← all topics

💻 Code Generation

AI coding tools and agents. Cursor, Devin, Copilot internals, SWE-bench, agentic refactoring, repo-scale understanding.

130 videos · coding-agentscode-generationai-codingcopilotclaude-codeagents

The workflow

flowchart LR
    A[Task / prompt] --> B[Retrieve repo context<br/>files + symbols]
    B --> C[LLM emits diff<br/>or whole file]
    C --> D[Execute / test<br/>in sandbox]
    D --> E{Pass?}
    E -->|No| F[Self-repair<br/>read error → patch]
    F --> C
    E -->|Yes| G[PR / commit<br/>+ review]

Coding agents are the first place where AI delivers full economic value. The eval is "did the test pass?"

Key takeaways

AI coding works best when paired with classical software discipline — shared design concepts, ubiquitous language, and resistance to entropy.
Treat LLM context as a finite 'smart zone' and structure coding workflows (small tasks, looping plans, compaction) to stay inside it.
Advanced context engineering — small, intentional, reviewed context windows — beats raw model power for complex brownfield coding work.
AI codegen optimizes the mechanics Brooks said were never the bottleneck, so the only sustainable fix is to keep doing the hard human work of designing simple, untangled systems.
Rigorous private-repo measurement shows AI coding tools yield a real but modest ~15–20% net productivity gain, largely offset by rework on AI-generated code.
Coding-agent harnesses should be tiny, observable, and self-modifiable so the model — already trained as a coding agent — owns its own context.

Videos (130)

"Software Fundamentals Matter More Than Ever" — Matt Pocock

AI coding works best when paired with classical software discipline — shared design concepts, ubiquitous language, and resistance to entropy.

666.1K views · Apr 23, 2026

Full Walkthrough: Workflow for AI Coding — Matt Pocock

Treat LLM context as a finite 'smart zone' and structure coding workflows (small tasks, looping plans, compaction) to stay inside it.

597.5K views · Apr 24, 2026

No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer

Advanced context engineering — small, intentional, reviewed context windows — beats raw model power for complex brownfield coding work.

544.7K views · Dec 02, 2025

The Infinite Software Crisis – Jake Nations, Netflix

AI codegen optimizes the mechanics Brooks said were never the bottleneck, so the only sustainable fix is to keep doing the hard human work of designing simple, untangled systems.

389.1K views · Dec 20, 2025

Does AI Actually Boost Developer Productivity? (100k Devs Study) - Yegor Denisov-Blanch, Stanford

Rigorous private-repo measurement shows AI coding tools yield a real but modest ~15–20% net productivity gain, largely offset by rework on AI-generated code.

300.1K views · Jul 23, 2025

Building pi in a World of Slop — Mario Zechner

Coding-agent harnesses should be tiny, observable, and self-modifiable so the model — already trained as a coding agent — owns its own context.

281.5K views · Apr 16, 2026

Claude Code & the evolution of agentic coding — Boris Cherny, Anthropic

Coding models are advancing faster than coding products, so Anthropic ships Claude Code as a minimal unopinionated surface to let users discover the right agentic UX.

133.7K views · Jul 04, 2025

Understanding is the new bottleneck — Geoffrey Litt, Notion

Use AI to teach you the systems it changes so faster coding does not erode your ability to shape the project.

127.8K views · Jul 10, 2026

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

Treat agents as infinitely-parallel implementers and invest your time in writing guardrails and persona-oriented docs that make 'a good job' legible to them.

117.1K views · Apr 17, 2026

Defying Gravity - Kevin Hou, Google DeepMind

Antigravity reframes the IDE around an agent manager that orchestrates editor and browser agents, leveraging Gemini 3's longer-horizon multimodal tool use.

104.8K views · Dec 02, 2025

How Claude Code Works - Jared Zoneraich, PromptLayer

Claude Code works because it strips scaffolding and trusts a tool-calling-tuned model in a simple agentic loop — the lesson is delete complexity, not add it.

92.0K views · Dec 26, 2025

Everything we knew about software has changed — Theo Browne, @t3dotgg ​

Expand task ambition and reconsider inherited workflows to benefit from increasingly capable coding agents.

91.0K views · Jul 08, 2026

From Vibe Coding To Vibe Engineering – Kitze, Sizzy

Embrace AI-assisted coding but layer engineering practices on top so you graduate from vibe coding's gambling loop to disciplined vibe engineering.

90.6K views · Dec 14, 2025

Vibes won't cut it — Chris Kelly, Augment Code

AI accelerates code generation but production software engineering — changing systems safely at scale — still requires human judgment, context, and rigorous practices.

86.8K views · Aug 03, 2025

"The engineer of the future is the person who is able to choose what is worth doing." — Addy Osmani

Focus engineering judgment on evidence-backed decisions and ownership of production outcomes.

83.0K views · Jul 14, 2026

How Windsurf writes 90% of your code with an Agentic IDE - Kevin Hou, Windsurf

Tight editor-agent integration via a shared action timeline is what lets Windsurf write the majority of code while keeping users in flow.

82.5K views · Mar 11, 2025

Agentic Engineering: Working With AI, Not Just Using It — Brendan O'Leary

Productivity gains from AI coding come from explicit context engineering and treating agents like fast but judgment-poor juniors you must direct.

79.4K views · Apr 07, 2026

From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWS

Large agent-assisted productivity gains require deliberate workflow and codebase changes, with attention to how results are measured.

75.4K views · Aug 28, 2026

The Golden Age of AI Engineering — Alexander Embiricos & Romain Huet & Peter Steinberger, OpenAI

Build agent workflows that span the whole job while preserving engineers' ability to inspect, steer, and make product decisions.

75.0K views · Jul 09, 2026

AI Engineering at Jane Street - John Crepezzi

For obscure internal languages, custom fine-tuning on workspace snapshots + build-state transitions beats off-the-shelf coding models.

70.5K views · Mar 28, 2025

Harness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayer

Treat unattended software factories cautiously in complex codebases because harnesses cannot eliminate every model and verification limitation.

66.2K views · Jul 23, 2026

2026: The Year The IDE Died — Steve Yegge & Gene Kim, Authors, Vibe Coding

The future of coding tools is swarms of specialized agents orchestrated through a UI, not a single muscular agent inside an IDE.

53.5K views · Dec 06, 2025

Making Codebases Agent Ready – Eno Reyes, Factory AI

The bottleneck for agent productivity in enterprises is automated-validation rigor in the codebase, not which coding agent you buy.

49.9K views · Dec 22, 2025

Amp Code: Next Generation AI Coding – Beyang Liu, Amp Code

Effective coding agents come from curated tools, dedicated subagents for search/reasoning, and a review UI — not from piling on MCP servers.

48.5K views · Dec 22, 2025

Collaborative AI Engineering: One Dev, Two Dozen Agents, Zero Alignment — Maggie Appleton, GitHub

Coding agents have collapsed implementation cost so alignment must become continuous and multiplayer — not a PR-time afterthought.

48.3K views · Apr 26, 2026

Spec-Driven Development: Agentic Coding at FAANG Scale and Quality — Al Harris, Amazon Kiro

Spec-driven development with EARS requirements and property-based testing gives agentic coding a verifiable throughline from intent to shipped code.

47.2K views · Jan 09, 2026

Self Coding Agents — Colin Flaherty, Augment Code

An AI coding agent given basic process and tool primitives can write the bulk of its own codebase, including features, tests, and self-profiling optimizations.

44.8K views · Apr 21, 2025

The AI Skill I Rely On Daily — Priscila Andre de Oliveira, Sentry

A reusable code-comprehension skill can deliver substantial daily value by making unfamiliar and changing systems easier to understand.

34.3K views · May 27, 2026

OpenAI Codex Masterclass — Vaibhav Srivastav & Katia Gil Guzman

Codex is positioned as a full software-engineering teammate across surfaces, with sub-agents, work trees, and plugins as the new productivity primitives.

33.9K views · Apr 29, 2026

BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike — Michal Cichra, Safe Intelligence

Make product intent durable and enforceable with linked decision records, executable behaviors, and automated feedback.

29.5K views · Jun 03, 2026

Building Cursor Composer – Lee Robinson, Cursor

Cursor Composer trades raw frontier-model intelligence for 4x speed by RL-training on a production-mirroring environment with custom MoE kernels.

24.8K views · Dec 02, 2025

The emerging skillset of wielding coding agents — Beyang Liu, Sourcegraph / Amp

Coding agents need a new operating mode (direct edits, oversight not approval, usage-based pricing, model-coupled scaffolding) — old chatbot intuitions actively hurt.

23.6K views · Jun 30, 2025

The State of AI Code Quality: Hype vs Reality — Itamar Friedman, Qodo

You don't break the AI productivity glass ceiling with better autocomplete — you break it with agentic, dynamically-learning quality workflows across the whole SDLC.

23.1K views · Dec 11, 2025

How Anthropic Builds: Lessons from Labs — Mike Krieger, Anthropic

Delegate ambitious outcomes while supplying the tools, verification loops, and rollout controls needed to reach them reliably.

22.7K views · Aug 27, 2026

Developer Experience in the Age of AI Coding Agents – Max Kanat-Alexander, Capital One

Make your codebase, tooling, and documentation match how the rest of the industry works so agents inherit decades of training-set fluency.

22.5K views · Dec 23, 2025

From Writing Code to Designing Systems: How the Developer Role is Changing — Chris Noring, Microsoft

Treat agent workflows and repository guardrails as core engineering work as implementation becomes increasingly delegated.

22.3K views · Jul 11, 2026

Building your own software factory — Eric Zakariasson, Cursor

Treat your codebase like a factory: structure for discoverability, add guardrails reactively, and invest in verifiable end-to-end checks.

21.3K views · Apr 28, 2026

Software Development Agents: What Works and What Doesn't - Robert Brennan, OpenHands

Coding agents become genuinely productive when you scope tasks tightly, sandbox aggressively, and treat the agent as the inner-loop coder while humans own architecture.

20.2K views · Jul 25, 2025

In the Land of AI Agents, the Verifiers Are King — Tariq Shaukat, Sonar

Embed verification into the generation loop so faster code production translates into maintainable, reliable software.

19.4K views · Jul 20, 2026

Loop Engineering from First Principles — Kyle Mistele, HumanLayer

Engineer coding loops around measurable targets and small verified changes so automation improves reviewability and system stability.

17.5K views · Jul 25, 2026

Devin 2.0 and the Future of SWE - Scott Wu, Cognition

Coding agents are scaling on a 70-day doubling curve; product strategy must re-baseline every model generation as Devin moves from migrations to multi-file feature work.

17.0K views · Jul 25, 2025

The Great Loops Debate — Dex Horthy, Geoff Huntley, Ian Livingstone, Greg Pstrucha, @insecure-agents

Judge loop automation by task boundaries, feedback quality, and engineering discipline rather than claims of effortless autonomy.

16.8K views · Jul 17, 2026

Your Coding Agent Should Do AI System Engineering — Ben Burtenshaw, Hugging Face

Pair coding agents with maintained examples, hardware benchmarks, and reusable distribution formats to make AI systems optimization practical.

16.6K views · May 21, 2026

Why Rust is the Ideal Language for Vibe-Coding — Daniel Szoke, Sentry

Choose language constraints that catch classes of agent mistakes automatically, rather than optimizing only for easy initial code generation.

16.3K views · May 27, 2026

Claude Fable, Claude Tag, and Anthropic's Culture — Cat Wu & Thariq Shihipar ft Simon Willison

More capable coding agents shift human effort toward product judgment and make persistent, collaborative automation a practical work surface.

16.2K views · Jul 15, 2026

Software Engineering Is Becoming Plan and Review — Louis Knight-Webb, Vibe Kanban

As coding agents take longer per run, your job collapses to planning and reviewing — invest in specs to amortize review cost across parallel agents.

15.7K views · May 02, 2026

Real World Development with GitHub Copilot and VS Code — Harald Kirschner, Christopher Harrison

Vibe coding maps to a maturity curve from YOLO prototyping to disciplined guardrails — VS Code + Copilot agent mode supports all three stages.

15.7K views · Aug 03, 2025

Rust is the language of the AGI - Michael Yuan

Rust's strict compiler turns 'hard to write' into a strong reward signal, making it the ideal target language when machines, not humans, are doing most of the coding.

15.5K views · Jun 03, 2025

The Making of Devin by Cognition AI: Scott Wu

Devin demonstrates that autonomous software engineers using human tooling (terminal, git, PRs) are the next phase beyond code-completion.

15.2K views · Jul 11, 2024

Beyond the Prototype: Using AI to Write High-Quality Code - Josh Albrecht, Imbue

Quality AI-generated code comes from synchronous prevention plus detection loops — plan, spec, lint, test, LLM-review — not from picking the smartest base model.

14.6K views · Jul 25, 2025

Building AI Agents with Real ROI in the Enterprise SDLC: Bruno (Booking.com) & Beyang (Sourcegraph)

Real enterprise AI-coding ROI comes from picking honest KPIs, training daily users, and giving agents deep codebase context for legacy migration work.

14.5K views · Apr 08, 2025

Replacing 12K LoC with a 200 LoC Skill — David Gomes, Cursor

Cursor replaced ~12K lines of worktree/best-of-N feature code with ~200 lines of markdown agent skills, demonstrating skills can collapse complex agent features.

13.9K views · Apr 30, 2026

Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked

Reliable background coding agents need a real context engine — curated, relationship-aware organizational knowledge — not just RAG or MCP plumbing.

12.8K views · May 03, 2026

Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff — Vincent Koc, OpenClaw

High-volume agent coding shifts engineering effort toward architecture, acceptance criteria, and deciding which changes belong in the product.

12.5K views · Jun 05, 2026

"Software engineering is not about writing code" — Benoit Schillings, Google DeepMind VP of Research

As code generation becomes cheaper, engineering value concentrates in specification, architecture, and managing system complexity.

11.9K views · Jul 17, 2026

Guide, Verify, Solve — Anirban Chatterjee, Sonar

Sustained AI coding productivity requires systematic quality verification matched to the application’s needs.

11.3K views · Aug 09, 2026

Recursive Coding Agents - Raymond Weitekamp, OpenProse

Reliable agent outcomes depend on how work and context are decomposed and verified, not only on model intelligence.

11.2K views · Jun 25, 2026

Fast Models Need Slow Developers — Sarah Chieng, Cerebras

Faster coding models make deliberate development and verification more valuable because unchecked errors can accumulate faster too.

10.6K views · May 22, 2026

Piloting agents in GitHub Copilot - Christopher Harrison, Microsoft

Treat GitHub Copilot like a pair programmer — readable code, clear instructions and explicit context matter more than clever prompting.

10.4K views · Jul 26, 2025

Codex, Behind the Harness — Dominik Kundel, OpenAI

A capable harness manages context and asynchronous actions explicitly while exposing reusable interfaces around the model.

9.6K views · Aug 10, 2026

Beyond Code Coverage: Functionality Testing with Playwright MCP — Marlene Mhangami, Microsoft

Use AI to accelerate behavioral testing and implementation while reserving deliberate effort for refactoring and code quality.

9.2K views · May 16, 2026

Vibe Engineering Effect Apps — Michael Arnaldi, Effectful

To make coding agents useful on undocumented libraries, drop the library repo straight into your project so the agent's code-focused training kicks in.

8.2K views · May 07, 2026

How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage) — Eyal Blum, Figma

Scale coding-agent adoption by investing in verifiable plans and shared engineering knowledge while addressing the human costs of the transition.

8.1K views · Aug 28, 2026

How to Generate Mergeable Code with a Context Engine — Peter Werry, Unblocked

Mergeable code requires organizational intent and historical constraints to reach agents in a focused, inspectable form.

8.0K views · Aug 27, 2026

Future-Proof Coding Agents – Bill Chen & Brian Fioca, OpenAI

Don't port prompts across models — match instructions to the model's trained habits, or use a co-developed model+harness like Codex.

7.9K views · Dec 05, 2025

How to Kill the Code Review — Ankit Jain, Aviator

Move review toward intent, behavioral evidence, and reusable checks while preserving the collaboration that line-by-line review previously supported.

7.8K views · Aug 17, 2026

Windsurf everywhere, doing everything, all at once - Kevin Hou, Windsurf

The next leap for AI coding tools is a shared human-AI timeline that lets parallel agents understand context and act without losing the user's intent.

7.8K views · Jun 23, 2025

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

Capture your judgments and corrections as reusable knowledge so each completed task improves the next one.

7.8K views · Aug 20, 2026

Your Code Has Bugs. Lean4 Has Proofs: Formal Verification for Engineers — Varun Pant, AWS

Use carefully reviewed specifications and machine-checked proofs for critical properties, while distinguishing proved models from implementations tested against them.

7.6K views · Aug 28, 2026

Using Spec-Driven Development for Production Workflows - Erik Hanchett, AWS

Use reviewed specifications as durable guidance for coding agents, with context discipline and human accountability throughout implementation.

7.6K views · Jun 28, 2026

RL for Autonomous Coding — Aakanksha Chowdhery, Reflection.ai

Reinforcement learning with automated verifiers (tests, compilers) is the unlock for autonomous coding because correctness can be checked cheaply at scale.

7.3K views · Jul 16, 2025

Self Driving Products: Product Signals to Pull Requests — Joshua Snyder, PostHog

Turn observability into actionable changes by grouping signals around underlying problems and grounding agent investigation in product context.

6.8K views · Jun 10, 2026

fighting slop with slop — Vaibhav Gupta, Boundary

Replace exhaustive manual code reading with strong design review, architectural invariants, and continuous agent-driven testing.

6.4K views · Jul 31, 2026

Your Coding Agent Just Got Cloned And Your Brain Isn't Ready - Rustin Banks, Google Jules

Async cloud coding agents like Jules unlock parallel multitasking and multi-variation development, but require AI at both ends of the workflow to remain sane.

6.3K views · Jul 25, 2025

Vibe Coding with Confidence — Itamar Friedman, Qodo

CLI-based agentic workflows that fold review and testing into authoring are the path from vibe-coded prototypes to trustworthy enterprise software.

6.2K views · Aug 06, 2025

Building uReview, Uber’s Multi-Agent Code Review Engine — Will Bond & Ameya Ketkar, Uber

Automated code review scales best when actionable feedback, team context, and detailed operational measurements reinforce each other.

6.0K views · Aug 28, 2026

Ship Production Software in Minutes, Not Months — Eno Reyes, Factory

Agent-native development means standardizing how your org thinks so droids can ingest your context and orchestrate work across the whole software lifecycle.

6.0K views · Jul 25, 2025

Code Generation and Maintenance at Scale: Morgante Pell

Large-scale code migrations need static analysis + semantic search + agentic execution — vanilla embedding RAG retrieves too much irrelevant code to be useful.

5.3K views · Oct 17, 2024

AI powered entomology: Lessons from millions of AI code reviews — Tomas Reimers, Graphite

AI code review only works when comments stay in the 'LLM-can-catch AND human-wants-it' quadrant — measured by downvotes plus whether developers actually act on them.

4.6K views · Jul 22, 2025

Should AI Engineers Still Read Code in 2026? The Z/L Continuum — Alex Volkov, ThursdAI

Higher code-generation throughput makes deliberate review and engineering accountability more consequential.

4.5K views · Jul 10, 2026

Agents, codebases, and teams — Aditya Khandelwal, Amazon AGI Lab

Treat effective team use of coding agents as an organizational and harness-engineering responsibility.

4.0K views · Aug 11, 2026

Multiplayer agentic engineering — Arjun Singh, Superconductor

Make agent sessions shared, persistent, and visible across the places where teams already collaborate.

3.6K views · Aug 09, 2026

AI Agents for Performance: Ship Faster, Pay Less — Rajat Shah, Netflix

Ground performance agents in production profiles and matching source revisions so optimization starts from measured bottlenecks.

3.5K views · Jul 28, 2026

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

Reliable automated code review requires shared organizational knowledge, consistent governance, and evidence humans can inspect.

3.3K views · Aug 20, 2026

Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs

Reassess refactoring workflows as agents improve, while measuring maintainability and correctness alongside execution speed.

3.3K views · Aug 08, 2026

How Building with AI Can Double the Throughput of Your Engineering Team — Brian Scanlan, Intercom

Large-scale AI productivity gains require a staffed organizational program, shared tooling, and company-specific context.

3.2K views · May 15, 2026

RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI

Treat a large repository as structured data that an agent can query programmatically instead of loading it wholesale into context.

3.2K views · Jul 12, 2026

LLM codegen fails and how to stop 'em — Danilo Campos, PostHog

Fight LLM codegen hallucination by tool-calling fresh markdown docs into context — context windows are big enough that RAG isn't required.

3.0K views · Apr 30, 2026

The Cure for the Vibe Coding Hangover — Corey J. Gallon, Rexmore

Replace vibes with discipline — specs not prompts, atomic features, dependency-driven order, and executable tests before any agent writes code.

3.0K views · Nov 24, 2025

How to Improve your Vibe Coding — Ian Butler

Vibe coding only works with explicit rules, careful context management, and thinking models — naive setups generate alert fatigue from false positives.

2.8K views · Aug 03, 2025

GitHub Copilot: The World's Most Widely Adopted AI Developer Tool

Copilot has become a full-stack developer assistant — IDE completion, chat, PR summaries, knowledge-base Q&A — across every major IDE and SCM.

2.7K views · Feb 06, 2025

Your coding agent doesn't always follow your rules — Talha Sheikh, Checkout.com

Turn requirements into executable verification contracts so the user is no longer the only enforcement layer.

2.5K views · Jul 08, 2026

How We Built Zeta2: Training an Edit Prediction Model in Production — Ben Kunkle, Zed

Train specialized coding models with repaired teacher data, carefully filtered user outcomes, and production validation.

2.4K views · May 30, 2026

Welcome to AIE CODE - Jed Borovik, Google DeepMind

AIE CODE Summit positions AI coding as the single most important applied-AI problem and brings a focused, single-track audience together around it.

2.4K views · Jan 05, 2026

Building AI For All: Amjad Masad & Michele Catasta

Replit is bundling AI coding assistance plus inference (Model Farm) free to all users to ensure the next billion developers aren't gated from AI-enhanced programming.

2.4K views · Oct 23, 2023

Enhancing Quality and Security in CI: Gunjan Patel

Use CI's slack time as the venue for slow, deliberate AI passes (rename/comment/test/security) — Copilot does the fast thinking, GhostPilot does the slow thinking.

2.2K views · Nov 27, 2024

A Genius With Amnesia - Victor Savkin, Nx

Cross-repository context and persistent work history reduce the human effort required to coordinate coding agents.

2.2K views · Jun 26, 2026

GPT Web App Generator - 10,000 apps created in a month: Matija Sosic

Constraining the codegen target (Wasp + React/Node) and tiering GPT-4 planning with GPT-3.5 implementation produces cheap, reliable full-stack app generation.

2.2K views · Jan 26, 2024

The Many Ends of Programming - Ray Myers

Map AI's impact on programming across six scenarios (from extreme completion to garbage pile) instead of treating it as a binary apocalypse.

2.1K views · Jun 10, 2025

To the moon! Navigating deep context in legacy code with Augment Agent — Forrest Brazeal, Matt Ball

Augment Agent positions its proprietary context engine as the real differentiator for AI on legacy codebases — model quality matters less than what you feed it.

2.0K views · Jun 27, 2025

Content Is Code - Matt Palmer, Conductor

When code generation becomes cheap, organizational structure and careful maintenance become the bottlenecks for high-quality content.

2.0K views · Jul 18, 2026

ReviewDebt: a practical framework for scoring every pull request — Sachin Gupta, Ebay

Measure the verification burden of generated changes alongside coding speed to keep review debt visible.

2.0K views · Jul 12, 2026

Reverse engineering a Viking VOIP phone protocol with Claude Code — Boris Starkov, Eleven Labs

Coding agents can solve legacy integration problems by combining protocol exploration with observed traffic and validation.

1.9K views · May 29, 2026

The Code AI Maturity Model and What It Means For You: Ado Kukic

Code AI follows a six-level autonomy ladder from autocomplete to full SDLC ownership — most teams sit at L2-L3 today.

1.9K views · Feb 13, 2024

What Data from 20m Pull Requests Reveal About AI Transformation — Nick Arcolano, Jellyfish

Interactive coding tools are delivering measurable 2x throughput and faster cycles without quality regressions, while fully autonomous agents remain pre-production at most companies.

1.8K views · Nov 24, 2025

Supercharging developer workflow with Amazon Q Developer - Vikash Agrawal

Amazon Q Developer covers the full SDLC — CLI + IDE slash commands plus GitHub and AWS console integration — letting one developer hand off planning, testing, docs and deploy to the agent.

1.8K views · Jun 10, 2025

The Prompt is the Platform - Dominik Tornow, Resonate HQ

Agents can help design reliable systems when abstract specifications are connected to implementation through precise simulation feedback.

1.8K views · Jun 29, 2026

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

Technical leaders can use well-contextualized autonomous runs to turn strategic judgment into working prototypes despite fragmented schedules.

1.7K views · Aug 20, 2026

Vision: Zero Bugs — Johann Schleier-Smith, Temporal

Aerospace shows zero-bug software is possible with N-version, formal-method, and process-driven engineering — a discipline AI-generated code increasingly needs.

1.7K views · Nov 24, 2025

Mastering Engineering Flow with Windsurf - Eashan Sinha, Windsurf

Windsurf bets that real productivity gains come from tracking implicit user intent and pairing agentic tool use with explicit workflows, not just better chat.

1.6K views · Jun 27, 2025

The AI Evolution: Mario Rodriguez, GitHub

GitHub Copilot's $100M+ ARR rests on UX (ghost text), latency engineering and Codex/GPT-3.5 — not just the model — and post-PMF success requires global infra and rigorous online evals.

1.5K views · Nov 07, 2023

Move Fast Break Nothing: Dedy Kredo

Reliable codegen needs a generator+critic pair: behavior-driven tests plus automated review flag the security and correctness issues humans miss.

1.5K views · Nov 08, 2023

Your agent is blindfolded — Johan Lajili, Poolside AI

Give coding agents the ability to observe and test the actual application so they can correct their own mistakes.

1.5K views · Jul 08, 2026

Copilots Everywhere: Thomas Dohmke and Eugene Yan

GitHub's bet is human-centric copilots that bridge issue-to-PR while keeping the developer in flow — augmentation, not autonomous replacement.

1.3K views · Jul 26, 2024

The Rise of the AI Software Engineer: Jesse Han

Morph's bet: combine static analysis + embeddings + graphs into a queryable code index that both retrieves context for any coding agent and generates fine-tuning data.

1.3K views · Feb 05, 2025

Develop at Idea Velocity - Jeffrey Lee-Chan, Snapchat

Persistent coordination, isolated coding workers, and strong feedback loops can reduce the friction between an idea and a working change.

1.3K views · Jul 11, 2026

Mentoring the Machine — Eric Hou, Augment Code

Engineers should treat coding agents like mentees — invest in teaching them the codebase so they absorb the firefighting that destroys deep work.

1.2K views · Jul 24, 2025

[Full Workshop] Vibe Coding at Scale: Customizing AI Assistants for Enterprise Environments

Move enterprises through yolo -> structured -> spectrum vibes by adding guardrails (workspace settings, popular stacks, auto-approval policies) without killing the creative speed.

1.2K views · Jun 27, 2025

How Coding Agents change Software Development Forever - Hailong Zhang

Effective coding agents are narrow, evaluation-grounded, and built on a shared agent-OS abstraction — not monolithic 'software engineer' bots.

1.2K views · Feb 22, 2025

Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL — Ahmad Awais, CommandCode

Coding agents need a learned, inspectable 'taste' layer — meta neuro-symbolic preference modeling — to move beyond sloppy defaults and brittle rules files.

1.1K views · Nov 24, 2025

Vibe Coding at Scale: Customizing AI Assistants for Enterprise Environments - Harald Kirshner,

Enterprise vibe coding works when you graduate from YOLO mode to templates plus MCP-based tools that constrain agents to your stack and conventions.

1.1K views · Jun 27, 2025

Collaborating with Agents in your Software Dev Workflow - Jon Peck & Christopher Harrison, Microsoft

Treat GitHub Copilot as a pair programmer reading your code — better naming, comments, and explicit intent are still the highest-leverage prompt-engineering for it.

1.1K views · Jun 27, 2025

[Workshop from Microsoft] Github Copilot - The World's Most Widely Adopted AI Developer Tool

GitHub Copilot's effectiveness leans heavily on the context (open tabs, comments, examples) developers provide; chat unlocks broader code Q&A while business code stays out of training.

829 views · Feb 07, 2025

We Gave an Agent Production Code Access and Then Tried to Sleep at Night — Moritz Johner, Form3

Production patching agents should operate inside deterministic orchestration that limits edits and owns publication, verification, and escalation.

775 views · Jul 20, 2026

The Eyes Are The (Context) Window to The Soul: How Windsurf Gets to Know You — Sam Fertig, Windsurf

Coding agents that 'know you' rely on heuristics (user behavior) + hard evidence (codebase) plus relevance-first context retrieval — not bigger windows.

702 views · Jun 27, 2025

The Agent Awakens: Collaborative Development with Copilot - Christopher Harrison, GitHub

Treat GitHub Copilot like an AI pair programmer — clear code, clear intent, and pick the right mode from completions to autonomous coding agent.

649 views · Jun 27, 2025

Don't get one-shotted: Use AI to test, review, merge, and deploy code — Tomas Reimers, Graphite

Build AI-native outer-loop tooling (review, CI, merge, deploy) because the inner-loop speedup is creating a review bottleneck and security risk.

595 views · Jun 27, 2025

Unlocking AI Powered DevOps Within Your Organization — Jon Peck, GitHub

Roll out AI DevOps by training brownfield prompting habits, codifying team standards in copilot-instructions.md, and curating exemplar knowledge bases.

582 views · Jun 27, 2025

GitHub Next Explorations: Rahul Pandita

GitHub Next bets on staged exploration: code-completion is evolving to multi-location 'Next Edit Suggestions' and to full inner-loop task completion via Copilot Workspace.

490 views · Feb 08, 2025

GitHub's AI Powered Security Platform: Sarah Khalife

GitHub is shifting from Copilot-only AI to AI embedded across the platform, with AppSec autofix and triage as a major investment area.

323 views · Feb 08, 2025