Simon Maple

Claude Code: The Six-Reaction Origin Story It started as a side project that got six reactions on Slack. A year later, it's writing the majority of Anthropic's product code. Lamis Mukta from Anthropic tells the origin story of Claude Code, and why the "worst" launches sometimes become the biggest ones. Watch the full episode at tessl.co/00r or listen wherever you get your podcasts.

@PatsKam Next you’ll tell me that undermorrow means today! 🤣 New word learnt, thank you!

Wait why do so many people not know that there is a word in English for “the day after tomorrow”??? 😭

@jscraik @liran_tal @paw_lean @georgepickett @OpenAIDevs @romainhuet Looks nice! Very sharp!

Started to prototype my portfolio design With Codex.app, what do people think?

@dipankarsarkar @Docker @shelajev @jbaruch @tessl_io This is why we run evals with and without the skills and provide an impact score. For sure one of the most valuable signals

@Docker @shelajev @jbaruch @tessl_io The token cost is the easy half to measure. The hard half: did the agent finish because of that skill, or in spite of it. Without a counterfactual run you're just trusting vibes. Skill registries only matter once you can attribute outcomes back to them.

The interesting part of AI-native development isn't writing another prompt. It's knowing whether a skill is actually improving your agent - or just adding more tokens. @shelajev and @jbaruch of @tessl_io discuss evals, skill registries, and context engineering: bit.ly/4eKPWX8

@stabler_james @MJAbbottLtd @PremierPitches @ReadingFC Hey James! Looking good. How will it fare with all the hot weather we’re having right now, are you having to keep it soaked with water or covering from the heat?

The pitch is done. New rootzone, new drainage, new heating, new irrigation. Seed went down on Saturday, sheets on today. Plenty of other works still going on, but the pitch is now left alone to grow-in. Thank you @MJAbbottLtd @PremierPitches @ReadingFC

Most teams have code reviews, CI pipelines, security checks, and deployment processes. Then they hand their coding agents a collection of prompts and skills with none of that. Join Simon Maple at AI Engineer SF for a session on why skills are becoming a critical part of the software stack, and why they deserve the same engineering discipline we've spent decades building around code. June 30, 2026 • 10:30am - 11:30am at Booth L-G48 Learn what happens when agent skills are versioned, reviewed, evaluated, and managed like production code, and why that shift is becoming essential for teams building with AI. See you at the Tessl booth.

Almost everyone wrote his own agent skill at this point, so no wonder we arrived here: a package manager for skills - tessl. Might be worth checking out, thanks @sjmaple #devoxxPL #goodtobehere

@advocatemack @DevoxxPL lol, yeh, the room was tiny! 🤣

Skills are the new code... 🧠 I've always thought that the more context you give your coding agents, the better. Turns out there is a sweet spot, a "goldilocks zone" of context, as @sjmaple put it at @DevoxxPL. Pretty wild to see the difference a well-written skills file can make on an agent's output. Shout out @tessl_io! too bad the room was so small.

@advocatemack @IOHelpMe @DevoxxPL Thanks for joining the session! Good to meet up in person and chat!

@IOHelpMe @sjmaple @DevoxxPL Totally agree… at least now 24 hours ago I was clueless

"𝐂𝐨𝐝𝐞 𝐩𝐫𝐨𝐝𝐮𝐜𝐭𝐢𝐨𝐧 𝐢𝐬 𝐧𝐨 𝐥𝐨𝐧𝐠𝐞𝐫 𝐭𝐡𝐞 𝐛𝐨𝐭𝐭𝐥𝐞𝐧𝐞𝐜𝐤." In our latest AI Native Dev conversation, Ryan Lopopolo (@_lopopolo) from @OpenAI explains why engineering teams need to rethink where they spend their time. As coding agents get better, the highest leverage work shifts from implementation to shaping the environment around it: defining clear interfaces, capturing team knowledge, creating feedback loops, and building systems that help agents make good decisions consistently. Ryan shared how his team went from roughly 3.5 PRs per engineer per week to around 70 as models and workflows improved. The hard part is no longer generating code. It's creating the context, guardrails, and workflows that turn code generation into reliable software delivery. Watch the full conversation or listen on YouTube, Spotify, or Apple Podcasts. Links in the comments.

@Timur_Yessenov @tessl_io @_lopopolo @OpenAI For sure, I think this is the only approach that will make humans actually focus on code reviews, where we're not throwing batches of reviews at people, but rather focusing them on key changes/decisions.

@sjmaple @tessl_io @_lopopolo @OpenAI that’s the part I’d watch too. human-less review works for boring invariants, but I still want a named owner for tradeoffs: architecture, product risk, weird edge cases. otherwise review turns into another green check.

@Timur_Yessenov @tessl_io @_lopopolo @OpenAI Part of the discussion was also about how they also do human-less code reviews a lot of the time. Super interesting chat

@tessl_io @_lopopolo @OpenAI The 70 PR/week number only matters if review doesn't become a swamp. My test: can each PR arrive with the changed files, failing check, verification command, and the one decision a human must make? Otherwise implementation moved faster than acceptance.

@ramy_abousetta @RCouhig All good, Leam usually subs the back line on the 85th minute! 😀

@sjmaple @RCouhig Get me in as a fullback, just don't expect 90 minutes 😂😂

Here we go! 🇪🇬🇪🇬

The most expensive model in the benchmark wasn't the best value. Rob Willoughby and Simon Maple ( @sjmaple ) evaluated 19 model configurations on real agentic tasks and found that DeepSeek V4 Flash scored 82.3 while costing just $0.0236 per task. Claude Haiku 4.5 scored 82.9 at roughly four times the cost, while DeepSeek V4 Pro scored 85.3 at nearly eight times the cost. The interesting part isn't that Flash beat stronger models. It didn't. The interesting part is how little quality was gained for how much additional spend. That becomes a very different conversation once you're running agents at scale. A model that looks marginally better on a benchmark can end up costing dramatically more over the course of a year, especially when agent workloads start growing. The benchmark also surfaced something that many teams probably aren't measuring closely enough. The biggest performance jump didn't come from switching models. It came from adding the right skill. DeepSeek V4 Flash moved from 64.1 to 82.3 with skill context applied, which raises an uncomfortable question about how much of agent performance is actually model selection versus everything built around the model. The full breakdown is worth reading, particularly the sections on points-per-dollar, turn counts, and why the cheapest model in the benchmark ended up being one of the most interesting. Read the full blog here: tessl.io/blog/same-qual…

Ryan Lopopolo tracked PR throughput on his OpenAI team from 3.5 per engineer per week up to 70 — not through adding headcount, but through iterating on the model and the harness together. Every revision of GPT-5 from 5.2 onward compounded on the last, and this clip shows exactly what that felt like from inside the team. Watch the full episode at youtu.be/MFQIKbr1IEo or listen wherever you get your podcasts. #AI #agenticcoding #claudecode #codex #AIskills

Developers using AI tools are creating and merging twice as many pull requests — but AI-generated PRs have a 60/40 merge rate compared to 80/20 for humans. That gap reveals something important about how agents are actually being used in the wild: probing, experimenting, spawning throwaway work. Jellyfish's Nick Arcolano breaks down what the data actually says. Watch the full episode at youtu.be/GbHfzFcIa0o or listen wherever you get your podcasts #AI #agenticcoding #claudecode #codex #AIskills

@arungupta @nvidia Amazing! Aditya looks all grown up now! Must be great to work together, congrats!

Started a new job as Director, Open Source Ecosystem and Developer Platform at @nvidia linkedin.com/posts/arunpgup…

@liran_tal @ainativedev @tessl_io @SammyHep Also, doesn't that box of goodies reek of @SammyHep 🤣

@liran_tal @ainativedev @tessl_io @SammyHep Appreciate you coming over and being so active! Loved seeing you again - miss you buddy!

Thank you for inviting me to speak at @ainativedev and meet some of the coolest AI builders talent and minds in London 🚀 Appreciate @tessl_io for building this and @SammyHep, @sjmaple and team for all the effort to organize and make it a stellar AI event