AI agents · YT Insights Explorer

Publication timeline

2025-011 video
2025-061 video
2025-111 video
2026-042 videos
2026-051 video
2026-061 video
2026-0814 videos
2026-0913 videos
2026-1014 videos

Source videos

AI Agents Cut 3-Day Portfolio Builds to Minutes — Jack McDonald, Apollo & Michael Manapat, Rowspace

The Agent Works. Does Anyone Trust It? — Michele Grant, Leading at Scale

Muse Wonder: Zuckerberg and Wang's $100B AI

Andrew Ng on Coding Agents and Deciding What to Build

Containment Is Lying to You: Measuring AI Agents Like Employees — Druid AI

Building AI Agents with Real-Time Web Data — Yohan Raju, Bright Data

AI Agents Don't Read Your Policy Docs. They Hit Your APIs — Gravitee

Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge

Your AI Agent Has No Nervous System — Matt Gibiec, Dynatrace

Nobody Agrees About Agentic Development

The Software Factory: From Bug Report to Production Code — Davis Palmie, Factory

From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Build the Right Thing: Product Engineering (Part 1) — Kent C. Dodds, EpicProduct.engineer

LIVE: Poteto (creator of pstack) on shipping 1,000's of PR's a month at SpaceX

The State of AI in Software Development: Data from 400+ Orgs — Justin Reock, DX

The Death of the Code Review: What the Data Actually Says — Laurie Voss, Arize AI

AI Can Write the Proof. Who Checks It? — Leonardo de Moura

What product looks like when coding is solved | Geoff Charles (Ramp CPO)

Thinking in Platforms • Kasper von Grünberg & Luca Galante • GOTO 2026

Inside Steve Yegge's Software Factory: Lessons from Running 50 Agents

Why Your Computer Is Not Ready for AI Agents | The Next Endeavor 2026

Rethinking the software development process for an era of specs and AI agents

AI Skills with Matt Pocock

AI Runs My Entire Business: EASY Way To Use AI Agents In Your Work, Content & Life (Step by Step!)

Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition

Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked

How we built Grok Bot in a month | Roman Ugarte (SpaceXAI)

PyData Chicago Meetup: August 2026

Inside Anthropic's 200-Person Platform Team | Katelyn Lesse and Angela Jiang

This company has more AI agents than employees

The Data Structure Problem AI Coding Agents Can't See

The Era of Compound Engineering — Kieran Klaassen, Every/Cora

Prototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Company

The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo

AI Agents vs Business Rules: Which Should Make Decisions?

LIVE: Uncle Bob on Software Fundamentals in the Age of AI

AI Agents Gone Rogue? Build, Defend & Attack AI-Enabled Apps • Katie Paxton-Fear • YOW! 2025

Building Docs for Agents, Not Humans: Inside OpenWiki

How Unify cut its AI agent costs 95% in two weeks

Continual Learning: How AI Agents Get Better With Every Use | Arjun Karanam, Trajectory

Omnigent: Open-Source Meta-Harness for AI Agents | Matei Zaharia

Creator of uv, ty, Ruff: How Software Engineering Is Changing | Charlie Marsh

Anthropic Workshop: Build Agents That Run for Hours — Ash Prabaker & Andrew Wilson

Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI

Building pi in a World of Slop — Mario Zechner

What Everyone Missed About Gemini 3 w/ Salim, Dave & Alexander Wissner-Gross | EP#209

Accelerating Clinical Research and Commercialization with AI Agents

Salesforce Founder Gives the Truth on AI Agents w/ Marc Benioff | EP #141

Observed neighbors

Mathlib scaling

Reaching estimated 100M lines requires agent-integrated library development beyond human contribution capacity

1 source videos

AI Can Write the Proof. Who Checks It? — Leonardo de Moura

Related tagged insights

AI Agents Cut 3-Day Portfolio Builds to Minutes — Jack McDonald, Apollo & Michael Manapat, Rowspace

In regulated financi…

The useful operating…

Trust in an enterpri…

General-purpose mode…

Deep, rules-based le…

Deployment succeeded…

The Agent Works. Does Anyone Trust It? — Michele Grant, Leading at Scale

Separate the computa…

Autonomy should be a…

Trust rests on three…

Value claims must be…

Accountability is mo…

The Human Work Stand…

Go-live is evidence …

Muse Wonder: Zuckerberg and Wang's $100B AI

Active memory is fra…

Multimodality is arg…

A model gateway laye…

Frontier capability …

Pre-training and pos…

Andrew Ng on Coding Agents and Deciding What to Build

Autonomous agents wi…

An AI engineering sk…

Cognitive offloading…

Developer work is sh…

Uncertainty manageme…

Containment Is Lying to You: Measuring AI Agents Like Employees — Druid AI

Containment (share o…

The evaluation frame…

The maturity scale s…

Evaluation must insp…

Agent evaluation is …

A weighted 0-2 score…

Building AI Agents with Real-Time Web Data — Yohan Raju, Bright Data

Separating web-data …

Replacing hardcoded …

Traditional multi-la…

Web MCP functions as…

Scaling hardcoded sc…

MCP-mediated access …

Product-intelligence…

AI Agents Don't Read Your Policy Docs. They Hit Your APIs — Gravitee

Governance of agent …

Agent identity and t…

Semantic caching (Re…

Runaway cost from bu…

Shadow AI traffic fr…

Agents should be dec…

Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge

MCP-style live looku…

Context is not one s…

Every context node h…

Vendors/platforms ar…

The context selectio…

A 'context graph' is…

Retrieving more raw …

Your AI Agent Has No Nervous System — Matt Gibiec, Dynatrace

A graduated autonomy…

Production runtime c…

The same OpenTelemet…

A distinct failure m…

Independent verifica…

Agent value/ROI and …

Nobody Agrees About Agentic Development

LLMs exhibit a bias …

A verification frame…

Effective code revie…

Junior engineers usi…

Engineering is funda…

As AI lowers barrier…

The Software Factory: From Bug Report to Production Code — Davis Palmie, Factory

The real engineering…

A Software Factory i…

Adoption should star…

Model agnosticism me…

Agent readiness is a…

Token-based measurem…

Sovereign deployment…

From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Grade the outcome, n…

Error analysis must …

An LLM judge rubric …

Observability is a p…

Agents require span-…

Code evals and LLM-a…

Manual human review …

Build the Right Thing: Product Engineering (Part 1) — Kent C. Dodds, EpicProduct.engineer

Agent capability has…

Architecture is the …

Validation evidence …

'User error' is a mi…

Validate the smalles…

The loop between shi…

LIVE: Poteto (creator of pstack) on shipping 1,000's of PR's a month at SpaceX

The human's primary …

Agent workflows spli…

Strong type systems,…

Adoption follows a s…

Micromanaging agents…

As agents handle imp…

The State of AI in Software Development: Data from 400+ Orgs — Justin Reock, DX

Code generation is a…

Longitudinal measure…

AI adoption decouple…

Seniority changes to…

AI readiness is a pr…

Change failure rate …

The Death of the Code Review: What the Data Actually Says — Laurie Voss, Arize AI

Accelerating code ge…

Passing a test suite…

Automated reviewers …

A concrete mitigatio…

Review is being refa…

The economic asymmet…

What product looks like when coding is solved | Geoff Charles (Ramp CPO)

Solving coding does …

Bootstrapping an age…

Requirement-definiti…

Coding-agent effecti…

Agents delivered ins…

Coordination is trea…

Automating review an…

Thinking in Platforms • Kasper von Grünberg & Luca Galante • GOTO 2026

Agent productivity i…

Platform engineering…

The failure mode of …

Platform failure is …

The PATHS (Paths to …

The industrializatio…

Inside Steve Yegge's Software Factory: Lessons from Running 50 Agents

Multi-agent coding f…

Guardrail and fence …

As agent count grows…

Agents are heterogen…

The issue tracker sh…

Autonomous agents ov…

Enterprise adoption …

Why Your Computer Is Not Ready for AI Agents | The Next Endeavor 2026

Autonomous agents co…

Memory scaling is ph…

Modular system desig…

Workload placement b…

Agentic workloads re…

Rethinking the software development process for an era of specs and AI agents

Software development…

Agent traces create …

Agent output quality…

Spec-driven developm…

The developer-effect…

Agents are being dep…

AI Skills with Matt Pocock

Leading words — ters…

Because AI collapses…

Intent-based access …

Object-native full-t…

The /grill-me skill …

Existing project art…

AI Runs My Entire Business: EASY Way To Use AI Agents In Your Work, Content & Life (Step by Step!)

The playbook is a ru…

The Playbook Outline…

Playbooks compose hi…

Parallel background …

The claimed failure …

Claimed throughput r…

The playbook/skill a…

Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition

Strict static type s…

The quality ceiling …

Agents' comparative …

Line-by-line human r…

Sub-100ms hot-patchi…

Blitz decouples brow…

Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked

A production context…

'Satisfaction of sea…

Hand-curated context…

The cost of bad cont…

Token optimization v…

Karpathy's framing —…

How we built Grok Bot in a month | Roman Ugarte (SpaceXAI)

The architectural bo…

The speaker frames t…

Natural language is …

Delegation is modele…

The team manually on…

Isolating a 6-12 per…

PyData Chicago Meetup: August 2026

The harness, not the…

Multi-agent scaling …

LLM-based simulation…

Synthetic users syst…

Persona prompting is…

Inside Anthropic's 200-Person Platform Team | Katelyn Lesse and Angela Jiang

The binding constrai…

Production agents do…

Managed agent harnes…

Autonomous agents cr…

Rather than constrai…

This company has more AI agents than employees

Kantar decouples age…

The unit of agent de…

The primary supply o…

Adoption is framed a…

Enablement runs on a…

Kantar rolled out Co…

The Data Structure Problem AI Coding Agents Can't See

Per-feature failure …

The highest-leverage…

The experiment's har…

'Fold knowledge into…

Sync engine design d…

Because agents canno…

The Era of Compound Engineering — Kieran Klaassen, Every/Cora

The engineering bott…

A hard allocation in…

Memory content polic…

The workflow loop co…

Standardized slash-c…

The claim that imple…

Prototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Company

The overnight loop t…

The prompting interf…

Voice-to-text is use…

A non-specialist use…

Agent-generated code…

Coding agents are mo…

The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo

Code review benchmar…

Instruction-file gov…

Code review serves t…

'Artificial wisdom' …

The unit of review i…

Uncoordinated agents…

AI Agents vs Business Rules: Which Should Make Decisions?

The decision system …

Determinism is treat…

The routing criterio…

Guardrails and human…

The failure mode of …

LIVE: Uncle Bob on Software Fundamentals in the Age of AI

Context windows have…

Architectural modula…

A multi-agent pipeli…

There is an asymmetr…

Raw agent productivi…

Up-front grand plann…

AI Agents Gone Rogue? Build, Defend & Attack AI-Enabled Apps • Katie Paxton-Fear • YOW! 2025

An agentic stack exp…

Tool outputs are an …

Agent self-reports c…

AI-generated code cr…

LLM refusal training…

Offensive security a…

Building Docs for Agents, Not Humans: Inside OpenWiki

Typed, deterministic…

Documentation writte…

The generation pipel…

Mermaid diagrams had…

The gains are asymme…

The project frames g…

How Unify cut its AI agent costs 95% in two weeks

Collapsing a multi-s…

Prompt caching canno…

Memory is managed as…

Tenant isolation is …

LLM-as-a-judge evalu…

Unify gives agents n…

Continual Learning: How AI Agents Get Better With Every Use | Arjun Karanam, Trajectory

Trace fidelity is a …

Product interface af…

Evaluations must be …

The harness is a tra…

Open-weight models a…

Production agents em…

A packaged continual…

Omnigent: Open-Source Meta-Harness for AI Agents | Matei Zaharia

A meta-harness that …

Contextual security …

Risk scoring enables…

Sandboxing the entir…

A runner component t…

Creator of uv, ty, Ruff: How Software Engineering Is Changing | Charlie Marsh

AI agents have colla…

Metric-optimizing ag…

With agents as the a…

Heavy reliance on ag…

Astral chose Rust fo…

The developer-tool b…

Anthropic Workshop: Build Agents That Run for Hours — Ash Prabaker & Andrew Wilson

Separating the build…

The three-agent harn…

Harness complexity i…

Compaction is not a …

Subjective qualities…

The primary debuggin…

Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI

Non-functional requi…

Repository structure…

Parallel agents shif…

The binding constrai…

The engineer's role …

Building pi in a World of Slop — Mario Zechner

Terminal Bench shows…

Coding harnesses oft…

Injecting compiler/L…

A coding agent harne…

A harness with zero …

What Everyone Missed About Gemini 3 w/ Salim, Dave & Alexander Wissner-Gross | EP#209

Infinite code contex…

Agent evaluation is …

Generative user inte…

Autonomous software …

Frontier model relea…

Legacy modernization…

Accelerating Clinical Research and Commercialization with AI Agents

A healthcare-grade a…

The platform decompo…

The Field Companion …

The architecture inc…

The platform uses NV…

Salesforce Founder Gives the Truth on AI Agents w/ Marc Benioff | EP #141

Salesforce's enterpr…

Salesforce's produce…

A reported 30% engin…

Adopting digital lab…