--- schema: 1 type: video title: >- The 6 Pillars of an Agentic Harness for Production — Varun Krovvidi, Resolve AI description: >- AI changed how we write code. But 70% of engineering time goes to running and fixing it. Varun Krovvidi, product marketing lead at Resolve AI, explains why AI that writes code well still struggles to run production. Code is self-documenting, modular and a single domain. Production spans code, infrastructure, telemetry and many teams, and needs one correct answer. He covers where agents crack as you scale: anchoring bias and the model treadmill, too much or too little context, coherent answers that aren't causal, missing guardrails, and no learning across investigations. Then he lays out six pillars of a harness that fixes them: model orchestration, context engineering, causal reasoning, governed actions, learning systems and evals. He finishes with a demo of Resolve AI turning a Grafana alert into a root cause, ruling out a coincidental GCP outage, and holding its ground when pushed. In this talk: • Why coding is easy for AI and production isn't • Five ways production agents break as they scale • Six pillars: orchestration, context, causal reasoning, governed actions, learning, evals • Demo: from Slack alert to root cause with ruled-out theories SPEAKER Varun Krovvidi, Product Marketing Lead, Resolve AI LinkedIn: https://www.linkedin.com/in/varunkrovvidi/ LINKS Resolve AI: https://resolve.ai Resolve AI on X: https://x.com/resolveai CHAPTERS 0:00 Intro 0:48 Who's on call? 1:33 Why AI got good at code 2:33 Running software is the other 70% 2:53 On-call, incidents and daily vitamins 4:13 The end of unlimited AI 5:18 The last mile is the longest 5:28 A multiplayer problem 6:23 Resolve's three kinds of agents 7:02 Why not just point a model at prod? 7:37 Crack 1: anchoring and the model treadmill 8:47 Crack 2: too much or too little context 9:47 Crack 3: coherent isn't causal 10:27 Crack 4: guardrails 11:02 Crack 5: learning loops 11:52 The six pillars: model orchestration 12:42 Context engineering 13:32 A causal chain of evidence 14:12 Governed actions 14:32 Learning systems 15:07 Evals at five levels 15:57 Demo: alert to root cause 18:12 Demo: ruled-out theories 19:02 Demo: pushing back on the agent 20:11 Wrap-up Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #AISRE #AIAgents #AIEngineer canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/the-6-pillars-of-an-agentic-harness-for-production-eed489608161 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/the-6-pillars-of-an-agentic-harness-for-production-eed489608161.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:19:41.573Z' language: null children: [] videoId: eXA2tjRZIbY durationSeconds: 1265 publishedAt: '2026-10-06T23:30:36.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 67 endSeconds: 100 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=67' heldReason: rights - ordinal: 1 text: null startSeconds: 110 endSeconds: 156 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=110' heldReason: rights - ordinal: 2 text: null startSeconds: 190 endSeconds: 258 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=190' heldReason: rights - ordinal: 3 text: null startSeconds: 269 endSeconds: 325 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=269' heldReason: rights - ordinal: 4 text: null startSeconds: 325 endSeconds: 336 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=325' heldReason: rights - ordinal: 5 text: null startSeconds: 423 endSeconds: 434 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=423' heldReason: rights - ordinal: 6 text: null startSeconds: 469 endSeconds: 532 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=469' heldReason: rights - ordinal: 7 text: null startSeconds: 469 endSeconds: 532 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=469' heldReason: rights - ordinal: 8 text: null startSeconds: 544 endSeconds: 587 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=544' heldReason: rights - ordinal: 9 text: null startSeconds: 598 endSeconds: 631 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=598' heldReason: rights - ordinal: 10 text: null startSeconds: 645 endSeconds: 667 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=645' heldReason: rights - ordinal: 11 text: null startSeconds: 678 endSeconds: 721 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=678' heldReason: rights - ordinal: 12 text: null startSeconds: 733 endSeconds: 768 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=733' heldReason: rights - ordinal: 13 text: null startSeconds: 779 endSeconds: 814 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=779' heldReason: rights - ordinal: 14 text: null startSeconds: 825 endSeconds: 858 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=825' heldReason: rights - ordinal: 15 text: null startSeconds: 868 endSeconds: 879 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=868' heldReason: rights - ordinal: 16 text: null startSeconds: 924 endSeconds: 957 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=924' heldReason: rights - ordinal: 17 text: null startSeconds: 967 endSeconds: 1092 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=967' heldReason: rights - ordinal: 18 text: null startSeconds: 967 endSeconds: 1092 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=967' heldReason: rights - ordinal: 19 text: null startSeconds: 1104 endSeconds: 1152 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=1104' heldReason: rights - ordinal: 20 text: null startSeconds: 1163 endSeconds: 1220 watch: 'https://liquidgold.cc/watch/eXA2tjRZIbY?t=1163' heldReason: rights --- # The 6 Pillars of an Agentic Harness for Production — Varun Krovvidi, Resolve AI AI changed how we write code. But 70% of engineering time goes to running and fixing it. Varun Krovvidi, product marketing lead at Resolve AI, explains why AI that writes code well still struggles to run production. Code is self-documenting, modular and a single domain. Production spans code, infrastructure, telemetry and many teams, and needs one correct answer. He covers where agents crack as you scale: anchoring bias and the model treadmill, too much or too little context, coherent answers that aren't causal, missing guardrails, and no learning across investigations. Then he lays out six pillars of a harness that fixes them: model orchestration, context engineering, causal reasoning, governed actions, learning systems and evals. He finishes with a demo of Resolve AI turning a Grafana alert into a root cause, ruling out a coincidental GCP outage, and holding its ground when pushed. In this talk: • Why coding is easy for AI and production isn't • Five ways production agents break as they scale • Six pillars: orchestration, context, causal reasoning, governed actions, learning, evals • Demo: from Slack alert to root cause with ruled-out theories SPEAKER Varun Krovvidi, Product Marketing Lead, Resolve AI LinkedIn: https://www.linkedin.com/in/varunkrovvidi/ LINKS Resolve AI: https://resolve.ai Resolve AI on X: https://x.com/resolveai CHAPTERS 0:00 Intro 0:48 Who's on call? 1:33 Why AI got good at code 2:33 Running software is the other 70% 2:53 On-call, incidents and daily vitamins 4:13 The end of unlimited AI 5:18 The last mile is the longest 5:28 A multiplayer problem 6:23 Resolve's three kinds of agents 7:02 Why not just point a model at prod? 7:37 Crack 1: anchoring and the model treadmill 8:47 Crack 2: too much or too little context 9:47 Crack 3: coherent isn't causal 10:27 Crack 4: guardrails 11:02 Crack 5: learning loops 11:52 The six pillars: model orchestration 12:42 Context engineering 13:32 A causal chain of evidence 14:12 Governed actions 14:32 Learning systems 15:07 Evals at five levels 15:57 Demo: alert to root cause 18:12 Demo: ruled-out theories 19:02 Demo: pushing back on the agent 20:11 Wrap-up Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #AISRE #AIAgents #AIEngineer Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/the-6-pillars-of-an-agentic-harness-for-production-eed489608161 · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.