AI Native DevCon 2026 London — all conference sessions as interactive skills
71
89%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Ryan Lopopolo
[inferred from filename and transcript] Harness Engineering: How to Build Software When Humans Steer and Agents Execute is an AI Native DevCon session covering harness engineering, human steering, agent execution, software delivery with agents, and agent workflows.
[inferred] The talk's main contribution is its framing of harness engineering, human steering, agent execution for practitioners working with AI-native software development.
The source is timestamped speech-to-text output. Speaker labels, punctuation, and some technical terms may be imperfect. Use timestamps when citing.
| # | Timestamp range | Section | Summary |
|---|---|---|---|
| 1 | 00:00-03:22 | Opening and framing | We've only got a few sessions left this afternoon, and then it's party time, I've been told. |
| 2 | 03:25-07:18 | Main discussion 1 | my priors of what even is possible to achieve with these tools. |
| 3 | 07:21-11:04 | Main discussion 2 | constraint, that context windows are continually being emptied and filled. |
| 4 | 11:08-14:59 | Main discussion 3 | I never want to give the same review feedback twice, and this is really the core of what harness engineering is. |
| 5 | 15:03-18:38 | Main discussion 4 | over to something halfway across the code base without any loss of quality or intelligence. |
| 6 | 18:41-22:18 | Main discussion 5 | operationalize it with a set or three of static guardrails. |
| 7 | 22:20-25:57 | Main discussion 6 | These functions cannot possibly be exercised because the unknown types can exist, and we get more aligned code, more aligned code that I would consider acceptable, high quality, m… |
| 8 | 25:57-29:35 | Closing points | vibe coding is a big part of what it takes to be successful here, because there's a ton of guardrails that only affect my local development process. |
transcript.md around the relevant timestamp.Last observed timestamp: 29:35
.tessl-plugin
talk-azriel-executable-specs-agentic-coding
talk-batey-building-product-teams-age-of-ai
talk-birgitta-closing-keynote
talk-cormack-tests-lie-observability-ai-honest
talk-debois-agent-enablement
talk-douglas-training-ai-on-your-own-code
talk-dubnov-merge-rate-ai-adoption
talk-farley-vibe-coding-best-we-can-do
talk-firtman-web-mcp-agentic-web
talk-foxwell-reinvention-dev-team
talk-graziano-spec-driven-development
talk-groetzinger-skills-everywhere
talk-jones-odevo-ai-native-transformation
talk-jourdan-pipelines-to-prompts
talk-katsioloudes-code-security-ai
talk-kerr-bipolar-disorder-dysregulation-ai
talk-lamis-context-engineering-dreaming
talk-lawson-agent-experience
talk-lopopolo-harness-engineering-humans-steer-agents-execute
talk-luebken-embedding-pi-coding-agent
talk-maleix-collective-intelligence
talk-marsden-agent-desktops
talk-martinelli-spec-driven-development
talk-moss-skills-team-workflow
talk-obstbaum-willoughby-evals-hard
talk-overweg-one-brain-no-filtering
talk-podjarny-skills-are-the-new-code
talk-roberts-ai-native-brownfield
talk-roberts-brownfield-ai-native
talk-scheire-artificial-intelligence
talk-selajev-docker-sandboxes-agents
talk-sloan-harness-engineering-beyond-code
talk-smith-connecting-context-future-transports
talk-stack-humans-architect-ai-writes-code
talk-stoneham-product-brain
talk-syme-agentic-repository-automation
talk-tal-skills-security
talk-thomas-ai-native-engineering
talk-trieloff-browser-agents
talk-walter-runtime-intelligence-agents
talk-wilson-cq-stack-overflow-for-agents
talk-wotherspoon-humans-vs-slop