AI Systems Brief with Krish

Build a nightly YouTube review agent with Claude Code. Follow the prompt, Python code, tools, agent loop and snapshot state, then see two runs and learn how to schedule your own.

00:00 Every night at 11

00:35 Intro

00:59 The job, and why it is an agent

02:15 Which coding assistant

02:32 The prompt

04:13 Claude Code builds it

04:30 What got built

06:03 The loop

06:42 Night one

07:49 Night two

09:42 Model, tools, loop, state

11:20 Schedule it

12:35 Three alternatives

13:21 Close

14:00 Outro

Daily 5: https://a2zai.ai/briefs

LinkedIn: https://www.linkedin.com/newsletters/ai-systems-brief-7461477781760294912/

Music: “Daily Beetle” Kevin MacLeod (incompetech.com), Creative Commons Attribution 4.0: https://creativecommons.org/licenses/by/4.0/

#AIAgents #ClaudeCode #AIEngineering #a2zai

Why can AI sound confident and still give the wrong answer? In this episode, Krish explains RAG—retrieval-augmented generation—through a customer asking whether they can return a pair of headphones.

Follow the question from a plausible answer to a search for the right policy. Learn how keyword and meaning-based retrieval work, why a citation can point to the wrong source, and how freshness, permissions and testing help make an AI assistant more useful.

AI Systems Brief with Krish — Episode 5. The store and policy are a fictional example.

Read the deeper builder guide, Designing RAG Systems: Turning Information Into Trusted Context (AI Systems Brief, edition 2):

https://www.linkedin.com/pulse/designing-rag-systems-turning-information-trusted-context-krish-adavi-0mggc/

Daily Five newsletter: https://a2zai.ai/briefs

YouTube: https://www.youtube.com/@a2zai-ai

Instagram: https://www.instagram.com/a2zai.ai/

00:00 Why confident AI answers can be wrong

00:40 AI Systems Brief with Krish

01:08 The headphone return question

02:51 RAG explained

03:58 Follow the question to the policy

05:32 Keyword and meaning-based search

06:31 The deeper LinkedIn guide

07:06 When the wrong policy is retrieved

07:44 Old information and current rules

08:18 Who can access the information?

08:54 Practical advice for users and builders

10:19 Test retrieval and answers separately

10:40 RAG and AI memory

11:21 The takeaway

12:12 Outro

Music: "Daily Beetle" Kevin MacLeod (incompetech.com)

Licensed under Creative Commons: By Attribution 4.0 License

https://creativecommons.org/licenses/by/4.0/

Source: https://incompetech.com/music/royalty-free/index.html?isrc=USUAN1500025

Excerpted, faded and ducked under narration for the intro and outro.

#RAG #AI #AIAgents #ChatGPT #a2zai

What can OpenAI Dot, Meta Muse and Claude Duet actually do beyond chat? Follow one Chicago-trip example, then compare the assistants' documented capabilities and practical jobs to explore with each.

Learn how preferences differ from fresh facts, how assistants use tools and keep working in the background, and how to hand over work while keeping the decisions that matter.

AI Systems Brief with Krish — Episode 4

Your host's real voice, with original explanatory animations and official product-source screens. The trip and suggested assignments are illustrative examples, not a hands-on benchmark. Features overlap. Duet is a research-preview waitlist starting with U.S. Pro/Max; Dot is rolling out gradually to eligible accounts. Sources checked October 24, 2026.

Daily Five AI newsletter: https://a2zai.ai/briefs

YouTube: https://www.youtube.com/@a2zai-ai

Instagram: https://www.instagram.com/a2zai.ai/

00:00 What happens after you delegate?

00:32 AI Systems Brief with Krish

00:55 One trip, one clear result

02:06 Preferences and fresh facts

03:25 Tools and the action loop

04:46 Dot vs Muse vs Duet

07:26 Work while you are away

07:59 The decision handoff

09:25 Try one recurring job

10:13 The takeaway and outro

Official sources:

https://learn.chatgpt.com/docs/dots

https://research.meta.ai/blog/security-and-safety-for-ai-agents-our-approach-with-muse

https://claude.com/resources/articles/claude-duet

Music: "Daily Beetle" Kevin MacLeod (incompetech.com)

Licensed under Creative Commons: By Attribution 4.0 License

https://creativecommons.org/licenses/by/4.0/

Source: https://incompetech.com/music/royalty-free/index.html?isrc=USUAN1500025

Excerpted, faded and ducked under original narration for intro and outro.

#AIAgents #ChatGPT #Claude #MetaAI #a2zai

AI tool calling can fail even after the action succeeds. Learn how timeouts, retries and idempotency affect AI agent reliability—and what evidence an agent harness needs before saying “done.”



What happens when an AI creates a task, the service succeeds, and the response disappears? In this audio-first episode, Krish Adavi walks through a small local experiment: a blind retry creates a duplicate, while a stable operation identifier prevents an extra effect in a service designed to honor it.



Learn how to separate permission from confirmation, interpret ambiguous timeouts, and define what “done” actually means in an agent harness.



The experiment is an isolated, in-memory, single-process simulation. It uses no LLM, live accounts, payments or external actions. It demonstrates a mechanism—not production reliability, persistence or concurrency safety. Video diagrams are explanatory illustrations, not captured production app screens.



Daily 5 AI newsletter: https://a2zai.ai/briefs

YouTube: https://www.youtube.com/@a2zai-ai

Instagram: https://www.instagram.com/a2zai.ai/



CHAPTERS

00:00 Your AI says “Done”

01:02 An answer becomes an action

02:27 The local experiment

03:03 Failure before creation

03:30 A lost confirmation

04:08 Why blind retries duplicate work

05:17 One operation, one stable identifier

06:49 Same key, changed intent

07:51 Recovering without safe retries

09:06 Permission versus confirmation

10:18 Give status words precise meanings

11:37 Test failures, not just prompts

12:56 Where the harness fits

13:23 Three practical takeaways



PRIMARY REFERENCES

Anthropic tool-use overview:

https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview

AWS Builders Library — Making retries safe with idempotent APIs:

https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/

Inspected October 20, 2026. Local evidence: tool-demo.py and tool-demo-results.json.



#AIAgents #ToolCalling #AgentHarness #Idempotency #AIEngineering



A left turn looks simple—until a van blocks your view and a pedestrian might step into the road. How does an AI driving system turn camera images into a decision?

Follow one imagined intersection through perception, uncertainty, possible futures, trajectory planning, onboard inference and feedback. Then learn why a convincing driving clip is not the same as a reliability test—and what AI builders can borrow from closed-loop evaluation.

AI Systems Brief with Krish — Episode 2

Audio-first: the explanation works without watching. The video adds original animated teaching diagrams.

Important: This episode discusses Tesla FSD Supervised, which requires an attentive driver ready to take over. It is an engineering explanation, not a driving tutorial or an assessment of an unsupervised service. The intersection and animations are conceptual—not actual Tesla footage, UI, or a disclosure of proprietary architecture. Cover artwork is AI-generated. The 44-feet example is arithmetic, not a Tesla latency benchmark or stopping distance.

CHAPTERS

00:00 How does a left turn become an AI decision?

01:50 Supervised does not mean autonomous

02:25 Images are not understanding

03:51 Why motion needs more than one frame

04:32 Hidden information is not a clear road

05:58 More than one possible future

07:50 A trajectory is more than a line

08:56 What end-to-end actually means

09:48 Training versus onboard inference

11:17 Why timing matters

12:53 Feedback: act, observe, repeat

13:39 Open-loop versus closed-loop testing

14:41 What this means for AI builders

15:15 Three lessons to take away

17:14 Next: finding the right source with RAG

SOURCES

Tesla FSD Supervised: https://www.tesla.com/support/fsd

Tesla engineering overview: https://www.tesla.com/AI

Tesla Model 3 manual: https://www.tesla.com/ownersmanual/model3/en_us/GUID-2CB60804-9CEA-4F4B-8B04-09B991368DC5.html

Public sources checked October 16, 2026. Vendor descriptions are not independent validation of performance.

Builder tools and deeper work: https://a2zai.ai

YouTube: https://www.youtube.com/@a2zai-ai

Instagram: https://www.instagram.com/a2zai.ai/

Follow AI Systems Brief with Krish for practical explanations of how AI systems work.

#TeslaFSD #AISystems #MachineLearning #AIEngineering #A2ZAI

AI Systems Brief with Krish — Episode 1

A short prompt can trigger a whole workflow. Follow a hypothetical hiking-boot return request through context gathering, tokens, prefill and decoding, KV caching, scheduling, tool calls and validation. Learn why a faster model does not always mean a faster useful result—and what builders should measure instead.

All return-policy details and timing numbers are illustrative, not a live store interaction or measured benchmark. Original explanatory animations accompany Krish's narration. The audio is self-contained.

Builder tools: https://a2zai.ai

YouTube: https://www.youtube.com/@a2zai-ai

Instagram: https://www.instagram.com/a2zai.ai/

Community and other channels: https://a2zai.ai/connect

CHAPTERS

00:00 After you hit Send

01:36 The model and the application

03:12 Context, tokens and prefill

05:52 How the answer is generated

07:30 KV caching

09:04 Scheduling and the clocks

10:43 When the assistant acts

12:04 The ten-second example

13:39 Practical builder takeaways

15:15 The whole journey

SOURCES

https://developer.nvidia.com/blog/mastering-llm-techniques-inference-optimization

https://huggingface.co/docs/transformers/main/kv_cache

https://huggingface.co/docs/transformers/v5.14.0/continuous_batching_architecture

https://docs.nvidia.com/nim/benchmarking/llm/metrics

https://www.anthropic.com/engineering/building-effective-agents

#a2zai #AISystems #LLM #AIEngineering