterate on workflow code (not just write it) is the key unlock for agents debugging Temporal appsHow skills.sh works — installation via npx skills add owner/repo, the leaderboard, auditing, and community contributionsVercel's Chat SDK skill and how it scaffolds agents for Slack, Discord, Teams, and WhatsAppUsing skills outside of code — marketing, SEO, copywriting, and motion graphics with RemotionSkills vs. MCP: why the future likely uses both together, and where each fitsThe case for skill cross-dependencies and skill bundles — a feature Donald and Mark noodle on liveIf you're building on Temporal, experimenting with Claude Code, or trying to understand how to give your coding agents better guardrails and domain knowledge, this episode is for you.The Temporal Agent Skill is launching next week — look for it on skills.sh.Resources:Temporal Agent Skills repo: https://github.com/temporalio/skill-temporal-developer/tree/devskills.sh: https://skills.sh/Vercel Agent Resources & Skills: https://vercel.com/docs/agent-resources/skillsTemporal with AI: https://docs.temporal.io/with-aiTemporal for AI: https://temporal.io/solutions/aiTemporal Community Slack (share your skill feedback here): https://temporal.io/slackOriginally streamed March 13, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/live/CXSHANydwig

Watch the video version for the demos and screen shares: https://www.youtube.com/live/jCQx4XvrEUkHolden Karau (Snowflake, formerly Databricks) and Lisa Cao (Databricks DevRel) joined us to dig into what it actually looks like to write Spark code with AI agents in 2026.We worked through a real example from Holden's High Performance Spark Second Edition — a Goldilocks-style exact percentiles problem across hundreds of columns — and watched Claude Code handle it from a cold-start repo, then again with proper context and a reference solution.Lisa walked through using a skill file to get Claude to write declarative pipelines the right way instead of hallucinating the syntax, and we talked about why local mode, Arrow UDFs, and the upcoming Python UDF transpilation work in Spark 4.3 matter for AI-assisted Spark development.We also covered: why the "agents trying to shut you up" failure mode shows up in code generation, the case for property-based testing as a guardrail for agentic coding, Spark 3 to Spark 4 porting as a more reliable path than one-shotting Spark 4, and where agents still struggle (dependency management, Spark internals, real stack trace debugging vs. pattern matching from Stack Overflow).Resources:Apache Spark: https://spark.apache.org & https://github.com/apache/sparkHigh Performance Spark (O'Reilly): https://www.oreilly.comSpark testing base: https://github.com/holdenk/spark-testing-baseDatabricks Spark: https://www.databricks.com/spark/aboutData + AI Summit (June 15–18, San Francisco): https://www.databricks.com/dataaisummitSnowflake Summit (June 1–4, San Francisco): https://www.snowflake.com/summitPySpark Data Sources: https://github.com/allisonwang-db/pyspark-data-sourcesPySpark SDP: https://github.com/lisancao/pyspark-sdpDistributed Computing 4 Kids: https://distributedcomputing4kids.com/What's working for you when you write Spark with agents? Drop your patterns and gotchas below. And let us know what you want to see on future episodes.Originally streamed May 13, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/live/jCQx4XvrEUk

Watch the video version for the demos and screen shares: https://www.youtube.com/live/fQGcbND0UasSarah Deaton, Technical Content Engineer at Anthropic and the person who owns the Claude Code docs, joined myself and my co-host Angela Zhou (Sr Technical Curriculum Dev @ Temporal) to walk through what's new and what's underused in Claude Code. We covered Claude Design for non-designers, the difference between CLAUDE.md, skills, hooks, and subagents (and when to reach for each), routines that run on schedules or GitHub events, the new rewind feature, auto mode, forked subagents, and the layers of sandboxing available for safer execution.Topics covered:Claude Design for visual work, mockups, and slide decks (and the handoff into Claude Code)When to use CLAUDE.md vs skills vs hooks vs subagentsWhy hooks are the deterministic layer underneath the model and where teams misuse CLAUDE.mdSlash init for scaffolding a new repo with Claude CodeRoutines: scheduled tasks plus GitHub events and API triggersRewind: pulling failed attempts out of the context window without polluting the next tryAuto mode and the classifier that gates risky actionsForked subagents: subagents that inherit the full conversation but keep their work isolatedSandboxing tiers: slash sandbox, dev containers, VMs, and Claude Code on the webResources:Claude: https://claude.ai/newClaude Code docs: https://code.claude.com/docsClaude Design: https://claude.ai/designCode with Claude events: https://claude.com/code-with-claudeSession management and 1M context blog post: https://claude.com/blog/using-claude-code-session-management-and-1m-contextTemporal AI: https://temporal.io/solutions/aiNote: This is the audio version of a video livestream that included live coding, screen shares, and on-screen demos. For the visual content, watch the full episode on YouTube.Originally streamed April 24, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/live/fQGcbND0Uas

Day two of Vibe Check live from Replay 2026.Shabnam Emdadi, staff software engineer at Shopify and Temporal Constellation member, on what AI frameworks are rediscovering from distributed systems, why retries are more expensive in an LLM world, and the case for judgment over one-more-prompt addiction.Francesc Campoy, Go expert and JustForFunc creator, on his first take on Temporal after the Go workshop, the cognitive offloading vs cognitive surrender distinction, and why software engineering still matters in production.Vibe Check co-hosts Melissa and Shy on the Replay keynote: Melissa's robot arm demo and agents workshop, and Shy's marathon to ship 2,300 hackable conference badges, including how Codex and Claude got the firmware over the line.Resources:Shopify: https://www.shopify.comJustForFunc: https://www.youtube.com/c/justforfuncReplay badge project: https://badge.temporal.ioTemporal AI: https://temporal.io/aiOriginally published May 7, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/watch?v=WXAIQxAKW4o

Ritika Shrivastava from Ember Robotics talks about what the AI agent world is rediscovering that robotics has known for years, and where companies trip up scaling from one robot to a hundred.Brian Douglas from Paper Compute breaks down their work on agent runtime and durable session recording, and where context engineering is heading post-MCP.Beverly Lu from Chime walks through what it actually takes to ship AI in a regulated fintech: evals as a discipline, domain experts in the loop, and per-model harnesses.We close with Johann Schleier-Smith from Temporal on the AI announcements from the keynote: priority and fairness, large payload storage, workflow streams, serverless workers, and where the harness conversation is heading.Resources:Ember Robotics: https://emberrobotics.comPaper Compute: https://papercompute.comChime: https://www.chime.comTemporal AI: https://temporal.io/aiOriginally published May 6, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/watch?v=GHHc4rDn8yY&t