Owlcast

Owlcast

di M Warrick
Come fareTecnologia
Stagione 1
Vibe Check: What should an agent remember?
> Watch the video version for the demos and screen shares: https://www.youtube.com/watch?v=VvaVzu_BjS0 What should an agent remember, and where should that memory actually live? Melanie sat down with Chris Gambill (Gambill Data) and Scott Haines (Databricks) to get concrete about agent memory: what belongs in the context window, what belongs in memory files, and what needs to live outside the agent entirely. Chris demoed OmniGent, the open source meta-harness from Databricks that runs multiple coding agents side by side. We watched it stand up a World Bank data pipeline into a medallion architecture, including a debate step where two models argue the approach before one goes and builds the plan. Scott walked through how he keeps sessions lean using a memory.md that points to the real source of truth instead of reloading the whole codebase, and why his context window stayed around 32k tokens instead of ballooning into the millions. From there we got into the parts that actually matter in production: - The three levels of memory: session, team or workspace, and organization-wide - Why hard security rules like "nothing gets pushed to main without a PR" belong outside the memory file, as an actual hook and not a suggestion - The idea the guests called "dreaming": agents summarizing their own sessions so the next one starts from the lessons, not the raw token history - Token usage as a signal: why token leaderboards are a bad productivity metric and what real ROI looks like (PRs opened and closed, healthier communities, actual contributions) - Multi-project and external memory: Postgres-backed sessions, sharing state through GitHub, and the risk of stale memory polluting a good result - Where autonomous agents and real money should still stop and ask first Resources - OmniGent (open source meta-harness from Databricks): https://omnigent.ai/ - Databricks: https://www.databricks.com/ - Chris Gambill, Gambill Data: https://gambilldata.com/ - Chris Gambill on YouTube (data engineering): https://www.youtube.com/@GambillDataEngineering - Scott Haines on YouTube (Conferences playlist): https://www.youtube.com/playlist?list=PLBJeAtDBQjJMANOGMxUd30nSIhdw9bcNt - Temporal orchestration for Open Lakehouse: https://www.openlakehouse.io/technologies/orchestration - Temporal, durable orchestration for AI agents: https://temporal.io --- Originally streamed July 22, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/watch?v=VvaVzu_BjS0
S1 · E19
28 lug 2026
1:00:22
Vibe Check: How autonomous is the agentic GTM stack?
Watch the video version for the demos and screen shares: https://www.youtube.com/live/kT9xu6xEurI Nehal Agrawal, a go-to-market engineer at Invigilo, joined us to show how she builds her own agents for GTM. Off-the-shelf tools like Clay and Apollo were too fragmented for Invigilo's niche verticals in construction, oil and gas, and manufacturing, so she built a custom orchestrator instead, and it pulled a 60% reply rate on post-event warm outreach over a typical 20%. Topics covered: - Why fragmented tools did not fit niche verticals, and when it makes sense to build your own orchestrator - The post-event outbound workflow: lead list in, agent-drafted sequences out, and a reply rate that mostly landed after the third follow-up - Why the agent drafts into Outlook but never sends on its own, and where human-in-the-loop belongs (cold versus warm, deal value) - The harnesses and dedicated security agent she runs to keep agents from running amok or burning tokens - Build versus buy for the GTM stack, agent-to-agent communication, and a recap of AI Engineer World's Fair including its first GTM track Resources: - Invigilo: https://www.invigilo.ai/ - Nehal Agrawal: https://www.nehalag.com/ - AI Engineer (AIE): https://www.ai.engineer/
S1 · E18
21 lug 2026
45:37
Vibe Check: Sandboxing, Skills, and Surviving Dev to Prod
> Watch the video version for the demos and screen shares: https://www.youtube.com/live/CMXCnbbiPoY Episode description Melanie and co-host Cecil Phillip are joined by James Bayer, CPO at Flox and a longtime infrastructure engineer from Pivotal and HashiCorp. James walks through reproducible software environments built on the Nix ecosystem — running the same Temporal environment directly on macOS, inside a Docker dev container, and inside an Apple Container microVM — then makes the case for treating AI skills like real software you lifecycle-manage. In this episode: Reproducible environments with Flox, separating software packaging from isolation Running one environment three ways: bare macOS, a Docker dev container, and an Apple Container microVM The manifest.toml and default environments for keeping utilities consistent everywhere, plus team sharing via hub.flox.dev Treating AI skills as software (roughly 25% ship with vulnerabilities), and registering the Temporal skill with Claude to build a live workflow Secrets patterns with Keychain, 1Password, and Vault, package and skill firewalls, and cross-platform portability across x64, ARM64, and Windows via WSL2 Resources: Flox: https://flox.dev Flox in Five (5-min tutorial): https://flox.dev/docs Flox Hub: https://hub.flox.dev Flox on GitHub: https://github.com/flox Temporal Validated Patterns: https://temporal.io/resources/validated-patterns
S1 · E17
30 giu 2026
47:48
Vibe Check: There's No Agent Without the Harness
Watch the video version for the demos and screen shares: https://www.youtube.com/live/N8Z-XIs_m8k Episode description Melanie is joined by Elizabeth Fuentes Leone (AI Engineer & Developer Advocate at AWS) and co-host Shubham Londhe to make the case that there's no agent without the harness: the code and infrastructure around the model that turns it into something you can run in production. Elizabeth builds a harness from scratch with AWS Bedrock AgentCore in a single CLI command, then walks through the pieces that do the work and where durability fits in. In this episode: What a harness actually is: the agent loop plus the infrastructure that feeds the model and handles its output Bedrock vs. AgentCore, and swapping model providers (Bedrock, Anthropic, OpenAI, Gemini) by changing one model ID AgentCore's built-ins: an MCP tool gateway with semantic search, session and persistent user memory, and zero-config observability Where Temporal fits (durable execution, retries, and state as a tool inside the loop) and why it complements, not replaces, LangGraph or LlamaIndex If you've built an agent that runs fine on your laptop and fell apart in production, this one's for you. Resources: Bedrock AgentCore: https://aws.amazon.com/bedrock/agentcore/ AgentCore credits: https://events.elifuentes.tech/events/agentcore-harness/ Elizabeth Fuentes Leone: https://elifuentes.tech/ Shubham Londhe: https://www.trainwithshubham.com/ Temporal on GitHub: https://github.com/temporalio How Temporal uses Bedrock AgentCore: https://aws.amazon.com/blogs/apn/how-temporal-uses-amazon-bedrock-agentcore-to-create-robust-ai-systems/
S1 · E16
23 giu 2026
53:28
Vibe Check: Priority, Fairness & Building Workflows from Scratch
Watch the video version for the demos and screen shares: https://www.youtube.com/live/-nuLcSKS1cI Melanie 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 analogy Building the workflow from scratch live in an IDE with Claude and the Temporal Skill loaded Running the logic as a standalone activity Starting workflows and activities directly from the Temporal Cloud UI Workflow streams, now in public preview for Python with TypeScript coming soon Resources: Task queue priority and fairness docs: https://docs.temporal.io/develop/task-queue-priority-fairness Temporal AI cookbook: https://docs.temporal.io/ai-cookbook Temporal on GitHub: https://github.com/temporalio Databricks Data + AI Summit: https://www.databricks.com/dataaisummit Originally streamed June 11, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/live/-nuLcSKS1cI
S1 · E15
16 giu 2026
55:09
Vibe Check: Zero to Data Pipeline — Building with AI & dlt in 10 Minutes
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 systems One-shotting a GitHub issues pipeline with Claude and the REST API skill Switching destinations with a single line of code (DuckDB, Snowflake, Iceberg, S3, Hugging Face) Schema contracts with Pydantic and the gatekeeper pattern for handling bad rows Attaching to a pipeline with Marimo notebooks to inspect data, schemas, and run data quality checks Failure introspection via checks.get_failures() and feeding failed rows into another dlt pipeline Exporting 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 workloads Skills vs. MCP in the dlt setup, and how skills get tuned differently for Claude, Codex, and Copilot dltHub Pro for hosted pipelines, monitoring, and deploying Marimo notebooks as dashboards If 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-hub Introducing dltHub Pro: https://dlthub.com/blog/introducing-dlthub-pro Hugging Face + dlt for ML: https://dlthub.com/blog/hugging-face-dlt-ml Elvis on GitHub: https://github.com/elviskahoro Temporal on GitHub: https://github.com/temporalio
S1 · E13
2 giu 2026
56:57
Vibe Check: Can AI Actually Write Spark? Live Coding w/ Databricks & Snowflake
Watch the video version for the demos and screen shares: https://www.youtube.com/live/jCQx4XvrEUk Holden 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/spark High Performance Spark (O'Reilly): https://www.oreilly.com Spark testing base: https://github.com/holdenk/spark-testing-base Databricks Spark: https://www.databricks.com/spark/about Data + AI Summit (June 15–18, San Francisco): https://www.databricks.com/dataaisummit Snowflake Summit (June 1–4, San Francisco): https://www.snowflake.com/summit PySpark Data Sources: https://github.com/allisonwang-db/pyspark-data-sources PySpark SDP: https://github.com/lisancao/pyspark-sdp Distributed 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
S1 · E12
22 mag 2026
47:17
Vibe Check at Replay '26: Day 2 w/ Shabnam Emdadi, Francesc Campoy, Melissa Herrera, & Shy
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.com JustForFunc: https://www.youtube.com/c/justforfunc Replay badge project: https://badge.temporal.io Temporal AI: https://temporal.io/ai Originally 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
S1 · E11
12 mag 2026
24:13
Vibe Check at Replay '26: w/ Ritika Shrivastava, Brian Douglas, Beverly Lu, & Johann Schleier-Smith
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.com Paper Compute: https://papercompute.com Chime: https://www.chime.com Temporal AI: https://temporal.io/ai Originally 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
S1 · E10
11 mag 2026
22:25
Vibe Check: Claude Code Unpacked — How to Actually Ship with AI Tooling
Watch the video version for the demos and screen shares: https://www.youtube.com/live/fQGcbND0Uas Sarah 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 subagents Why hooks are the deterministic layer underneath the model and where teams misuse CLAUDE.md Slash init for scaffolding a new repo with Claude Code Routines: scheduled tasks plus GitHub events and API triggers Rewind: pulling failed attempts out of the context window without polluting the next try Auto mode and the classifier that gates risky actions Forked subagents: subagents that inherit the full conversation but keep their work isolated Sandboxing tiers: slash sandbox, dev containers, VMs, and Claude Code on the web Resources: Claude: https://claude.ai/new Claude Code docs: https://code.claude.com/docs Claude Design: https://claude.ai/design Code with Claude events: https://claude.com/code-with-claude Session management and 1M context blog post: https://claude.com/blog/using-claude-code-session-management-and-1m-context Temporal AI: https://temporal.io/solutions/ai Note: 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
S1 · E9
19 mag 2026
45:29
1 di 2