Owlcast

M Warrick

0.0 (0)
Technology

Owlcast explores AI and the systems that power it, sharing what works, what doesn't, and what's still being figured out. Solo episodes, conversations with builders, and the Vibe Check series from Temporal. All working through what it actually takes to build today.

2d ago

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
Jul 21

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/
Jul 7

Vibe Check: Temporal SDKs are Not a Thin Client

Watch the video version for the demos and screen shares: https://www.youtube.com/live/YXjbfc8ioV8 In this livestream, Chad Retz (Temporal SDK maintainer, 4+ years at Temporal) digs into the open source code that powers your workflows. We go beyond the surface and explore: Why Temporal is fully MIT licensed (and why that matters)The difference between the Temporal Server and the SDKsHow the Python SDK turns your code into durable, replayable workflowsWhat really happens when you call execute_workflowHow workers poll, replay history, and deterministically execute your codeInterceptors, activations, commands, and the Rust coreError handling, retries, and gRPC under the hoodHow to contribute to Temporal's open source reposHow Chad uses AI (Claude, Opus) to build SDK features across languagesIf you've ever wondered how Temporal makes your code durable or why the SDKs are so "smart" then this is for you. Explore the repos: https://github.com/temporalio Originally streamed February 20, 2026 on Vibe Check Temporal YouTube channel and you can watch the full episode at: https://www.youtube.com/live/YXjbfc8ioV8
Jun 30

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 isolationRunning one environment three ways: bare macOS, a Docker dev container, and an Apple Container microVMThe manifest.toml and default environments for keeping utilities consistent everywhere, plus team sharing via hub.flox.devTreating AI skills as software (roughly 25% ship with vulnerabilities), and registering the Temporal skill with Claude to build a live workflowSecrets 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.devFlox in Five (5-min tutorial): https://flox.dev/docsFlox Hub: https://hub.flox.devFlox on GitHub: https://github.com/floxTemporal Validated Patterns: https://temporal.io/resources/validated-patterns
Jun 23

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 outputBedrock vs. AgentCore, and swapping model providers (Bedrock, Anthropic, OpenAI, Gemini) by changing one model IDAgentCore's built-ins: an MCP tool gateway with semantic search, session and persistent user memory, and zero-config observabilityWhere 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/temporalioHow Temporal uses Bedrock AgentCore: https://aws.amazon.com/blogs/apn/how-temporal-uses-amazon-bedrock-agentcore-to-create-robust-ai-systems/
Jun 16

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 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 soon Resources: 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
Jun 9

Vibe Check: Planning a Sailing Trip with AI Agents — ADK Go in Action

Watch the video version for the demos and screen shares: https://youtu.be/rAY1ERVJLY4 Terry 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
Jun 2

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 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

Owlcast explores AI and the systems that power it, sharing what works, what doesn't, and what's still being figured out. Solo episodes, conversations with builders, and the Vibe Check series from Temporal. All working through what it actually takes to build today.

Creator

M Warrick
Years Active

2026
Episodes

13
Rating

Clean
Copyright

© Nyghtowl 2026
Show Website

Owlcast